增加授权认证

- Add explicit return type annotation `Record<string, string[]>` to getAcceptConfig function
- Improve type safety and IDE autocomplete for file type configuration
- Enhance code clarity for accepted file types mapping in import dialog

.github/workflows/docker-build.yml

@@ -16,7 +16,7 @@ env:
   IMAGE_PREFIX: yyhuni
 
 permissions:
-  contents: write  # 允许修改仓库内容
+  contents: write
 
 jobs:
   build:
@@ -27,18 +27,23 @@ jobs:
           - image: xingrin-server
             dockerfile: docker/server/Dockerfile
             context: .
+            platforms: linux/amd64,linux/arm64
           - image: xingrin-frontend
             dockerfile: docker/frontend/Dockerfile
             context: .
+            platforms: linux/amd64  # ARM64 构建时 Next.js 在 QEMU 下会崩溃
           - image: xingrin-worker
             dockerfile: docker/worker/Dockerfile
             context: .
+            platforms: linux/amd64,linux/arm64
           - image: xingrin-nginx
             dockerfile: docker/nginx/Dockerfile
             context: .
+            platforms: linux/amd64,linux/arm64
           - image: xingrin-agent
             dockerfile: docker/agent/Dockerfile
             context: .
+            platforms: linux/amd64,linux/arm64
 
     steps:
       - name: Checkout
@@ -48,7 +53,6 @@ jobs:
         run: |
           echo "=== Before cleanup ==="
           df -h
-          # 删除不需要的大型软件包
           sudo rm -rf /usr/share/dotnet
           sudo rm -rf /usr/local/lib/android
           sudo rm -rf /opt/ghc
@@ -95,40 +99,72 @@ jobs:
         with:
           context: ${{ matrix.context }}
           file: ${{ matrix.dockerfile }}
-          platforms: linux/amd64,linux/arm64
+          platforms: ${{ matrix.platforms }}
           push: true
           tags: |
             ${{ env.IMAGE_PREFIX }}/${{ matrix.image }}:${{ steps.version.outputs.VERSION }}
             ${{ steps.version.outputs.IS_RELEASE == 'true' && format('{0}/{1}:latest', env.IMAGE_PREFIX, matrix.image) || '' }}
-          cache-from: |
-            type=gha
-            type=registry,ref=${{ env.IMAGE_PREFIX }}/${{ matrix.image }}:buildcache
-          cache-to: |
-            type=gha,mode=max
-            type=registry,ref=${{ env.IMAGE_PREFIX }}/${{ matrix.image }}:buildcache,mode=max
+          build-args: |
+            IMAGE_TAG=${{ steps.version.outputs.VERSION }}
+          cache-from: type=gha,scope=${{ matrix.image }}
+          cache-to: type=gha,mode=max,scope=${{ matrix.image }}
+          provenance: false
+          sbom: false
 
   # 所有镜像构建成功后，更新 VERSION 文件
+  # 根据 tag 所在的分支更新对应分支的 VERSION 文件
   update-version:
     runs-on: ubuntu-latest
-    needs: build  # 等待所有 build job 完成
+    needs: build
     if: startsWith(github.ref, 'refs/tags/v')
     steps:
-      - name: Checkout
+      - name: Checkout repository
         uses: actions/checkout@v4
         with:
-          ref: main
+          fetch-depth: 0  # 获取完整历史，用于判断 tag 所在分支
           token: ${{ secrets.GITHUB_TOKEN }}
 
+      - name: Determine source branch and version
+        id: branch
+        run: |
+          VERSION="${GITHUB_REF#refs/tags/}"
+          
+          # 查找包含此 tag 的分支
+          BRANCHES=$(git branch -r --contains ${{ github.ref_name }})
+          echo "Branches containing tag: $BRANCHES"
+          
+          # 判断 tag 来自哪个分支
+          if echo "$BRANCHES" | grep -q "origin/main"; then
+            TARGET_BRANCH="main"
+            UPDATE_LATEST="true"
+          elif echo "$BRANCHES" | grep -q "origin/dev"; then
+            TARGET_BRANCH="dev"
+            UPDATE_LATEST="false"
+          else
+            echo "Warning: Tag not found in main or dev branch, defaulting to main"
+            TARGET_BRANCH="main"
+            UPDATE_LATEST="false"
+          fi
+          
+          echo "BRANCH=$TARGET_BRANCH" >> $GITHUB_OUTPUT
+          echo "VERSION=$VERSION" >> $GITHUB_OUTPUT
+          echo "UPDATE_LATEST=$UPDATE_LATEST" >> $GITHUB_OUTPUT
+          echo "Will update VERSION on branch: $TARGET_BRANCH"
+
+      - name: Checkout target branch
+        run: |
+          git checkout ${{ steps.branch.outputs.BRANCH }}
+
       - name: Update VERSION file
         run: |
-          VERSION="${GITHUB_REF#refs/tags/}"
+          VERSION="${{ steps.branch.outputs.VERSION }}"
           echo "$VERSION" > VERSION
-          echo "Updated VERSION to $VERSION"
+          echo "Updated VERSION to $VERSION on branch ${{ steps.branch.outputs.BRANCH }}"
 
       - name: Commit and push
         run: |
           git config user.name "github-actions[bot]"
           git config user.email "github-actions[bot]@users.noreply.github.com"
           git add VERSION
-          git diff --staged --quiet || git commit -m "chore: bump version to ${GITHUB_REF#refs/tags/}"
-          git push
+          git diff --staged --quiet || git commit -m "chore: bump version to ${{ steps.branch.outputs.VERSION }}"
+          git push origin ${{ steps.branch.outputs.BRANCH }}

.gitignore

@@ -96,6 +96,7 @@ backend/vendor/
 .idea/
 .cursor/
 .claude/
+.kiro/
 .playwright-mcp/
 *.swp
 *.swo
@@ -131,3 +132,5 @@ temp/
 
 HGETALL
 KEYS
+vuln_scan/input_endpoints.txt
+open-in-v0

LICENSE

@@ -1,131 +1,674 @@
-# PolyForm Noncommercial License 1.0.0
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
 
-<https://polyformproject.org/licenses/noncommercial/1.0.0>
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
 
-## Acceptance
+                            Preamble
 
-In order to get any license under these terms, you must agree
-to them as both strict obligations and conditions to all
-your licenses.
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
 
-## Copyright License
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
 
-The licensor grants you a copyright license for the
-software to do everything you might do with the software
-that would otherwise infringe the licensor's copyright
-in it for any permitted purpose.  However, you may
-only distribute the software according to [Distribution
-License](#distribution-license) and make changes or new works
-based on the software according to [Changes and New Works
-License](#changes-and-new-works-license).
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
 
-## Distribution License
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
 
-The licensor grants you an additional copyright license
-to distribute copies of the software.  Your license
-to distribute covers distributing the software with
-changes and new works permitted by [Changes and New Works
-License](#changes-and-new-works-license).
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
 
-## Notices
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
 
-You must ensure that anyone who gets a copy of any part of
-the software from you also gets a copy of these terms or the
-URL for them above, as well as copies of any plain-text lines
-beginning with `Required Notice:` that the licensor provided
-with the software.  For example:
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
 
-> Required Notice: Copyright Yuhang Yang (yyhuni)
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
 
-## Changes and New Works License
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
 
-The licensor grants you an additional copyright license to
-make changes and new works based on the software for any
-permitted purpose.
+  The precise terms and conditions for copying, distribution and
+modification follow.
 
-## Patent License
+                       TERMS AND CONDITIONS
 
-The licensor grants you a patent license for the software that
-covers patent claims the licensor can license, or becomes able
-to license, that you would infringe by using the software.
+  0. Definitions.
 
-## Noncommercial Purposes
+  "This License" refers to version 3 of the GNU General Public License.
 
-Any noncommercial purpose is a permitted purpose.
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
 
-## Personal Uses
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
 
-Personal use for research, experiment, and testing for
-the benefit of public knowledge, personal study, private
-entertainment, hobby projects, amateur pursuits, or religious
-observance, without any anticipated commercial application,
-is use for a permitted purpose.
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
 
-## Noncommercial Organizations
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
 
-Use by any charitable organization, educational institution,
-public research organization, public safety or health
-organization, environmental protection organization,
-or government institution is use for a permitted purpose
-regardless of the source of funding or obligations resulting
-from the funding.
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
 
-## Fair Use
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
 
-You may have "fair use" rights for the software under the
-law. These terms do not limit them.
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
 
-## No Other Rights
+  1. Source Code.
 
-These terms do not allow you to sublicense or transfer any of
-your licenses to anyone else, or prevent the licensor from
-granting licenses to anyone else.  These terms do not imply
-any other licenses.
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
 
-## Patent Defense
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
 
-If you make any written claim that the software infringes or
-contributes to infringement of any patent, your patent license
-for the software granted under these terms ends immediately. If
-your company makes such a claim, your patent license ends
-immediately for work on behalf of your company.
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
 
-## Violations
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
 
-The first time you are notified in writing that you have
-violated any of these terms, or done anything with the software
-not covered by your licenses, your licenses can nonetheless
-continue if you come into full compliance with these terms,
-and take practical steps to correct past violations, within
-32 days of receiving notice.  Otherwise, all your licenses
-end immediately.
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
 
-## No Liability
+  The Corresponding Source for a work in source code form is that
+same work.
 
-***As far as the law allows, the software comes as is, without
-any warranty or condition, and the licensor will not be liable
-to you for any damages arising out of these terms or the use
-or nature of the software, under any kind of legal claim.***
+  2. Basic Permissions.
 
-## Definitions
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
 
-The **licensor** is the individual or entity offering these
-terms, and the **software** is the software the licensor makes
-available under these terms.
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
 
-**You** refers to the individual or entity agreeing to these
-terms.
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
 
-**Your company** is any legal entity, sole proprietorship,
-or other kind of organization that you work for, plus all
-organizations that have control over, are under the control of,
-or are under common control with that organization.  **Control**
-means ownership of substantially all the assets of an entity,
-or the power to direct its management and policies by vote,
-contract, or otherwise.  Control can be direct or indirect.
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
 
-**Your licenses** are all the licenses granted to you for the
-software under these terms.
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
 
-**Use** means anything you do with the software requiring one
-of your licenses.
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<https://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<https://www.gnu.org/licenses/why-not-lgpl.html>.

README.md

@@ -1,27 +1,40 @@
-<h1 align="center">Xingrin - 星环</h1>
+<h1 align="center">XingRin - 星环</h1>
 
 <p align="center">
-  <b>一款现代化的企业级漏洞扫描与资产管理平台</b><br>
-  提供自动化安全检测、资产发现、漏洞管理等功能
+  <b>🛡️ 攻击面管理平台 (ASM) | 自动化资产发现与漏洞扫描系统</b>
 </p>
 
 <p align="center">
-  <b>🌗 明暗模式切换</b>
+  <a href="https://github.com/yyhuni/xingrin/stargazers"><img src="https://img.shields.io/github/stars/yyhuni/xingrin?style=flat-square&logo=github" alt="GitHub stars"></a>
+  <a href="https://github.com/yyhuni/xingrin/network/members"><img src="https://img.shields.io/github/forks/yyhuni/xingrin?style=flat-square&logo=github" alt="GitHub forks"></a>
+  <a href="https://github.com/yyhuni/xingrin/issues"><img src="https://img.shields.io/github/issues/yyhuni/xingrin?style=flat-square&logo=github" alt="GitHub issues"></a>
+  <a href="https://github.com/yyhuni/xingrin/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-PolyForm%20NC-blue?style=flat-square" alt="License"></a>
 </p>
 
 <p align="center">
-  <img src="docs/screenshots/light.png" alt="Light Mode" width="49%">
-  <img src="docs/screenshots/dark.png" alt="Dark Mode" width="49%">
+  <a href="#-功能特性">功能特性</a> •
+  <a href="#-快速开始">快速开始</a> •
+  <a href="#-文档">文档</a> •
+  <a href="#-技术栈">技术栈</a> •
+  <a href="#-反馈与贡献">反馈与贡献</a>
 </p>
 
 <p align="center">
-  <b>🎨 多种 UI 主题</b>
+  <sub>🔍 关键词: ASM | 攻击面管理 | 漏洞扫描 | 资产发现 | Bug Bounty | 渗透测试 | Nuclei | 子域名枚举 | EASM</sub>
+</p>
+
+---
+
+
+<p align="center">
+  <b>🎨 现代化 UI </b>
 </p>
 
 <p align="center">
-  <img src="docs/screenshots/bubblegum.png" alt="Bubblegum" width="32%">
-  <img src="docs/screenshots/cosmic-night.png" alt="Cosmic Night" width="32%">
-  <img src="docs/screenshots/quantum-rose.png" alt="Quantum Rose" width="32%">
+  <img src="docs/screenshots/light.png" alt="Light Mode" width="24%">
+  <img src="docs/screenshots/bubblegum.png" alt="Bubblegum" width="24%">
+  <img src="docs/screenshots/cosmic-night.png" alt="Cosmic Night" width="24%">
+  <img src="docs/screenshots/quantum-rose.png" alt="Quantum Rose" width="24%">
 </p>
 
 ## 📚 文档
@@ -31,6 +44,7 @@
 - [🔄 版本管理](./docs/version-management.md) - Git Tag 驱动的自动化版本管理系统
 - [📦 Nuclei 模板架构](./docs/nuclei-template-architecture.md) - 模板仓库的存储与同步
 - [📖 字典文件架构](./docs/wordlist-architecture.md) - 字典文件的存储与同步
+- [🔍 扫描流程架构](./docs/scan-flow-architecture.md) - 完整扫描流程与工具编排
 
 
 ---
@@ -48,6 +62,54 @@
 - **自定义流程** - YAML 配置扫描流程，灵活编排
 - **定时扫描** - Cron 表达式配置，自动化周期扫描
 
+#### 扫描流程架构
+
+完整的扫描流程包括：子域名发现、端口扫描、站点发现、URL 收集、目录扫描、漏洞扫描等阶段
+
+```mermaid
+flowchart LR
+    START["开始扫描"]
+    
+    subgraph STAGE1["阶段 1: 资产发现"]
+        direction TB
+        SUB["子域名发现<br/>subfinder, amass, puredns"]
+        PORT["端口扫描<br/>naabu"]
+        SITE["站点识别<br/>httpx"]
+        SUB --> PORT --> SITE
+    end
+    
+    subgraph STAGE2["阶段 2: 深度分析"]
+        direction TB
+        URL["URL 收集<br/>waymore, katana"]
+        DIR["目录扫描<br/>ffuf"]
+    end
+    
+    subgraph STAGE3["阶段 3: 漏洞检测"]
+        VULN["漏洞扫描<br/>nuclei, dalfox"]
+    end
+    
+    FINISH["扫描完成"]
+    
+    START --> STAGE1
+    SITE --> STAGE2
+    STAGE2 --> STAGE3
+    STAGE3 --> FINISH
+    
+    style START fill:#34495e,stroke:#2c3e50,stroke-width:2px,color:#fff
+    style FINISH fill:#27ae60,stroke:#229954,stroke-width:2px,color:#fff
+    style STAGE1 fill:#3498db,stroke:#2980b9,stroke-width:2px,color:#fff
+    style STAGE2 fill:#9b59b6,stroke:#8e44ad,stroke-width:2px,color:#fff
+    style STAGE3 fill:#e67e22,stroke:#d35400,stroke-width:2px,color:#fff
+    style SUB fill:#5dade2,stroke:#3498db,stroke-width:1px,color:#fff
+    style PORT fill:#5dade2,stroke:#3498db,stroke-width:1px,color:#fff
+    style SITE fill:#5dade2,stroke:#3498db,stroke-width:1px,color:#fff
+    style URL fill:#bb8fce,stroke:#9b59b6,stroke-width:1px,color:#fff
+    style DIR fill:#bb8fce,stroke:#9b59b6,stroke-width:1px,color:#fff
+    style VULN fill:#f0b27a,stroke:#e67e22,stroke-width:1px,color:#fff
+```
+
+详细说明请查看 [扫描流程架构文档](./docs/scan-flow-architecture.md)
+
 ### 🖥️ 分布式架构
 - **多节点扫描** - 支持部署多个 Worker 节点，横向扩展扫描能力
 - **本地节点** - 零配置，安装即自动注册本地 Docker Worker
@@ -56,62 +118,46 @@
 - **节点监控** - 实时心跳检测，CPU/内存/磁盘状态监控
 - **断线重连** - 节点离线自动检测，恢复后自动重新接入
 
-```
-┌─────────────────────────────────────────────────────────────────┐
-│                         主服务器 (Master)                         │
-│  ┌─────────┐  ┌─────────┐  ┌─────────┐  ┌─────────┐            │
-│  │ Next.js │  │ Django  │  │ Postgres│  │  Redis  │            │
-│  │ 前端    │  │ 后端    │  │ 数据库  │  │  缓存   │            │
-│  └─────────┘  └────┬────┘  └─────────┘  └─────────┘            │
-│                    │                                            │
-│              ┌─────┴─────┐                                      │
-│              │ 任务调度器 │                                      │
-│              │ Scheduler │                                      │
-│              └─────┬─────┘                                      │
-└────────────────────┼────────────────────────────────────────────┘
-                     │
-        ┌────────────┼────────────┐
-        │            │            │
-        ▼            ▼            ▼
-┌───────────┐ ┌───────────┐ ┌───────────┐
-│  Worker 1 │ │  Worker 2 │ │  Worker N │
-│  (本地)   │ │  (远程)   │ │  (远程)   │
-├───────────┤ ├───────────┤ ├───────────┤
-│ • Nuclei  │ │ • Nuclei  │ │ • Nuclei  │
-│ • httpx   │ │ • httpx   │ │ • httpx   │
-│ • naabu   │ │ • naabu   │ │ • naabu   │
-│ • ...     │ │ • ...     │ │ • ...     │
-├───────────┤ ├───────────┤ ├───────────┤
-│  心跳上报  │ │  心跳上报  │ │  心跳上报  │
-└───────────┘ └───────────┘ └───────────┘
+```mermaid
+flowchart TB
+    subgraph MASTER["主服务器 (Master Server)"]
+        direction TB
+        
+        REDIS["Redis 负载缓存"]
+        
+        subgraph SCHEDULER["任务调度器 (Task Distributor)"]
+            direction TB
+            SUBMIT["接收扫描任务"]
+            SELECT["负载感知选择"]
+            DISPATCH["智能分发"]
+            
+            SUBMIT --> SELECT
+            SELECT --> DISPATCH
+        end
+        
+        REDIS -.负载数据.-> SELECT
+    end
+    
+    subgraph WORKERS["Worker 节点集群"]
+        direction TB
+        
+        W1["Worker 1 (本地)<br/>CPU: 45% | MEM: 60%"]
+        W2["Worker 2 (远程)<br/>CPU: 30% | MEM: 40%"]
+        W3["Worker N (远程)<br/>CPU: 90% | MEM: 85%"]
+    end
+    
+    DISPATCH -->|任务分发| W1
+    DISPATCH -->|任务分发| W2
+    DISPATCH -->|高负载跳过| W3
+    
+    W1 -.心跳上报.-> REDIS
+    W2 -.心跳上报.-> REDIS
+    W3 -.心跳上报.-> REDIS
 ```
 
 ### 📊 可视化界面
 - **数据统计** - 资产/漏洞统计仪表盘
 - **实时通知** - WebSocket 消息推送
-- **暗色主题** - 支持明暗主题切换
-
----
-
-## 🛠️ 技术栈
-
-- **前端**: Next.js + React + TailwindCSS
-- **后端**: Django + Django REST Framework
-- **数据库**: PostgreSQL + Redis
-- **部署**: Docker + Nginx
-
-### 🔧 内置扫描工具
-
-| 类别 | 工具 |
-|------|------|
-| 子域名爆破 | puredns, massdns, dnsgen |
-| 被动发现 | subfinder, amass, assetfinder, Sublist3r |
-| 端口扫描 | naabu |
-| 站点发现 | httpx |
-| 目录扫描 | ffuf |
-| 爬虫 | katana |
-| 被动URL收集 | waymore, uro |
-| 漏洞扫描 | nuclei, dalfox |
 
 ---
 
@@ -120,7 +166,7 @@
 ### 环境要求
 
 - **操作系统**: Ubuntu 20.04+ / Debian 11+ （推荐）
-- **硬件**: 2核 4G 内存起步，10GB+ 磁盘空间
+- **硬件**: 2核 4G 内存起步，20GB+ 磁盘空间
 
 ### 一键安装
 
@@ -132,13 +178,18 @@ cd xingrin
 # 安装并启动（生产模式）
 sudo ./install.sh
 
-# 开发模式
-sudo ./install.sh --dev
+# 🇨🇳 中国大陆用户推荐使用镜像加速（第三方加速服务可能会失效，不保证长期可用）
+sudo ./install.sh --mirror
 ```
 
+> **💡 --mirror 参数说明**
+> - 自动配置 Docker 镜像加速（国内镜像源）
+> - 加速 Git 仓库克隆（Nuclei 模板等）
+> - 大幅提升安装速度，避免网络超时
+
 ### 访问服务
 
-- **Web 界面**: `https://localhost` 或 `http://localhost`
+- **Web 界面**: `https://ip:8083` 
 
 ### 常用命令
 
@@ -154,19 +205,12 @@ sudo ./restart.sh
 
 # 卸载
 sudo ./uninstall.sh
-
-# 更新
-sudo ./update.sh
 ```
-## 日志
-- 项目日志：/opt/xingrin/logs 下存储了这个项目的运行日志信息，error文件存储了错误相关信息，xingrin.log存储了包括错误在内的所有项目日志
-- 工具调用日志：/opt/xingrin/results 下存储了工具的运行结果日志，比如naabu，httpx等的结果调用日志
 
 ## 🤝 反馈与贡献
 
 - 🐛 **如果发现 Bug** 可以点击右边链接进行提交 [Issue](https://github.com/yyhuni/xingrin/issues)
 - 💡 **有新想法，比如UI设计，功能设计等** 欢迎点击右边链接进行提交建议 [Issue](https://github.com/yyhuni/xingrin/issues)
-- 🔧 **想参与开发？** 关注我公众号与我个人联系
 
 ## 📧 联系
 - 目前版本就我个人使用，可能会有很多边界问题
@@ -192,22 +236,30 @@ sudo ./update.sh
 - 遵守所在地区的法律法规
 - 承担因滥用产生的一切后果
 
+## 🌟 Star History
+
+如果这个项目对你有帮助，请给一个 ⭐ Star 支持一下！
+
+[![Star History Chart](https://api.star-history.com/svg?repos=yyhuni/xingrin&type=Date)](https://star-history.com/#yyhuni/xingrin&Date)
+
 ## 📄 许可证
 
-本项目采用 [PolyForm Noncommercial License 1.0.0](LICENSE) 许可证。
+本项目采用 [GNU General Public License v3.0](LICENSE) 许可证。
 
 ### 允许的用途
 
 - ✅ 个人学习和研究
-- ✅ 非商业安全测试
-- ✅ 教育机构使用
-- ✅ 非营利组织使用
+- ✅ 商业和非商业使用
+- ✅ 修改和分发
+- ✅ 专利使用
+- ✅ 私人使用
 
-### 禁止的用途
+### 义务和限制
 
-- ❌ **商业用途**（包括但不限于：出售、商业服务、SaaS 等）
+- 📋 **开源义务**：分发时必须提供源代码
+- 📋 **相同许可**：衍生作品必须使用相同许可证
+- 📋 **版权声明**：必须保留原始版权和许可证声明
+- ❌ **责任免除**：不提供任何担保
 - ❌ 未经授权的渗透测试
 - ❌ 任何违法行为
 
-如需商业授权，请联系作者。
-

VERSION

@@ -1 +1 @@
-v1.0.10
+v1.2.8-dev

backend/apps/asset/dtos/asset/directory_dto.py

@@ -7,7 +7,6 @@ from typing import Optional
 @dataclass
 class DirectoryDTO:
     """目录数据传输对象"""
-    website_id: int
     target_id: int
     url: str
     status: Optional[int] = None

backend/apps/asset/dtos/asset/website_dto.py

@@ -9,7 +9,7 @@ class WebSiteDTO:
     """网站数据传输对象"""
     target_id: int
     url: str
-    host: str
+    host: str = ''
     title: str = ''
     status_code: Optional[int] = None
     content_length: Optional[int] = None

backend/apps/asset/dtos/snapshot/directory_snapshot_dto.py

@@ -12,11 +12,10 @@ class DirectorySnapshotDTO:
     
     用于保存扫描过程中发现的目录信息到快照表
     
-    注意：website_id 和 target_id 只用于传递数据和转换为资产 DTO，不会保存到快照表中。
+    注意：target_id 只用于传递数据和转换为资产 DTO，不会保存到快照表中。
     快照只属于 scan。
     """
     scan_id: int
-    website_id: int  # 仅用于传递数据，不保存到数据库
     target_id: int  # 仅用于传递数据，不保存到数据库
     url: str
     status: Optional[int] = None
@@ -36,7 +35,6 @@ class DirectorySnapshotDTO:
             DirectoryDTO: 资产表 DTO
         """
         return DirectoryDTO(
-            website_id=self.website_id,
             target_id=self.target_id,
             url=self.url,
             status=self.status,

backend/apps/asset/models/asset_models.py

@@ -4,13 +4,6 @@ from django.contrib.postgres.fields import ArrayField
 from django.core.validators import MinValueValidator, MaxValueValidator
 
 
-class SoftDeleteManager(models.Manager):
-    """软删除管理器：默认只返回未删除的记录"""
-    
-    def get_queryset(self):
-        return super().get_queryset().filter(deleted_at__isnull=True)
-
-
 class Subdomain(models.Model):
     """
     子域名模型（纯资产表）
@@ -29,33 +22,24 @@ class Subdomain(models.Model):
         help_text='所属的扫描目标（主关联字段，表示所属关系，不能为空）'
     )
     name = models.CharField(max_length=1000, help_text='子域名名称')
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='首次发现时间')
-    
-    # ==================== 软删除字段 ====================
-    deleted_at = models.DateTimeField(null=True, blank=True, db_index=True, help_text='删除时间（NULL表示未删除）')
-    
-    # ==================== 管理器 ====================
-    objects = SoftDeleteManager()  # 默认管理器：只返回未删除的记录
-    all_objects = models.Manager()  # 全量管理器：包括已删除的记录（用于硬删除）
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'subdomain'
         verbose_name = '子域名'
         verbose_name_plural = '子域名'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['-created_at']),
             models.Index(fields=['name', 'target']),  # 复合索引，优化 get_by_names_and_target_id 批量查询
             models.Index(fields=['target']),     # 优化从target_id快速查找下面的子域名
             models.Index(fields=['name']),            # 优化从name快速查找子域名，搜索场景
-            models.Index(fields=['deleted_at', '-discovered_at']),  # 软删除 + 时间索引
         ]
         constraints = [
-            # 部分唯一约束：只对未删除记录生效
+            # 普通唯一约束：name + target 组合唯一
             models.UniqueConstraint(
                 fields=['name', 'target'],
-                condition=models.Q(deleted_at__isnull=True),
-                name='unique_name_target_active'
+                name='unique_subdomain_name_target'
             )
         ]
 
@@ -87,7 +71,7 @@ class Endpoint(models.Model):
         default='',
         help_text='重定向地址（HTTP 3xx 响应头 Location）'
     )
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
     title = models.CharField(
         max_length=1000,
         blank=True,
@@ -139,33 +123,25 @@ class Endpoint(models.Model):
         default=list,
         help_text='匹配的GF模式列表，用于识别敏感端点（如api, debug, config等）'
     )
-    
-    # ==================== 软删除字段 ====================
-    deleted_at = models.DateTimeField(null=True, blank=True, db_index=True, help_text='删除时间（NULL表示未删除）')
-    
-    # ==================== 管理器 ====================
-    objects = SoftDeleteManager()  # 默认管理器：只返回未删除的记录
-    all_objects = models.Manager()  # 全量管理器：包括已删除的记录（用于硬删除）
 
     class Meta:
         db_table = 'endpoint'
         verbose_name = '端点'
         verbose_name_plural = '端点'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['-created_at']),
             models.Index(fields=['target']),       # 优化从target_id快速查找下面的端点（主关联字段）
             models.Index(fields=['url']),          # URL索引，优化查询性能
             models.Index(fields=['host']),         # host索引，优化根据主机名查询
             models.Index(fields=['status_code']),  # 状态码索引，优化筛选
-            models.Index(fields=['deleted_at', '-discovered_at']),  # 软删除 + 时间索引
+            models.Index(fields=['title']),        # title索引，优化智能过滤搜索
         ]
         constraints = [
-            # 部分唯一约束：只对未删除记录生效
+            # 普通唯一约束：url + target 组合唯一
             models.UniqueConstraint(
                 fields=['url', 'target'],
-                condition=models.Q(deleted_at__isnull=True),
-                name='unique_endpoint_url_target_active'
+                name='unique_endpoint_url_target'
             )
         ]
 
@@ -197,7 +173,7 @@ class WebSite(models.Model):
         default='',
         help_text='重定向地址（HTTP 3xx 响应头 Location）'
     )
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
     title = models.CharField(
         max_length=1000,
         blank=True,
@@ -243,32 +219,25 @@ class WebSite(models.Model):
         blank=True,
         help_text='是否支持虚拟主机'
     )
-    
-    # ==================== 软删除字段 ====================
-    deleted_at = models.DateTimeField(null=True, blank=True, db_index=True, help_text='删除时间（NULL表示未删除）')
-    
-    # ==================== 管理器 ====================
-    objects = SoftDeleteManager()  # 默认管理器：只返回未删除的记录
-    all_objects = models.Manager()  # 全量管理器：包括已删除的记录（用于硬删除）
 
     class Meta:
         db_table = 'website'
         verbose_name = '站点'
         verbose_name_plural = '站点'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['-created_at']),
             models.Index(fields=['url']),  # URL索引，优化查询性能
             models.Index(fields=['host']),  # host索引，优化根据主机名查询
             models.Index(fields=['target']),     # 优化从target_id快速查找下面的站点
-            models.Index(fields=['deleted_at', '-discovered_at']),  # 软删除 + 时间索引
+            models.Index(fields=['title']),      # title索引，优化智能过滤搜索
+            models.Index(fields=['status_code']),  # 状态码索引，优化智能过滤搜索
         ]
         constraints = [
-            # 部分唯一约束：只对未删除记录生效
+            # 普通唯一约束：url + target 组合唯一
             models.UniqueConstraint(
                 fields=['url', 'target'],
-                condition=models.Q(deleted_at__isnull=True),
-                name='unique_website_url_target_active'
+                name='unique_website_url_target'
             )
         ]
 
@@ -282,19 +251,11 @@ class Directory(models.Model):
     """
 
     id = models.AutoField(primary_key=True)
-    website = models.ForeignKey(
-        'Website',
-        on_delete=models.CASCADE,
-        related_name='directories',
-        help_text='所属的站点（主关联字段，表示所属关系，不能为空）'
-    )
     target = models.ForeignKey(
-        'targets.Target',  # 使用字符串引用
+        'targets.Target',
         on_delete=models.CASCADE,
         related_name='directories',
-        null=True,
-        blank=True,
-        help_text='所属的扫描目标（冗余字段，用于快速查询）'
+        help_text='所属的扫描目标'
     )
     
     url = models.CharField(
@@ -335,34 +296,24 @@ class Directory(models.Model):
         help_text='请求耗时（单位：纳秒）'
     )
     
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
-    
-    # ==================== 软删除字段 ====================
-    deleted_at = models.DateTimeField(null=True, blank=True, db_index=True, help_text='删除时间（NULL表示未删除）')
-    
-    # ==================== 管理器 ====================
-    objects = SoftDeleteManager()  # 默认管理器：只返回未删除的记录
-    all_objects = models.Manager()  # 全量管理器：包括已删除的记录（用于硬删除）
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'directory'
         verbose_name = '目录'
         verbose_name_plural = '目录'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['-created_at']),
             models.Index(fields=['target']),     # 优化从target_id快速查找下面的目录
             models.Index(fields=['url']),        # URL索引，优化搜索和唯一约束
-            models.Index(fields=['website']),    # 站点索引，优化按站点查询
             models.Index(fields=['status']),     # 状态码索引，优化筛选
-            models.Index(fields=['deleted_at', '-discovered_at']),  # 软删除 + 时间索引
         ]
         constraints = [
-            # 部分唯一约束：只对未删除记录生效
+            # 普通唯一约束：target + url 组合唯一
             models.UniqueConstraint(
-                fields=['website', 'url'],
-                condition=models.Q(deleted_at__isnull=True),
-                name='unique_directory_url_website_active'
+                fields=['target', 'url'],
+                name='unique_directory_url_target'
             ),
         ]
 
@@ -410,43 +361,29 @@ class HostPortMapping(models.Model):
     )
     
     # ==================== 时间字段 ====================
-    discovered_at = models.DateTimeField(
+    created_at = models.DateTimeField(
         auto_now_add=True,
-        help_text='发现时间'
+        help_text='创建时间'
     )
-    
-    # ==================== 软删除字段 ====================
-    deleted_at = models.DateTimeField(
-        null=True,
-        blank=True,
-        db_index=True,
-        help_text='删除时间（NULL表示未删除）'
-    )
-    
-    # ==================== 管理器 ====================
-    objects = SoftDeleteManager()  # 默认管理器：只返回未删除的记录
-    all_objects = models.Manager()  # 全量管理器：包括已删除的记录（用于硬删除）
 
     class Meta:
         db_table = 'host_port_mapping'
         verbose_name = '主机端口映射'
         verbose_name_plural = '主机端口映射'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['target']),           # 优化按目标查询
             models.Index(fields=['host']),             # 优化按主机名查询
             models.Index(fields=['ip']),               # 优化按IP查询
             models.Index(fields=['port']),             # 优化按端口查询
             models.Index(fields=['host', 'ip']),       # 优化组合查询
-            models.Index(fields=['-discovered_at']),   # 优化时间排序
-            models.Index(fields=['deleted_at', '-discovered_at']),  # 软删除 + 时间索引
+            models.Index(fields=['-created_at']),   # 优化时间排序
         ]
         constraints = [
-            # 复合唯一约束：target + host + ip + port 组合唯一（只对未删除记录生效）
+            # 复合唯一约束：target + host + ip + port 组合唯一
             models.UniqueConstraint(
                 fields=['target', 'host', 'ip', 'port'],
-                condition=models.Q(deleted_at__isnull=True),
-                name='unique_target_host_ip_port_active'
+                name='unique_target_host_ip_port'
             ),
         ]
 
@@ -474,7 +411,7 @@ class Vulnerability(models.Model):
     )
     
     # ==================== 核心字段 ====================
-    url = models.TextField(help_text='漏洞所在的URL')
+    url = models.CharField(max_length=2000, help_text='漏洞所在的URL')
     vuln_type = models.CharField(max_length=100, help_text='漏洞类型（如 xss, sqli）')
     severity = models.CharField(
         max_length=20,
@@ -488,27 +425,20 @@ class Vulnerability(models.Model):
     raw_output = models.JSONField(blank=True, default=dict, help_text='工具原始输出')
     
     # ==================== 时间字段 ====================
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='首次发现时间')
-    
-    # ==================== 软删除字段 ====================
-    deleted_at = models.DateTimeField(null=True, blank=True, db_index=True, help_text='删除时间（NULL表示未删除）')
-    
-    # ==================== 管理器 ====================
-    objects = SoftDeleteManager()
-    all_objects = models.Manager()
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'vulnerability'
         verbose_name = '漏洞'
         verbose_name_plural = '漏洞'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['target']),
             models.Index(fields=['vuln_type']),
             models.Index(fields=['severity']),
             models.Index(fields=['source']),
-            models.Index(fields=['-discovered_at']),
-            models.Index(fields=['deleted_at', '-discovered_at']),
+            models.Index(fields=['url']),          # url索引，优化智能过滤搜索
+            models.Index(fields=['-created_at']),
         ]
 
     def __str__(self):

backend/apps/asset/models/snapshot_models.py

@@ -15,17 +15,17 @@ class SubdomainSnapshot(models.Model):
     )
     
     name = models.CharField(max_length=1000, help_text='子域名名称')
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
     
     class Meta:
         db_table = 'subdomain_snapshot'
         verbose_name = '子域名快照'
         verbose_name_plural = '子域名快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),
             models.Index(fields=['name']),
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['-created_at']),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个子域名只能记录一次
@@ -70,18 +70,19 @@ class WebsiteSnapshot(models.Model):
     )
     body_preview = models.TextField(blank=True, default='', help_text='响应体预览')
     vhost = models.BooleanField(null=True, blank=True, help_text='虚拟主机标志')
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'website_snapshot'
         verbose_name = '网站快照'
         verbose_name_plural = '网站快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),
             models.Index(fields=['url']),
             models.Index(fields=['host']),  # host索引，优化根据主机名查询
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['title']),  # title索引，优化标题搜索
+            models.Index(fields=['-created_at']),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个URL只能记录一次
@@ -118,18 +119,19 @@ class DirectorySnapshot(models.Model):
     lines = models.IntegerField(null=True, blank=True, help_text='响应体行数（按换行符分割）')
     content_type = models.CharField(max_length=200, blank=True, default='', help_text='响应头 Content-Type 值')
     duration = models.BigIntegerField(null=True, blank=True, help_text='请求耗时（单位：纳秒）')
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'directory_snapshot'
         verbose_name = '目录快照'
         verbose_name_plural = '目录快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),
             models.Index(fields=['url']),
             models.Index(fields=['status']),  # 状态码索引，优化筛选
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['content_type']),  # content_type索引，优化内容类型搜索
+            models.Index(fields=['-created_at']),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个目录URL只能记录一次
@@ -183,16 +185,16 @@ class HostPortMappingSnapshot(models.Model):
     )
     
     # ==================== 时间字段 ====================
-    discovered_at = models.DateTimeField(
+    created_at = models.DateTimeField(
         auto_now_add=True,
-        help_text='发现时间'
+        help_text='创建时间'
     )
 
     class Meta:
         db_table = 'host_port_mapping_snapshot'
         verbose_name = '主机端口映射快照'
         verbose_name_plural = '主机端口映射快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),             # 优化按扫描查询
             models.Index(fields=['host']),             # 优化按主机名查询
@@ -200,7 +202,7 @@ class HostPortMappingSnapshot(models.Model):
             models.Index(fields=['port']),             # 优化按端口查询
             models.Index(fields=['host', 'ip']),       # 优化组合查询
             models.Index(fields=['scan', 'host']),     # 优化扫描+主机查询
-            models.Index(fields=['-discovered_at']),   # 优化时间排序
+            models.Index(fields=['-created_at']),   # 优化时间排序
         ]
         constraints = [
             # 复合唯一约束：同一次扫描中，scan + host + ip + port 组合唯一
@@ -257,19 +259,21 @@ class EndpointSnapshot(models.Model):
         default=list,
         help_text='匹配的GF模式列表'
     )
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'endpoint_snapshot'
         verbose_name = '端点快照'
         verbose_name_plural = '端点快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),
             models.Index(fields=['url']),
             models.Index(fields=['host']),  # host索引，优化根据主机名查询
+            models.Index(fields=['title']),  # title索引，优化标题搜索
             models.Index(fields=['status_code']),  # 状态码索引，优化筛选
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['webserver']),  # webserver索引，优化服务器搜索
+            models.Index(fields=['-created_at']),
         ]
         constraints = [
             # 唯一约束：同一次扫描中，同一个URL只能记录一次
@@ -302,7 +306,7 @@ class VulnerabilitySnapshot(models.Model):
     )
     
     # ==================== 核心字段 ====================
-    url = models.TextField(help_text='漏洞所在的URL')
+    url = models.CharField(max_length=2000, help_text='漏洞所在的URL')
     vuln_type = models.CharField(max_length=100, help_text='漏洞类型（如 xss, sqli）')
     severity = models.CharField(
         max_length=20,
@@ -316,19 +320,20 @@ class VulnerabilitySnapshot(models.Model):
     raw_output = models.JSONField(blank=True, default=dict, help_text='工具原始输出')
     
     # ==================== 时间字段 ====================
-    discovered_at = models.DateTimeField(auto_now_add=True, help_text='发现时间')
+    created_at = models.DateTimeField(auto_now_add=True, help_text='创建时间')
 
     class Meta:
         db_table = 'vulnerability_snapshot'
         verbose_name = '漏洞快照'
         verbose_name_plural = '漏洞快照'
-        ordering = ['-discovered_at']
+        ordering = ['-created_at']
         indexes = [
             models.Index(fields=['scan']),
+            models.Index(fields=['url']),  # url索引，优化URL搜索
             models.Index(fields=['vuln_type']),
             models.Index(fields=['severity']),
             models.Index(fields=['source']),
-            models.Index(fields=['-discovered_at']),
+            models.Index(fields=['-created_at']),
         ]
 
     def __str__(self):

backend/apps/asset/repositories/asset/directory_repository.py

@@ -3,162 +3,141 @@ Django ORM 实现的 Directory Repository
 """
 
 import logging
-from typing import List, Tuple, Dict, Iterator
-from django.db import transaction, IntegrityError, OperationalError, DatabaseError
-from django.utils import timezone
+from typing import List, Iterator
+from django.db import transaction
 
 from apps.asset.models.asset_models import Directory
 from apps.asset.dtos import DirectoryDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
 
 logger = logging.getLogger(__name__)
 
 
-
 @auto_ensure_db_connection
 class DjangoDirectoryRepository:
     """Django ORM 实现的 Directory Repository"""
 
-    def bulk_create_ignore_conflicts(self, items: List[DirectoryDTO]) -> int:
+    def bulk_upsert(self, items: List[DirectoryDTO]) -> int:
         """
-        批量创建 Directory，忽略冲突
+        批量创建或更新 Directory（upsert）
+        
+        存在则更新所有字段，不存在则创建。
+        使用 Django 原生 update_conflicts。
+        
+        注意：自动按模型唯一约束去重，保留最后一条记录。
         
         Args:
             items: Directory DTO 列表
             
         Returns:
-            int: 实际创建的记录数
-            
-        Raises:
-            IntegrityError: 数据完整性错误
-            OperationalError: 数据库操作错误
-            DatabaseError: 数据库错误
+            int: 处理的记录数
         """
         if not items:
             return 0
-
+        
         try:
-            # 转换为 Django 模型对象
-            directory_objects = [
+            # 自动按模型唯一约束去重
+            unique_items = deduplicate_for_bulk(items, Directory)
+            
+            # 直接从 DTO 字段构建 Model
+            directories = [
                 Directory(
-                    website_id=item.website_id,
                     target_id=item.target_id,
                     url=item.url,
                     status=item.status,
                     content_length=item.content_length,
                     words=item.words,
                     lines=item.lines,
-                    content_type=item.content_type,
+                    content_type=item.content_type or '',
                     duration=item.duration
                 )
-                for item in items
+                for item in unique_items
             ]
-
+            
             with transaction.atomic():
-                # 批量插入或忽略冲突
-                # 如果 website + url 已存在，忽略冲突
                 Directory.objects.bulk_create(
-                    directory_objects,
-                    ignore_conflicts=True
+                    directories,
+                    update_conflicts=True,
+                    unique_fields=['target', 'url'],
+                    update_fields=[
+                        'status', 'content_length', 'words',
+                        'lines', 'content_type', 'duration'
+                    ],
+                    batch_size=1000
                 )
-
-            logger.debug(f"成功处理 {len(items)} 条 Directory 记录")
-            return len(items)
-
-        except IntegrityError as e:
-            logger.error(
-                f"批量插入 Directory 失败 - 数据完整性错误: {e}, "
-                f"记录数: {len(items)}"
-            )
-            raise
-
-        except OperationalError as e:
-            logger.error(
-                f"批量插入 Directory 失败 - 数据库操作错误: {e}, "
-                f"记录数: {len(items)}"
-            )
-            raise
-
-        except DatabaseError as e:
-            logger.error(
-                f"批量插入 Directory 失败 - 数据库错误: {e}, "
-                f"记录数: {len(items)}"
-            )
-            raise
-
+            
+            logger.debug(f"批量 upsert Directory 成功: {len(unique_items)} 条")
+            return len(unique_items)
+                
         except Exception as e:
-            logger.error(
-                f"批量插入 Directory 失败 - 未知错误: {e}, "
-                f"记录数: {len(items)}, "
-                f"错误类型: {type(e).__name__}",
-                exc_info=True
-            )
+            logger.error(f"批量 upsert Directory 失败: {e}")
             raise
 
-    def get_by_website(self, website_id: int) -> List[DirectoryDTO]:
+    def bulk_create_ignore_conflicts(self, items: List[DirectoryDTO]) -> int:
         """
-        获取指定站点的所有目录
+        批量创建 Directory（存在即跳过）
+        
+        与 bulk_upsert 不同，此方法不会更新已存在的记录。
+        适用于批量添加场景，只提供 URL，没有其他字段数据。
+        
+        注意：自动按模型唯一约束去重，保留最后一条记录。
         
         Args:
-            website_id: 站点 ID
+            items: Directory DTO 列表
             
         Returns:
-            List[DirectoryDTO]: 目录列表
+            int: 处理的记录数
         """
+        if not items:
+            return 0
+        
         try:
-            directories = Directory.objects.filter(website_id=website_id)
-            return [
-                DirectoryDTO(
-                    website_id=d.website_id,
-                    target_id=d.target_id,
-                    url=d.url,
-                    status=d.status,
-                    content_length=d.content_length,
-                    words=d.words,
-                    lines=d.lines,
-                    content_type=d.content_type,
-                    duration=d.duration
+            # 自动按模型唯一约束去重
+            unique_items = deduplicate_for_bulk(items, Directory)
+            
+            directories = [
+                Directory(
+                    target_id=item.target_id,
+                    url=item.url,
+                    status=item.status,
+                    content_length=item.content_length,
+                    words=item.words,
+                    lines=item.lines,
+                    content_type=item.content_type or '',
+                    duration=item.duration
                 )
-                for d in directories
+                for item in unique_items
             ]
-
-        except Exception as e:
-            logger.error(f"获取目录列表失败 - Website ID: {website_id}, 错误: {e}")
-            raise
-
-    def count_by_website(self, website_id: int) -> int:
-        """
-        统计指定站点的目录总数
-        
-        Args:
-            website_id: 站点 ID
             
-        Returns:
-            int: 目录总数
-        """
-        try:
-            count = Directory.objects.filter(website_id=website_id).count()
-            logger.debug(f"Website {website_id} 的目录总数: {count}")
-            return count
-
+            with transaction.atomic():
+                Directory.objects.bulk_create(
+                    directories,
+                    ignore_conflicts=True,
+                    batch_size=1000
+                )
+            
+            logger.debug(f"批量创建 Directory 成功（ignore_conflicts）: {len(unique_items)} 条")
+            return len(unique_items)
+                
         except Exception as e:
-            logger.error(f"统计目录数量失败 - Website ID: {website_id}, 错误: {e}")
+            logger.error(f"批量创建 Directory 失败: {e}")
             raise
-    
+
+    def count_by_target(self, target_id: int) -> int:
+        """统计目标下的目录总数"""
+        return Directory.objects.filter(target_id=target_id).count()
+
     def get_all(self):
-        """
-        获取所有目录
-        
-        Returns:
-            QuerySet: 目录查询集
-        """
-        return Directory.objects.all()
-    
+        """获取所有目录"""
+        return Directory.objects.all().order_by('-created_at')
+
     def get_by_target(self, target_id: int):
-        return Directory.objects.filter(target_id=target_id).select_related('website').order_by('-discovered_at')
+        """获取目标下的所有目录"""
+        return Directory.objects.filter(target_id=target_id).order_by('-created_at')
 
     def get_urls_for_export(self, target_id: int, batch_size: int = 1000) -> Iterator[str]:
-        """流式导出目标下的所有目录 URL（只查 url 字段，避免加载多余数据）。"""
+        """流式导出目标下的所有目录 URL"""
         try:
             queryset = (
                 Directory.objects
@@ -172,78 +151,31 @@ class DjangoDirectoryRepository:
         except Exception as e:
             logger.error("流式导出目录 URL 失败 - Target ID: %s, 错误: %s", target_id, e)
             raise
-    
-    def soft_delete_by_ids(self, directory_ids: List[int]) -> int:
+
+    def iter_raw_data_for_export(
+        self, 
+        target_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
         """
-        根据 ID 列表批量软删除Directory
+        流式获取原始数据用于 CSV 导出
         
         Args:
-            directory_ids: Directory ID 列表
+            target_id: 目标 ID
+            batch_size: 每批数据量
         
-        Returns:
-            软删除的记录数
+        Yields:
+            包含所有目录字段的字典
         """
-        try:
-            updated_count = (
-                Directory.objects
-                .filter(id__in=directory_ids)
-                .update(deleted_at=timezone.now())
+        qs = (
+            Directory.objects
+            .filter(target_id=target_id)
+            .values(
+                'url', 'status', 'content_length', 'words',
+                'lines', 'content_type', 'duration', 'created_at'
             )
-            logger.debug(
-                "批量软删除Directory成功 - Count: %s, 更新记录: %s",
-                len(directory_ids),
-                updated_count
-            )
-            return updated_count
-        except Exception as e:
-            logger.error(
-                "批量软删除Directory失败 - IDs: %s, 错误: %s",
-                directory_ids,
-                e
-            )
-            raise
-    
-    def hard_delete_by_ids(self, directory_ids: List[int]) -> Tuple[int, Dict[str, int]]:
-        """
-        根据 ID 列表硬删除Directory（使用数据库级 CASCADE）
+            .order_by('url')
+        )
         
-        Args:
-            directory_ids: Directory ID 列表
-        
-        Returns:
-            (删除的记录数, 删除详情字典)
-        """
-        try:
-            batch_size = 1000
-            total_deleted = 0
-            
-            logger.debug(f"开始批量删除 {len(directory_ids)} 个Directory（数据库 CASCADE）...")
-            
-            for i in range(0, len(directory_ids), batch_size):
-                batch_ids = directory_ids[i:i + batch_size]
-                count, _ = Directory.all_objects.filter(id__in=batch_ids).delete()
-                total_deleted += count
-                logger.debug(f"批次删除完成: {len(batch_ids)} 个Directory，删除 {count} 条记录")
-            
-            deleted_details = {
-                'directories': len(directory_ids),
-                'total': total_deleted,
-                'note': 'Database CASCADE - detailed stats unavailable'
-            }
-            
-            logger.debug(
-                "批量硬删除成功（CASCADE）- Directory数: %s, 总删除记录: %s",
-                len(directory_ids),
-                total_deleted
-            )
-            
-            return total_deleted, deleted_details
-        
-        except Exception as e:
-            logger.error(
-                "批量硬删除失败（CASCADE）- Directory数: %s, 错误: %s",
-                len(directory_ids),
-                str(e),
-                exc_info=True
-            )
-            raise
+        for row in qs.iterator(chunk_size=batch_size):
+            yield row

backend/apps/asset/repositories/asset/endpoint_repository.py

@@ -1,11 +1,12 @@
 """Endpoint Repository - Django ORM 实现"""
 
 import logging
-from typing import List, Optional, Tuple, Dict, Any
+from typing import List, Iterator
 
 from apps.asset.models import Endpoint
 from apps.asset.dtos.asset import EndpointDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
 from django.db import transaction
 
 logger = logging.getLogger(__name__)
@@ -15,25 +16,31 @@ logger = logging.getLogger(__name__)
 class DjangoEndpointRepository:
     """端点 Repository - 负责端点表的数据访问"""
     
-    def bulk_create_ignore_conflicts(self, items: List[EndpointDTO]) -> int:
+    def bulk_upsert(self, items: List[EndpointDTO]) -> int:
         """
-        批量创建端点（忽略冲突）
+        批量创建或更新端点（upsert）
+        
+        存在则更新所有字段，不存在则创建。
+        使用 Django 原生 update_conflicts。
+        
+        注意：自动按模型唯一约束去重，保留最后一条记录。
         
         Args:
             items: 端点 DTO 列表
             
         Returns:
-            int: 创建的记录数
+            int: 处理的记录数
         """
         if not items:
             return 0
         
         try:
-            endpoints = []
-            for item in items:
-                # Endpoint 模型当前只关联 target，不再依赖 website 外键
-                # 这里按照 EndpointDTO 的字段映射构造 Endpoint 实例
-                endpoints.append(Endpoint(
+            # 自动按模型唯一约束去重
+            unique_items = deduplicate_for_bulk(items, Endpoint)
+            
+            # 直接从 DTO 字段构建 Model
+            endpoints = [
+                Endpoint(
                     target_id=item.target_id,
                     url=item.url,
                     host=item.host or '',
@@ -47,62 +54,35 @@ class DjangoEndpointRepository:
                     vhost=item.vhost,
                     location=item.location or '',
                     matched_gf_patterns=item.matched_gf_patterns if item.matched_gf_patterns else []
-                ))
+                )
+                for item in unique_items
+            ]
             
             with transaction.atomic():
-                created = Endpoint.objects.bulk_create(
+                Endpoint.objects.bulk_create(
                     endpoints,
-                    ignore_conflicts=True,
+                    update_conflicts=True,
+                    unique_fields=['url', 'target'],
+                    update_fields=[
+                        'host', 'title', 'status_code', 'content_length',
+                        'webserver', 'body_preview', 'content_type', 'tech',
+                        'vhost', 'location', 'matched_gf_patterns'
+                    ],
                     batch_size=1000
                 )
-                return len(created)
+            
+            logger.debug(f"批量 upsert 端点成功: {len(unique_items)} 条")
+            return len(unique_items)
                 
         except Exception as e:
-            logger.error(f"批量创建端点失败: {e}")
+            logger.error(f"批量 upsert 端点失败: {e}")
             raise
     
-    def get_by_website(self, website_id: int) -> List[EndpointDTO]:
-        """
-        获取网站下的所有端点
-        
-        Args:
-            website_id: 网站 ID
-            
-        Returns:
-            List[EndpointDTO]: 端点列表
-        """
-        endpoints = Endpoint.objects.filter(
-            website_id=website_id
-        ).order_by('-discovered_at')
-        
-        result = []
-        for endpoint in endpoints:
-            result.append(EndpointDTO(
-                website_id=endpoint.website_id,
-                target_id=endpoint.target_id,
-                url=endpoint.url,
-                title=endpoint.title,
-                status_code=endpoint.status_code,
-                content_length=endpoint.content_length,
-                webserver=endpoint.webserver,
-                body_preview=endpoint.body_preview,
-                content_type=endpoint.content_type,
-                tech=endpoint.tech,
-                vhost=endpoint.vhost,
-                location=endpoint.location,
-                matched_gf_patterns=endpoint.matched_gf_patterns
-            ))
-        
-        return result
-    
-    def get_queryset_by_target(self, target_id: int):
-        return Endpoint.objects.filter(target_id=target_id).order_by('-discovered_at')
-
     def get_all(self):
         """获取所有端点（全局查询）"""
-        return Endpoint.objects.all().order_by('-discovered_at')
+        return Endpoint.objects.all().order_by('-created_at')
     
-    def get_by_target(self, target_id: int) -> List[EndpointDTO]:
+    def get_by_target(self, target_id: int):
         """
         获取目标下的所有端点
         
@@ -110,43 +90,9 @@ class DjangoEndpointRepository:
             target_id: 目标 ID
             
         Returns:
-            List[EndpointDTO]: 端点列表
+            QuerySet: 端点查询集
         """
-        endpoints = Endpoint.objects.filter(
-            target_id=target_id
-        ).order_by('-discovered_at')
-        
-        result = []
-        for endpoint in endpoints:
-            result.append(EndpointDTO(
-                website_id=endpoint.website_id,
-                target_id=endpoint.target_id,
-                url=endpoint.url,
-                title=endpoint.title,
-                status_code=endpoint.status_code,
-                content_length=endpoint.content_length,
-                webserver=endpoint.webserver,
-                body_preview=endpoint.body_preview,
-                content_type=endpoint.content_type,
-                tech=endpoint.tech,
-                vhost=endpoint.vhost,
-                location=endpoint.location,
-                matched_gf_patterns=endpoint.matched_gf_patterns
-            ))
-        
-        return result
-    
-    def count_by_website(self, website_id: int) -> int:
-        """
-        统计网站下的端点数量
-        
-        Args:
-            website_id: 网站 ID
-            
-        Returns:
-            int: 端点数量
-        """
-        return Endpoint.objects.filter(website_id=website_id).count()
+        return Endpoint.objects.filter(target_id=target_id).order_by('-created_at')
     
     def count_by_target(self, target_id: int) -> int:
         """
@@ -159,34 +105,88 @@ class DjangoEndpointRepository:
             int: 端点数量
         """
         return Endpoint.objects.filter(target_id=target_id).count()
-    
-    def soft_delete_by_ids(self, ids: List[int]) -> int:
+
+    def bulk_create_ignore_conflicts(self, items: List[EndpointDTO]) -> int:
         """
-        软删除端点（批量）
+        批量创建端点（存在即跳过）
+        
+        与 bulk_upsert 不同，此方法不会更新已存在的记录。
+        适用于快速扫描场景，只提供 URL，没有其他字段数据。
+        
+        注意：自动按模型唯一约束去重，保留最后一条记录。
         
         Args:
-            ids: 端点 ID 列表
+            items: 端点 DTO 列表
             
         Returns:
-            int: 更新的记录数
+            int: 处理的记录数
         """
-        from django.utils import timezone
-        return Endpoint.objects.filter(
-            id__in=ids
-        ).update(deleted_at=timezone.now())
-    
-    def hard_delete_by_ids(self, ids: List[int]) -> Tuple[int, Dict[str, int]]:
+        if not items:
+            return 0
+        
+        try:
+            # 自动按模型唯一约束去重
+            unique_items = deduplicate_for_bulk(items, Endpoint)
+            
+            # 直接从 DTO 字段构建 Model
+            endpoints = [
+                Endpoint(
+                    target_id=item.target_id,
+                    url=item.url,
+                    host=item.host or '',
+                    title=item.title or '',
+                    status_code=item.status_code,
+                    content_length=item.content_length,
+                    webserver=item.webserver or '',
+                    body_preview=item.body_preview or '',
+                    content_type=item.content_type or '',
+                    tech=item.tech if item.tech else [],
+                    vhost=item.vhost,
+                    location=item.location or '',
+                    matched_gf_patterns=item.matched_gf_patterns if item.matched_gf_patterns else []
+                )
+                for item in unique_items
+            ]
+            
+            with transaction.atomic():
+                Endpoint.objects.bulk_create(
+                    endpoints,
+                    ignore_conflicts=True,
+                    batch_size=1000
+                )
+            
+            logger.debug(f"批量创建端点成功（ignore_conflicts）: {len(unique_items)} 条")
+            return len(unique_items)
+                
+        except Exception as e:
+            logger.error(f"批量创建端点失败: {e}")
+            raise
+
+    def iter_raw_data_for_export(
+        self, 
+        target_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
         """
-        硬删除端点（批量）
+        流式获取原始数据用于 CSV 导出
         
         Args:
-            ids: 端点 ID 列表
-            
-        Returns:
-            Tuple[int, Dict[str, int]]: (删除总数, 详细信息)
-        """
-        deleted_count, details = Endpoint.all_objects.filter(
-            id__in=ids
-        ).delete()
+            target_id: 目标 ID
+            batch_size: 每批数据量
         
-        return deleted_count, details
+        Yields:
+            包含所有端点字段的字典
+        """
+        qs = (
+            Endpoint.objects
+            .filter(target_id=target_id)
+            .values(
+                'url', 'host', 'location', 'title', 'status_code',
+                'content_length', 'content_type', 'webserver', 'tech',
+                'body_preview', 'vhost', 'matched_gf_patterns', 'created_at'
+            )
+            .order_by('url')
+        )
+        
+        for row in qs.iterator(chunk_size=batch_size):
+            yield row

backend/apps/asset/repositories/asset/host_port_mapping_repository.py

@@ -1,32 +1,36 @@
 """HostPortMapping Repository - Django ORM 实现"""
 
 import logging
-from typing import List, Iterator
+from typing import List, Iterator, Dict, Optional
+
+from django.db.models import QuerySet, Min
 
 from apps.asset.models.asset_models import HostPortMapping
 from apps.asset.dtos.asset import HostPortMappingDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
 
 logger = logging.getLogger(__name__)
 
 
 @auto_ensure_db_connection
 class DjangoHostPortMappingRepository:
-    """HostPortMapping Repository - Django ORM 实现"""
+    """HostPortMapping Repository - Django ORM 实现
+    
+    职责：纯数据访问，不包含业务逻辑
+    """
 
     def bulk_create_ignore_conflicts(self, items: List[HostPortMappingDTO]) -> int:
         """
         批量创建主机端口关联（忽略冲突）
         
+        注意：自动按模型唯一约束去重，保留最后一条记录。
+        
         Args:
             items: 主机端口关联 DTO 列表
         
         Returns:
-            int: 实际创建的记录数（注意：ignore_conflicts 时可能为 0）
-        
-        Note:
-            - 基于唯一约束 (target + host + ip + port) 自动去重
-            - 忽略已存在的记录，不更新
+            int: 实际创建的记录数
         """
         try:
             logger.debug("准备批量创建主机端口关联 - 数量: %d", len(items))
@@ -34,18 +38,20 @@ class DjangoHostPortMappingRepository:
             if not items:
                 logger.debug("主机端口关联为空，跳过创建")
                 return 0
+            
+            # 自动按模型唯一约束去重
+            unique_items = deduplicate_for_bulk(items, HostPortMapping)
                 
-            # 构建记录对象
-            records = []
-            for item in items:
-                records.append(HostPortMapping(
+            records = [
+                HostPortMapping(
                     target_id=item.target_id,
                     host=item.host,
                     ip=item.ip,
                     port=item.port
-                ))
+                )
+                for item in unique_items
+            ]
             
-            # 批量创建（忽略冲突，基于唯一约束去重）
             created = HostPortMapping.objects.bulk_create(
                 records, 
                 ignore_conflicts=True
@@ -89,79 +95,47 @@ class DjangoHostPortMappingRepository:
         for ip in queryset:
             yield ip
 
-    def get_ip_aggregation_by_target(self, target_id: int, search: str = None):
-        from django.db.models import Min
+    def get_queryset_by_target(self, target_id: int) -> QuerySet:
+        """获取目标下的 QuerySet"""
+        return HostPortMapping.objects.filter(target_id=target_id)
 
-        qs = HostPortMapping.objects.filter(target_id=target_id)
-        if search:
-            qs = qs.filter(ip__icontains=search)
+    def get_all_queryset(self) -> QuerySet:
+        """获取所有记录的 QuerySet"""
+        return HostPortMapping.objects.all()
 
-        ip_aggregated = (
-            qs
-            .values('ip')
-            .annotate(
-                discovered_at=Min('discovered_at')
-            )
-            .order_by('-discovered_at')
+    def get_queryset_by_ip(self, ip: str, target_id: Optional[int] = None) -> QuerySet:
+        """获取指定 IP 的 QuerySet"""
+        qs = HostPortMapping.objects.filter(ip=ip)
+        if target_id:
+            qs = qs.filter(target_id=target_id)
+        return qs
+
+    def iter_raw_data_for_export(
+        self, 
+        target_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            target_id: 目标 ID
+            batch_size: 每批数据量
+        
+        Yields:
+            {
+                'ip': '192.168.1.1',
+                'host': 'example.com',
+                'port': 80,
+                'created_at': datetime
+            }
+        """
+        qs = (
+            HostPortMapping.objects
+            .filter(target_id=target_id)
+            .values('ip', 'host', 'port', 'created_at')
+            .order_by('ip', 'host', 'port')
         )
-
-        results = []
-        for item in ip_aggregated:
-            ip = item['ip']
-            mappings = (
-                HostPortMapping.objects
-                .filter(target_id=target_id, ip=ip)
-                .values('host', 'port')
-                .distinct()
-            )
-
-            hosts = sorted({m['host'] for m in mappings})
-            ports = sorted({m['port'] for m in mappings})
-
-            results.append({
-                'ip': ip,
-                'hosts': hosts,
-                'ports': ports,
-                'discovered_at': item['discovered_at'],
-            })
-
-        return results
-
-    def get_all_ip_aggregation(self, search: str = None):
-        """获取所有 IP 聚合数据（全局查询）"""
-        from django.db.models import Min
-
-        qs = HostPortMapping.objects.all()
-        if search:
-            qs = qs.filter(ip__icontains=search)
-
-        ip_aggregated = (
-            qs
-            .values('ip')
-            .annotate(
-                discovered_at=Min('discovered_at')
-            )
-            .order_by('-discovered_at')
-        )
-
-        results = []
-        for item in ip_aggregated:
-            ip = item['ip']
-            mappings = (
-                HostPortMapping.objects
-                .filter(ip=ip)
-                .values('host', 'port')
-                .distinct()
-            )
-
-            hosts = sorted({m['host'] for m in mappings})
-            ports = sorted({m['port'] for m in mappings})
-
-            results.append({
-                'ip': ip,
-                'hosts': hosts,
-                'ports': ports,
-                'discovered_at': item['discovered_at'],
-            })
-
-        return results
+        
+        for row in qs.iterator(chunk_size=batch_size):
+            yield row

backend/apps/asset/repositories/asset/subdomain_repository.py

@@ -1,117 +1,72 @@
+"""Subdomain Repository - Django ORM 实现"""
+
 import logging
 from typing import List, Iterator
 
-from django.db import transaction, IntegrityError, OperationalError, DatabaseError
-from django.utils import timezone
-from typing import Tuple, Dict
+from django.db import transaction
 
 from apps.asset.models.asset_models import Subdomain
 from apps.asset.dtos import SubdomainDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
 
 logger = logging.getLogger(__name__)
 
 
 @auto_ensure_db_connection
 class DjangoSubdomainRepository:
-    """基于 Django ORM 的子域名仓储实现。"""
+    """基于 Django ORM 的子域名仓储实现"""
 
     def bulk_create_ignore_conflicts(self, items: List[SubdomainDTO]) -> None:
         """
         批量创建子域名，忽略冲突
         
+        注意：自动按模型唯一约束去重，保留最后一条记录。
+        
         Args:
             items: 子域名 DTO 列表
-            
-        Raises:
-            IntegrityError: 数据完整性错误（如唯一约束冲突）
-            OperationalError: 数据库操作错误（如连接失败）
-            DatabaseError: 其他数据库错误
         """
         if not items:
             return
 
         try:
+            # 自动按模型唯一约束去重
+            unique_items = deduplicate_for_bulk(items, Subdomain)
+            
             subdomain_objects = [
                 Subdomain(
                     name=item.name,
                     target_id=item.target_id,
                 )
-                for item in items
+                for item in unique_items
             ]
 
             with transaction.atomic():
-                # 使用 ignore_conflicts 策略：
-                # - 新子域名：INSERT 完整记录
-                # - 已存在子域名：忽略（不更新，因为没有探测字段数据）
-                # 注意：ignore_conflicts 无法返回实际创建的数量
-                Subdomain.objects.bulk_create(  # type: ignore[attr-defined]
+                Subdomain.objects.bulk_create(
                     subdomain_objects,
-                    ignore_conflicts=True,  # 忽略重复记录
+                    ignore_conflicts=True,
                 )
 
-            logger.debug(f"成功处理 {len(items)} 条子域名记录")
-
-        except IntegrityError as e:
-            logger.error(
-                f"批量插入子域名失败 - 数据完整性错误: {e}, "
-                f"记录数: {len(items)}, "
-                f"示例域名: {items[0].name if items else 'N/A'}"
-            )
-            raise
-
-        except OperationalError as e:
-            logger.error(
-                f"批量插入子域名失败 - 数据库操作错误: {e}, "
-                f"记录数: {len(items)}"
-            )
-            raise
-
-        except DatabaseError as e:
-            logger.error(
-                f"批量插入子域名失败 - 数据库错误: {e}, "
-                f"记录数: {len(items)}"
-            )
-            raise
+            logger.debug(f"成功处理 {len(unique_items)} 条子域名记录")
 
         except Exception as e:
-            logger.error(
-                f"批量插入子域名失败 - 未知错误: {e}, "
-                f"记录数: {len(items)}, "
-                f"错误类型: {type(e).__name__}",
-                exc_info=True
-            )
+            logger.error(f"批量插入子域名失败: {e}")
             raise
     
-    def get_or_create(self, name: str, target_id: int) -> Tuple[Subdomain, bool]:
-        """
-        获取或创建子域名
-        
-        Args:
-            name: 子域名名称
-            target_id: 目标 ID
-        
-        Returns:
-            (Subdomain对象, 是否新创建)
-        """
-        return Subdomain.objects.get_or_create(
-            name=name,
-            target_id=target_id,
-        )
+    def get_all(self):
+        """获取所有子域名"""
+        return Subdomain.objects.all().order_by('-created_at')
+
+    def get_by_target(self, target_id: int):
+        """获取目标下的所有子域名"""
+        return Subdomain.objects.filter(target_id=target_id).order_by('-created_at')
+    
+    def count_by_target(self, target_id: int) -> int:
+        """统计目标下的域名数量"""
+        return Subdomain.objects.filter(target_id=target_id).count()
     
     def get_domains_for_export(self, target_id: int, batch_size: int = 1000) -> Iterator[str]:
-        """
-        流式导出域名（用于生成扫描工具输入文件）
-        
-        使用 iterator() 进行流式查询，避免一次性加载所有数据到内存
-        
-        Args:
-            target_id: 目标 ID
-            batch_size: 每次从数据库读取的行数
-            
-        Yields:
-            str: 域名
-        """
+        """流式导出域名"""
         queryset = Subdomain.objects.filter(
             target_id=target_id
         ).only('name').iterator(chunk_size=batch_size)
@@ -119,138 +74,36 @@ class DjangoSubdomainRepository:
         for subdomain in queryset:
             yield subdomain.name
     
-    def get_by_target(self, target_id: int):
-        return Subdomain.objects.filter(target_id=target_id).order_by('-discovered_at')
-    
-    def count_by_target(self, target_id: int) -> int:
-        """
-        统计目标下的域名数量
-        
-        Args:
-            target_id: 目标 ID
-            
-        Returns:
-            int: 域名数量
-        """
-        return Subdomain.objects.filter(target_id=target_id).count()
-    
     def get_by_names_and_target_id(self, names: set, target_id: int) -> dict:
-        """
-        根据域名列表和目标ID批量查询 Subdomain
-        
-        Args:
-            names: 域名集合
-            target_id: 目标 ID
-            
-        Returns:
-            dict: {domain_name: Subdomain对象}
-        """
+        """根据域名列表和目标ID批量查询 Subdomain"""
         subdomains = Subdomain.objects.filter(
             name__in=names,
             target_id=target_id
         ).only('id', 'name')
         
         return {sd.name: sd for sd in subdomains}
-    
-    def get_all(self):
+
+    def iter_raw_data_for_export(
+        self, 
+        target_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
         """
-        获取所有子域名
-        
-        Returns:
-            QuerySet: 子域名查询集
-        """
-        return Subdomain.objects.all()
-    
-    def soft_delete_by_ids(self, subdomain_ids: List[int]) -> int:
-        """
-        根据 ID 列表批量软删除子域名
+        流式获取原始数据用于 CSV 导出
         
         Args:
-            subdomain_ids: 子域名 ID 列表
+            target_id: 目标 ID
+            batch_size: 每批数据量
         
-        Returns:
-            软删除的记录数
-        
-        Note:
-            - 使用软删除：只标记为已删除，不真正删除数据库记录
-            - 保留所有关联数据，可恢复
+        Yields:
+            {'name': 'sub.example.com', 'created_at': datetime}
         """
-        try:
-            updated_count = (
-                Subdomain.objects
-                .filter(id__in=subdomain_ids)
-                .update(deleted_at=timezone.now())
-            )
-            logger.debug(
-                "批量软删除子域名成功 - Count: %s, 更新记录: %s",
-                len(subdomain_ids),
-                updated_count
-            )
-            return updated_count
-        except Exception as e:
-            logger.error(
-                "批量软删除子域名失败 - IDs: %s, 错误: %s",
-                subdomain_ids,
-                e
-            )
-            raise
-    
-    def hard_delete_by_ids(self, subdomain_ids: List[int]) -> Tuple[int, Dict[str, int]]:
-        """
-        根据 ID 列表硬删除子域名（使用数据库级 CASCADE）
+        qs = (
+            Subdomain.objects
+            .filter(target_id=target_id)
+            .values('name', 'created_at')
+            .order_by('name')
+        )
         
-        Args:
-            subdomain_ids: 子域名 ID 列表
-        
-        Returns:
-            (删除的记录数, 删除详情字典)
-        
-        Strategy:
-            使用数据库级 CASCADE 删除，性能最优
-        
-        Note:
-            - 硬删除：从数据库中永久删除
-            - 数据库自动处理所有外键级联删除
-            - 不触发 Django 信号（pre_delete/post_delete）
-        """
-        try:
-            batch_size = 1000  # 每批处理1000个子域名
-            total_deleted = 0
-            
-            logger.debug(f"开始批量删除 {len(subdomain_ids)} 个子域名（数据库 CASCADE）...")
-            
-            # 分批处理子域名ID，避免单次删除过多
-            for i in range(0, len(subdomain_ids), batch_size):
-                batch_ids = subdomain_ids[i:i + batch_size]
-                
-                # 直接删除子域名，数据库自动级联删除所有关联数据
-                count, _ = Subdomain.all_objects.filter(id__in=batch_ids).delete()
-                total_deleted += count
-                
-                logger.debug(f"批次删除完成: {len(batch_ids)} 个子域名，删除 {count} 条记录")
-            
-            # 由于使用数据库 CASCADE，无法获取详细统计
-            deleted_details = {
-                'subdomains': len(subdomain_ids),
-                'total': total_deleted,
-                'note': 'Database CASCADE - detailed stats unavailable'
-            }
-            
-            logger.debug(
-                "批量硬删除成功（CASCADE）- 子域名数: %s, 总删除记录: %s",
-                len(subdomain_ids),
-                total_deleted
-            )
-            
-            return total_deleted, deleted_details
-        
-        except Exception as e:
-            logger.error(
-                "批量硬删除失败（CASCADE）- 子域名数: %s, 错误: %s",
-                len(subdomain_ids),
-                str(e),
-                exc_info=True
-            )
-            raise
-
-
+        for row in qs.iterator(chunk_size=batch_size):
+            yield row

backend/apps/asset/repositories/asset/website_repository.py

@@ -3,110 +3,87 @@ Django ORM 实现的 WebSite Repository
 """
 
 import logging
-from typing import List, Generator, Tuple, Dict, Optional
-from django.db import transaction, IntegrityError, OperationalError, DatabaseError
-from django.utils import timezone
+from typing import List, Generator, Optional, Iterator
+from django.db import transaction
 
 from apps.asset.models.asset_models import WebSite
 from apps.asset.dtos import WebSiteDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
 
 logger = logging.getLogger(__name__)
 
 
-
 @auto_ensure_db_connection
 class DjangoWebSiteRepository:
     """Django ORM 实现的 WebSite Repository"""
 
-    def bulk_create_ignore_conflicts(self, items: List[WebSiteDTO]) -> None:
+    def bulk_upsert(self, items: List[WebSiteDTO]) -> int:
         """
-        批量创建 WebSite，忽略冲突
+        批量创建或更新 WebSite（upsert）
+        
+        存在则更新所有字段，不存在则创建。
+        使用 Django 原生 update_conflicts。
+        
+        注意：自动按模型唯一约束去重，保留最后一条记录。
         
         Args:
             items: WebSite DTO 列表
             
-        Raises:
-            IntegrityError: 数据完整性错误
-            OperationalError: 数据库操作错误
-            DatabaseError: 数据库错误
+        Returns:
+            int: 处理的记录数
         """
         if not items:
-            return
-
+            return 0
+        
         try:
-            # 转换为 Django 模型对象
-            website_objects = [
+            # 自动按模型唯一约束去重
+            unique_items = deduplicate_for_bulk(items, WebSite)
+            
+            # 直接从 DTO 字段构建 Model
+            websites = [
                 WebSite(
                     target_id=item.target_id,
                     url=item.url,
-                    host=item.host,
-                    location=item.location,
-                    title=item.title,
-                    webserver=item.webserver,
-                    body_preview=item.body_preview,
-                    content_type=item.content_type,
-                    tech=item.tech,
+                    host=item.host or '',
+                    location=item.location or '',
+                    title=item.title or '',
+                    webserver=item.webserver or '',
+                    body_preview=item.body_preview or '',
+                    content_type=item.content_type or '',
+                    tech=item.tech if item.tech else [],
                     status_code=item.status_code,
                     content_length=item.content_length,
                     vhost=item.vhost
                 )
-                for item in items
+                for item in unique_items
             ]
-
+            
             with transaction.atomic():
-                # 批量插入或更新
-                # 如果URL和目标已存在，忽略冲突
                 WebSite.objects.bulk_create(
-                    website_objects,
-                    ignore_conflicts=True
+                    websites,
+                    update_conflicts=True,
+                    unique_fields=['url', 'target'],
+                    update_fields=[
+                        'host', 'location', 'title', 'webserver',
+                        'body_preview', 'content_type', 'tech',
+                        'status_code', 'content_length', 'vhost'
+                    ],
+                    batch_size=1000
                 )
-
-            logger.debug(f"成功处理 {len(items)} 条 WebSite 记录")
-
-        except IntegrityError as e:
-            logger.error(
-                f"批量插入 WebSite 失败 - 数据完整性错误: {e}, "
-                f"记录数: {len(items)}"
-            )
-            raise
-
-        except OperationalError as e:
-            logger.error(
-                f"批量插入 WebSite 失败 - 数据库操作错误: {e}, "
-                f"记录数: {len(items)}"
-            )
-            raise
-
-        except DatabaseError as e:
-            logger.error(
-                f"批量插入 WebSite 失败 - 数据库错误: {e}, "
-                f"记录数: {len(items)}"
-            )
-            raise
-
+            
+            logger.debug(f"批量 upsert WebSite 成功: {len(unique_items)} 条")
+            return len(unique_items)
+                
         except Exception as e:
-            logger.error(
-                f"批量插入 WebSite 失败 - 未知错误: {e}, "
-                f"记录数: {len(items)}, "
-                f"错误类型: {type(e).__name__}",
-                exc_info=True
-            )
+            logger.error(f"批量 upsert WebSite 失败: {e}")
             raise
 
     def get_urls_for_export(self, target_id: int, batch_size: int = 1000) -> Generator[str, None, None]:
         """
         流式导出目标下的所有站点 URL
-        
-        Args:
-            target_id: 目标 ID  
-            batch_size: 批次大小
-            
-        Yields:
-            str: 站点 URL
         """
         try:
-            # 查询目标下的站点，只选择 URL 字段，避免不必要的数据传输
             queryset = WebSite.objects.filter(
                 target_id=target_id
             ).values_list('url', flat=True).iterator(chunk_size=batch_size)
@@ -117,144 +94,93 @@ class DjangoWebSiteRepository:
             logger.error(f"流式导出站点 URL 失败 - Target ID: {target_id}, 错误: {e}")
             raise
 
+    def get_all(self):
+        """获取所有网站"""
+        return WebSite.objects.all().order_by('-created_at')
+
     def get_by_target(self, target_id: int):
-        return WebSite.objects.filter(target_id=target_id).order_by('-discovered_at')
+        """获取目标下的所有网站"""
+        return WebSite.objects.filter(target_id=target_id).order_by('-created_at')
 
     def count_by_target(self, target_id: int) -> int:
-        """
-        统计目标下的站点总数
-        
-        Args:
-            target_id: 目标 ID
-            
-        Returns:
-            int: 站点总数
-        """
-        try:
-            count = WebSite.objects.filter(target_id=target_id).count()
-            logger.debug(f"Target {target_id} 的站点总数: {count}")
-            return count
-            
-        except Exception as e:
-            logger.error(f"统计站点数量失败 - Target ID: {target_id}, 错误: {e}")
-            raise
-
-    def count_by_scan(self, scan_id: int) -> int:
-        """
-        统计扫描下的站点总数
-        """
-        try:
-            count = WebSite.objects.filter(scan_id=scan_id).count()
-            logger.debug(f"Scan {scan_id} 的站点总数: {count}")
-            return count
-        except Exception as e:
-            logger.error(f"统计站点数量失败 - Scan ID: {scan_id}, 错误: {e}")
-            raise
+        """统计目标下的站点总数"""
+        return WebSite.objects.filter(target_id=target_id).count()
 
     def get_by_url(self, url: str, target_id: int) -> Optional[int]:
+        """根据 URL 和 target_id 查找站点 ID"""
+        website = WebSite.objects.filter(url=url, target_id=target_id).first()
+        return website.id if website else None
+
+    def bulk_create_ignore_conflicts(self, items: List[WebSiteDTO]) -> int:
         """
-        根据 URL 和 target_id 查找站点 ID
+        批量创建 WebSite（存在即跳过）
+        
+        注意：自动按模型唯一约束去重，保留最后一条记录。
+        """
+        if not items:
+            return 0
+        
+        try:
+            # 自动按模型唯一约束去重
+            unique_items = deduplicate_for_bulk(items, WebSite)
+            
+            websites = [
+                WebSite(
+                    target_id=item.target_id,
+                    url=item.url,
+                    host=item.host or '',
+                    location=item.location or '',
+                    title=item.title or '',
+                    webserver=item.webserver or '',
+                    body_preview=item.body_preview or '',
+                    content_type=item.content_type or '',
+                    tech=item.tech if item.tech else [],
+                    status_code=item.status_code,
+                    content_length=item.content_length,
+                    vhost=item.vhost
+                )
+                for item in unique_items
+            ]
+            
+            with transaction.atomic():
+                WebSite.objects.bulk_create(
+                    websites,
+                    ignore_conflicts=True,
+                    batch_size=1000
+                )
+            
+            logger.debug(f"批量创建 WebSite 成功（ignore_conflicts）: {len(unique_items)} 条")
+            return len(unique_items)
+                
+        except Exception as e:
+            logger.error(f"批量创建 WebSite 失败: {e}")
+            raise
+
+    def iter_raw_data_for_export(
+        self, 
+        target_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
         
         Args:
-            url: 站点 URL
             target_id: 目标 ID
-            
-        Returns:
-            Optional[int]: 站点 ID，如果不存在返回 None
-            
-        Raises:
-            ValueError: 发现多个站点时
-        """
-        try:
-            website = WebSite.objects.filter(url=url, target_id=target_id).first()
-            if website:
-                return website.id
-            return None
-            
-        except Exception as e:
-            logger.error(f"查询站点失败 - URL: {url}, Target ID: {target_id}, 错误: {e}")
-            raise
-    
-    def get_all(self):
-        """
-        获取所有网站
+            batch_size: 每批数据量
         
-        Returns:
-            QuerySet: 网站查询集
+        Yields:
+            包含所有网站字段的字典
         """
-        return WebSite.objects.all()
-    
-    def soft_delete_by_ids(self, website_ids: List[int]) -> int:
-        """
-        根据 ID 列表批量软删除WebSite
-        
-        Args:
-            website_ids: WebSite ID 列表
-        
-        Returns:
-            软删除的记录数
-        """
-        try:
-            updated_count = (
-                WebSite.objects
-                .filter(id__in=website_ids)
-                .update(deleted_at=timezone.now())
+        qs = (
+            WebSite.objects
+            .filter(target_id=target_id)
+            .values(
+                'url', 'host', 'location', 'title', 'status_code',
+                'content_length', 'content_type', 'webserver', 'tech',
+                'body_preview', 'vhost', 'created_at'
             )
-            logger.debug(
-                "批量软删除WebSite成功 - Count: %s, 更新记录: %s",
-                len(website_ids),
-                updated_count
-            )
-            return updated_count
-        except Exception as e:
-            logger.error(
-                "批量软删除WebSite失败 - IDs: %s, 错误: %s",
-                website_ids,
-                e
-            )
-            raise
-    
-    def hard_delete_by_ids(self, website_ids: List[int]) -> Tuple[int, Dict[str, int]]:
-        """
-        根据 ID 列表硬删除WebSite（使用数据库级 CASCADE）
+            .order_by('url')
+        )
         
-        Args:
-            website_ids: WebSite ID 列表
-        
-        Returns:
-            (删除的记录数, 删除详情字典)
-        """
-        try:
-            batch_size = 1000
-            total_deleted = 0
-            
-            logger.debug(f"开始批量删除 {len(website_ids)} 个WebSite（数据库 CASCADE）...")
-            
-            for i in range(0, len(website_ids), batch_size):
-                batch_ids = website_ids[i:i + batch_size]
-                count, _ = WebSite.all_objects.filter(id__in=batch_ids).delete()
-                total_deleted += count
-                logger.debug(f"批次删除完成: {len(batch_ids)} 个WebSite，删除 {count} 条记录")
-            
-            deleted_details = {
-                'websites': len(website_ids),
-                'total': total_deleted,
-                'note': 'Database CASCADE - detailed stats unavailable'
-            }
-            
-            logger.debug(
-                "批量硬删除成功（CASCADE）- WebSite数: %s, 总删除记录: %s",
-                len(website_ids),
-                total_deleted
-            )
-            
-            return total_deleted, deleted_details
-        
-        except Exception as e:
-            logger.error(
-                "批量硬删除失败（CASCADE）- WebSite数: %s, 错误: %s",
-                len(website_ids),
-                str(e),
-                exc_info=True
-            )
-            raise
+        for row in qs.iterator(chunk_size=batch_size):
+            yield row

backend/apps/asset/repositories/snapshot/directory_snapshot_repository.py

@@ -1,12 +1,13 @@
 """Directory Snapshot Repository - 目录快照数据访问层"""
 
 import logging
-from typing import List
+from typing import List, Iterator
 from django.db import transaction
 
 from apps.asset.models import DirectorySnapshot
 from apps.asset.dtos.snapshot import DirectorySnapshotDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
 
 logger = logging.getLogger(__name__)
 
@@ -25,6 +26,8 @@ class DjangoDirectorySnapshotRepository:
         
         使用 ignore_conflicts 策略，如果快照已存在（相同 scan + url）则跳过
         
+        注意：会自动按 (scan_id, url) 去重，保留最后一条记录。
+        
         Args:
             items: 目录快照 DTO 列表
         
@@ -37,6 +40,9 @@ class DjangoDirectorySnapshotRepository:
             return
         
         try:
+            # 根据模型唯一约束自动去重
+            unique_items = deduplicate_for_bulk(items, DirectorySnapshot)
+            
             # 转换为 Django 模型对象
             snapshot_objects = [
                 DirectorySnapshot(
@@ -49,7 +55,7 @@ class DjangoDirectorySnapshotRepository:
                     content_type=item.content_type,
                     duration=item.duration
                 )
-                for item in items
+                for item in unique_items
             ]
             
             with transaction.atomic():
@@ -60,7 +66,7 @@ class DjangoDirectorySnapshotRepository:
                     ignore_conflicts=True
                 )
             
-            logger.debug("成功保存 %d 条目录快照记录", len(items))
+            logger.debug("成功保存 %d 条目录快照记录", len(unique_items))
             
         except Exception as e:
             logger.error(
@@ -72,7 +78,35 @@ class DjangoDirectorySnapshotRepository:
             raise
     
     def get_by_scan(self, scan_id: int):
-        return DirectorySnapshot.objects.filter(scan_id=scan_id).order_by('-discovered_at')
+        return DirectorySnapshot.objects.filter(scan_id=scan_id).order_by('-created_at')
 
     def get_all(self):
-        return DirectorySnapshot.objects.all().order_by('-discovered_at')
+        return DirectorySnapshot.objects.all().order_by('-created_at')
+
+    def iter_raw_data_for_export(
+        self, 
+        scan_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            scan_id: 扫描 ID
+            batch_size: 每批数据量
+        
+        Yields:
+            包含所有目录字段的字典
+        """
+        qs = (
+            DirectorySnapshot.objects
+            .filter(scan_id=scan_id)
+            .values(
+                'url', 'status', 'content_length', 'words',
+                'lines', 'content_type', 'duration', 'created_at'
+            )
+            .order_by('url')
+        )
+        
+        for row in qs.iterator(chunk_size=batch_size):
+            yield row

backend/apps/asset/repositories/snapshot/endpoint_snapshot_repository.py

@@ -1,11 +1,12 @@
 """EndpointSnapshot Repository - Django ORM 实现"""
 
 import logging
-from typing import List
+from typing import List, Iterator
 
 from apps.asset.models.snapshot_models import EndpointSnapshot
 from apps.asset.dtos.snapshot import EndpointSnapshotDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
 
 logger = logging.getLogger(__name__)
 
@@ -18,6 +19,8 @@ class DjangoEndpointSnapshotRepository:
         """
         保存端点快照
         
+        注意：会自动按 (scan_id, url) 去重，保留最后一条记录。
+        
         Args:
             items: 端点快照 DTO 列表
         
@@ -31,10 +34,13 @@ class DjangoEndpointSnapshotRepository:
             if not items:
                 logger.debug("端点快照为空，跳过保存")
                 return
+            
+            # 根据模型唯一约束自动去重
+            unique_items = deduplicate_for_bulk(items, EndpointSnapshot)
                 
             # 构建快照对象
             snapshots = []
-            for item in items:
+            for item in unique_items:
                 snapshots.append(EndpointSnapshot(
                     scan_id=item.scan_id,
                     url=item.url,
@@ -68,7 +74,36 @@ class DjangoEndpointSnapshotRepository:
             raise
     
     def get_by_scan(self, scan_id: int):
-        return EndpointSnapshot.objects.filter(scan_id=scan_id).order_by('-discovered_at')
+        return EndpointSnapshot.objects.filter(scan_id=scan_id).order_by('-created_at')
 
     def get_all(self):
-        return EndpointSnapshot.objects.all().order_by('-discovered_at')
+        return EndpointSnapshot.objects.all().order_by('-created_at')
+
+    def iter_raw_data_for_export(
+        self, 
+        scan_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            scan_id: 扫描 ID
+            batch_size: 每批数据量
+        
+        Yields:
+            包含所有端点字段的字典
+        """
+        qs = (
+            EndpointSnapshot.objects
+            .filter(scan_id=scan_id)
+            .values(
+                'url', 'host', 'location', 'title', 'status_code',
+                'content_length', 'content_type', 'webserver', 'tech',
+                'body_preview', 'vhost', 'matched_gf_patterns', 'created_at'
+            )
+            .order_by('url')
+        )
+        
+        for row in qs.iterator(chunk_size=batch_size):
+            yield row

backend/apps/asset/repositories/snapshot/host_port_mapping_snapshot_repository.py

@@ -6,6 +6,7 @@ from typing import List, Iterator
 from apps.asset.models.snapshot_models import HostPortMappingSnapshot
 from apps.asset.dtos.snapshot import HostPortMappingSnapshotDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
 
 logger = logging.getLogger(__name__)
 
@@ -18,6 +19,8 @@ class DjangoHostPortMappingSnapshotRepository:
         """
         保存主机端口关联快照
         
+        注意：会自动按 (scan_id, host, ip, port) 去重，保留最后一条记录。
+        
         Args:
             items: 主机端口关联快照 DTO 列表
         
@@ -31,10 +34,13 @@ class DjangoHostPortMappingSnapshotRepository:
             if not items:
                 logger.debug("主机端口关联快照为空，跳过保存")
                 return
+            
+            # 根据模型唯一约束自动去重
+            unique_items = deduplicate_for_bulk(items, HostPortMappingSnapshot)
                 
             # 构建快照对象
             snapshots = []
-            for item in items:
+            for item in unique_items:
                 snapshots.append(HostPortMappingSnapshot(
                     scan_id=item.scan_id,
                     host=item.host,
@@ -59,20 +65,28 @@ class DjangoHostPortMappingSnapshotRepository:
             )
             raise
     
-    def get_ip_aggregation_by_scan(self, scan_id: int, search: str = None):
+    def get_ip_aggregation_by_scan(self, scan_id: int, filter_query: str = None):
         from django.db.models import Min
+        from apps.common.utils.filter_utils import apply_filters
 
         qs = HostPortMappingSnapshot.objects.filter(scan_id=scan_id)
-        if search:
-            qs = qs.filter(ip__icontains=search)
+        
+        # 应用智能过滤
+        if filter_query:
+            field_mapping = {
+                'ip': 'ip',
+                'port': 'port',
+                'host': 'host',
+            }
+            qs = apply_filters(qs, filter_query, field_mapping)
 
         ip_aggregated = (
             qs
             .values('ip')
             .annotate(
-                discovered_at=Min('discovered_at')
+                created_at=Min('created_at')
             )
-            .order_by('-discovered_at')
+            .order_by('-created_at')
         )
 
         results = []
@@ -92,24 +106,32 @@ class DjangoHostPortMappingSnapshotRepository:
                 'ip': ip,
                 'hosts': hosts,
                 'ports': ports,
-                'discovered_at': item['discovered_at'],
+                'created_at': item['created_at'],
             })
 
         return results
 
-    def get_all_ip_aggregation(self, search: str = None):
+    def get_all_ip_aggregation(self, filter_query: str = None):
         """获取所有 IP 聚合数据"""
         from django.db.models import Min
+        from apps.common.utils.filter_utils import apply_filters
 
         qs = HostPortMappingSnapshot.objects.all()
-        if search:
-            qs = qs.filter(ip__icontains=search)
+        
+        # 应用智能过滤
+        if filter_query:
+            field_mapping = {
+                'ip': 'ip',
+                'port': 'port',
+                'host': 'host',
+            }
+            qs = apply_filters(qs, filter_query, field_mapping)
 
         ip_aggregated = (
             qs
             .values('ip')
-            .annotate(discovered_at=Min('discovered_at'))
-            .order_by('-discovered_at')
+            .annotate(created_at=Min('created_at'))
+            .order_by('-created_at')
         )
 
         results = []
@@ -127,7 +149,7 @@ class DjangoHostPortMappingSnapshotRepository:
                 'ip': ip,
                 'hosts': hosts,
                 'ports': ports,
-                'discovered_at': item['discovered_at'],
+                'created_at': item['created_at'],
             })
         return results
 
@@ -143,3 +165,33 @@ class DjangoHostPortMappingSnapshotRepository:
         )
         for ip in queryset:
             yield ip
+
+    def iter_raw_data_for_export(
+        self, 
+        scan_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            scan_id: 扫描 ID
+            batch_size: 每批数据量
+        
+        Yields:
+            {
+                'ip': '192.168.1.1',
+                'host': 'example.com',
+                'port': 80,
+                'created_at': datetime
+            }
+        """
+        qs = (
+            HostPortMappingSnapshot.objects
+            .filter(scan_id=scan_id)
+            .values('ip', 'host', 'port', 'created_at')
+            .order_by('ip', 'host', 'port')
+        )
+        
+        for row in qs.iterator(chunk_size=batch_size):
+            yield row

backend/apps/asset/repositories/snapshot/subdomain_snapshot_repository.py

@@ -1,11 +1,12 @@
 """Django ORM 实现的 SubdomainSnapshot Repository"""
 
 import logging
-from typing import List
+from typing import List, Iterator
 
 from apps.asset.models.snapshot_models import SubdomainSnapshot
 from apps.asset.dtos import SubdomainSnapshotDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
 
 logger = logging.getLogger(__name__)
 
@@ -18,6 +19,8 @@ class DjangoSubdomainSnapshotRepository:
         """
         保存子域名快照
         
+        注意：会自动按 (scan_id, name) 去重，保留最后一条记录。
+        
         Args:
             items: 子域名快照 DTO 列表
         
@@ -31,10 +34,13 @@ class DjangoSubdomainSnapshotRepository:
             if not items:
                 logger.debug("子域名快照为空，跳过保存")
                 return
+            
+            # 根据模型唯一约束自动去重
+            unique_items = deduplicate_for_bulk(items, SubdomainSnapshot)
                 
             # 构建快照对象
             snapshots = []
-            for item in items:
+            for item in unique_items:
                 snapshots.append(SubdomainSnapshot(
                     scan_id=item.scan_id,
                     name=item.name,
@@ -55,7 +61,32 @@ class DjangoSubdomainSnapshotRepository:
             raise
     
     def get_by_scan(self, scan_id: int):
-        return SubdomainSnapshot.objects.filter(scan_id=scan_id).order_by('-discovered_at')
+        return SubdomainSnapshot.objects.filter(scan_id=scan_id).order_by('-created_at')
 
     def get_all(self):
-        return SubdomainSnapshot.objects.all().order_by('-discovered_at')
+        return SubdomainSnapshot.objects.all().order_by('-created_at')
+
+    def iter_raw_data_for_export(
+        self, 
+        scan_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            scan_id: 扫描 ID
+            batch_size: 每批数据量
+        
+        Yields:
+            {'name': 'sub.example.com', 'created_at': datetime}
+        """
+        qs = (
+            SubdomainSnapshot.objects
+            .filter(scan_id=scan_id)
+            .values('name', 'created_at')
+            .order_by('name')
+        )
+        
+        for row in qs.iterator(chunk_size=batch_size):
+            yield row

backend/apps/asset/repositories/snapshot/vulnerability_snapshot_repository.py

@@ -8,6 +8,7 @@ from django.db import transaction
 from apps.asset.models import VulnerabilitySnapshot
 from apps.asset.dtos.snapshot import VulnerabilitySnapshotDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
 
 logger = logging.getLogger(__name__)
 
@@ -21,12 +22,17 @@ class DjangoVulnerabilitySnapshotRepository:
 
         使用 ``ignore_conflicts`` 策略，如果快照已存在则跳过。
         具体唯一约束由数据库模型控制。
+        
+        注意：会自动按唯一约束字段去重，保留最后一条记录。
         """
         if not items:
             logger.warning("漏洞快照列表为空，跳过保存")
             return
 
         try:
+            # 根据模型唯一约束自动去重
+            unique_items = deduplicate_for_bulk(items, VulnerabilitySnapshot)
+            
             snapshot_objects = [
                 VulnerabilitySnapshot(
                     scan_id=item.scan_id,
@@ -38,7 +44,7 @@ class DjangoVulnerabilitySnapshotRepository:
                     description=item.description,
                     raw_output=item.raw_output,
                 )
-                for item in items
+                for item in unique_items
             ]
 
             with transaction.atomic():
@@ -47,7 +53,7 @@ class DjangoVulnerabilitySnapshotRepository:
                     ignore_conflicts=True,
                 )
 
-            logger.debug("成功保存 %d 条漏洞快照记录", len(items))
+            logger.debug("成功保存 %d 条漏洞快照记录", len(unique_items))
 
         except Exception as e:
             logger.error(
@@ -60,7 +66,7 @@ class DjangoVulnerabilitySnapshotRepository:
 
     def get_by_scan(self, scan_id: int):
         """按扫描任务获取漏洞快照 QuerySet。"""
-        return VulnerabilitySnapshot.objects.filter(scan_id=scan_id).order_by("-discovered_at")
+        return VulnerabilitySnapshot.objects.filter(scan_id=scan_id).order_by("-created_at")
 
     def get_all(self):
-        return VulnerabilitySnapshot.objects.all().order_by('-discovered_at')
+        return VulnerabilitySnapshot.objects.all().order_by('-created_at')

backend/apps/asset/repositories/snapshot/website_snapshot_repository.py

@@ -1,11 +1,12 @@
 """WebsiteSnapshot Repository - Django ORM 实现"""
 
 import logging
-from typing import List
+from typing import List, Iterator
 
 from apps.asset.models.snapshot_models import WebsiteSnapshot
 from apps.asset.dtos.snapshot import WebsiteSnapshotDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
 
 logger = logging.getLogger(__name__)
 
@@ -18,6 +19,8 @@ class DjangoWebsiteSnapshotRepository:
         """
         保存网站快照
         
+        注意：会自动按 (scan_id, url) 去重，保留最后一条记录。
+        
         Args:
             items: 网站快照 DTO 列表
         
@@ -31,10 +34,13 @@ class DjangoWebsiteSnapshotRepository:
             if not items:
                 logger.debug("网站快照为空，跳过保存")
                 return
+            
+            # 根据模型唯一约束自动去重
+            unique_items = deduplicate_for_bulk(items, WebsiteSnapshot)
                 
             # 构建快照对象
             snapshots = []
-            for item in items:
+            for item in unique_items:
                 snapshots.append(WebsiteSnapshot(
                     scan_id=item.scan_id,
                     url=item.url,
@@ -68,7 +74,50 @@ class DjangoWebsiteSnapshotRepository:
             raise
     
     def get_by_scan(self, scan_id: int):
-        return WebsiteSnapshot.objects.filter(scan_id=scan_id).order_by('-discovered_at')
+        return WebsiteSnapshot.objects.filter(scan_id=scan_id).order_by('-created_at')
 
     def get_all(self):
-        return WebsiteSnapshot.objects.all().order_by('-discovered_at')
+        return WebsiteSnapshot.objects.all().order_by('-created_at')
+
+    def iter_raw_data_for_export(
+        self, 
+        scan_id: int,
+        batch_size: int = 1000
+    ) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            scan_id: 扫描 ID
+            batch_size: 每批数据量
+        
+        Yields:
+            包含所有网站字段的字典
+        """
+        qs = (
+            WebsiteSnapshot.objects
+            .filter(scan_id=scan_id)
+            .values(
+                'url', 'host', 'location', 'title', 'status',
+                'content_length', 'content_type', 'web_server', 'tech',
+                'body_preview', 'vhost', 'created_at'
+            )
+            .order_by('url')
+        )
+        
+        for row in qs.iterator(chunk_size=batch_size):
+            # 重命名字段以匹配 CSV 表头
+            yield {
+                'url': row['url'],
+                'host': row['host'],
+                'location': row['location'],
+                'title': row['title'],
+                'status_code': row['status'],
+                'content_length': row['content_length'],
+                'content_type': row['content_type'],
+                'webserver': row['web_server'],
+                'tech': row['tech'],
+                'body_preview': row['body_preview'],
+                'vhost': row['vhost'],
+                'created_at': row['created_at'],
+            }

backend/apps/asset/serializers.py

@@ -26,9 +26,9 @@ class SubdomainSerializer(serializers.ModelSerializer):
     class Meta:
         model = Subdomain
         fields = [
-            'id', 'name', 'discovered_at', 'target'
+            'id', 'name', 'created_at', 'target'
         ]
-        read_only_fields = ['id', 'discovered_at']
+        read_only_fields = ['id', 'created_at']
 
 
 class SubdomainListSerializer(serializers.ModelSerializer):
@@ -41,9 +41,9 @@ class SubdomainListSerializer(serializers.ModelSerializer):
     class Meta:
         model = Subdomain
         fields = [
-            'id', 'name', 'discovered_at'
+            'id', 'name', 'created_at'
         ]
-        read_only_fields = ['id', 'discovered_at']
+        read_only_fields = ['id', 'created_at']
 
 
 # class IPAddressListSerializer(serializers.ModelSerializer):
@@ -87,7 +87,7 @@ class WebSiteSerializer(serializers.ModelSerializer):
             'tech',
             'vhost',
             'subdomain',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -107,7 +107,7 @@ class VulnerabilitySerializer(serializers.ModelSerializer):
             'cvss_score',
             'description',
             'raw_output',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -126,7 +126,7 @@ class VulnerabilitySnapshotSerializer(serializers.ModelSerializer):
             'cvss_score',
             'description',
             'raw_output',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -134,8 +134,8 @@ class VulnerabilitySnapshotSerializer(serializers.ModelSerializer):
 class EndpointListSerializer(serializers.ModelSerializer):
     """端点列表序列化器（用于目标端点列表页）"""
 
-    # 将 GF 匹配模式映射为前端使用的 tags 字段
-    tags = serializers.ListField(
+    # GF 匹配模式（gf-patterns 工具匹配的敏感 URL 模式）
+    gfPatterns = serializers.ListField(
         child=serializers.CharField(),
         source='matched_gf_patterns',
         read_only=True,
@@ -155,8 +155,8 @@ class EndpointListSerializer(serializers.ModelSerializer):
             'body_preview',
             'tech',
             'vhost',
-            'tags',
-            'discovered_at',
+            'gfPatterns',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -164,8 +164,7 @@ class EndpointListSerializer(serializers.ModelSerializer):
 class DirectorySerializer(serializers.ModelSerializer):
     """目录序列化器"""
     
-    website_url = serializers.CharField(source='website.url', read_only=True)
-    discovered_at = serializers.DateTimeField(read_only=True)
+    created_at = serializers.DateTimeField(read_only=True)
     
     class Meta:
         model = Directory
@@ -178,8 +177,7 @@ class DirectorySerializer(serializers.ModelSerializer):
             'lines',
             'content_type',
             'duration',
-            'website_url',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -192,12 +190,12 @@ class IPAddressAggregatedSerializer(serializers.Serializer):
     - ip: IP 地址
     - hosts: 该 IP 关联的所有主机名列表
     - ports: 该 IP 关联的所有端口列表
-    - discovered_at: 首次发现时间
+    - created_at: 创建时间
     """
     ip = serializers.IPAddressField(read_only=True)
     hosts = serializers.ListField(child=serializers.CharField(), read_only=True)
     ports = serializers.ListField(child=serializers.IntegerField(), read_only=True)
-    discovered_at = serializers.DateTimeField(read_only=True)
+    created_at = serializers.DateTimeField(read_only=True)
 
 
 # ==================== 快照序列化器 ====================
@@ -207,7 +205,7 @@ class SubdomainSnapshotSerializer(serializers.ModelSerializer):
     
     class Meta:
         model = SubdomainSnapshot
-        fields = ['id', 'name', 'discovered_at']
+        fields = ['id', 'name', 'created_at']
         read_only_fields = fields
 
 
@@ -233,7 +231,7 @@ class WebsiteSnapshotSerializer(serializers.ModelSerializer):
             'tech',
             'vhost',
             'subdomain_name',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -241,9 +239,6 @@ class WebsiteSnapshotSerializer(serializers.ModelSerializer):
 class DirectorySnapshotSerializer(serializers.ModelSerializer):
     """目录快照序列化器（用于扫描历史）"""
     
-    # DirectorySnapshot 当前不再关联 Website，这里暂时将 website_url 映射为自身的 url，保证字段兼容
-    website_url = serializers.CharField(source='url', read_only=True)
-    
     class Meta:
         model = DirectorySnapshot
         fields = [
@@ -255,8 +250,7 @@ class DirectorySnapshotSerializer(serializers.ModelSerializer):
             'lines',
             'content_type',
             'duration',
-            'website_url',
-            'discovered_at',
+            'created_at',
         ]
         read_only_fields = fields
 
@@ -264,8 +258,8 @@ class DirectorySnapshotSerializer(serializers.ModelSerializer):
 class EndpointSnapshotSerializer(serializers.ModelSerializer):
     """端点快照序列化器（用于扫描历史）"""
 
-    # 将 GF 匹配模式映射为前端使用的 tags 字段
-    tags = serializers.ListField(
+    # GF 匹配模式（gf-patterns 工具匹配的敏感 URL 模式）
+    gfPatterns = serializers.ListField(
         child=serializers.CharField(),
         source='matched_gf_patterns',
         read_only=True,
@@ -286,7 +280,7 @@ class EndpointSnapshotSerializer(serializers.ModelSerializer):
             'body_preview',
             'tech',
             'vhost',
-            'tags',
-            'discovered_at',
+            'gfPatterns',
+            'created_at',
         ]
         read_only_fields = fields

backend/apps/asset/services/asset/directory_service.py

@@ -1,8 +1,12 @@
-import logging
-from typing import Tuple, Iterator
+"""Directory Service - 目录业务逻辑层"""
+
+import logging
+from typing import List, Iterator, Optional
 
-from apps.asset.models.asset_models import Directory
 from apps.asset.repositories import DjangoDirectoryRepository
+from apps.asset.dtos import DirectoryDTO
+from apps.common.validators import is_valid_url, is_url_match_target
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
@@ -10,46 +14,122 @@ logger = logging.getLogger(__name__)
 class DirectoryService:
     """目录业务逻辑层"""
     
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'status': 'status',
+    }
+    
     def __init__(self, repository=None):
-        """
-        初始化目录服务
-        
-        Args:
-            repository: 目录仓储实例（用于依赖注入）
-        """
+        """初始化目录服务"""
         self.repo = repository or DjangoDirectoryRepository()
     
-    # ==================== 创建操作 ====================
-    
-    def bulk_create_ignore_conflicts(self, directory_dtos: list) -> None:
+    def bulk_upsert(self, directory_dtos: List[DirectoryDTO]) -> int:
         """
-        批量创建目录记录，忽略冲突（用于扫描任务）
+        批量创建或更新目录（upsert）
+        
+        存在则更新所有字段，不存在则创建。
         
         Args:
             directory_dtos: DirectoryDTO 列表
-        """
-        return self.repo.bulk_create_ignore_conflicts(directory_dtos)
-    
-    # ==================== 查询操作 ====================
-
-    def get_all(self):
-        """
-        获取所有目录
-        
+            
         Returns:
-            QuerySet: 目录查询集
+            int: 处理的记录数
         """
-        logger.debug("获取所有目录")
-        return self.repo.get_all()
+        if not directory_dtos:
+            return 0
+        
+        try:
+            return self.repo.bulk_upsert(directory_dtos)
+        except Exception as e:
+            logger.error(f"批量 upsert 目录失败: {e}")
+            raise
     
-    def get_directories_by_target(self, target_id: int):
-        logger.debug("获取目标下所有目录 - Target ID: %d", target_id)
-        return self.repo.get_by_target(target_id)
+    def bulk_create_urls(self, target_id: int, target_name: str, target_type: str, urls: List[str]) -> int:
+        """
+        批量创建目录（仅 URL，使用 ignore_conflicts）
+        
+        验证 URL 格式和匹配，过滤无效/不匹配 URL，去重后批量创建。
+        已存在的记录会被跳过。
+        
+        Args:
+            target_id: 目标 ID
+            target_name: 目标名称（用于匹配验证）
+            target_type: 目标类型 ('domain', 'ip', 'cidr')
+            urls: URL 列表
+            
+        Returns:
+            int: 实际创建的记录数
+        """
+        if not urls:
+            return 0
+        
+        # 过滤有效 URL 并去重
+        valid_urls = []
+        seen = set()
+        
+        for url in urls:
+            if not isinstance(url, str):
+                continue
+            url = url.strip()
+            if not url or url in seen:
+                continue
+            if not is_valid_url(url):
+                continue
+            
+            # 匹配验证（前端已阻止不匹配的提交，后端作为双重保障）
+            if not is_url_match_target(url, target_name, target_type):
+                continue
+            
+            seen.add(url)
+            valid_urls.append(url)
+        
+        if not valid_urls:
+            return 0
+        
+        # 获取创建前的数量
+        count_before = self.repo.count_by_target(target_id)
+        
+        # 创建 DTO 列表并批量创建
+        directory_dtos = [
+            DirectoryDTO(url=url, target_id=target_id)
+            for url in valid_urls
+        ]
+        self.repo.bulk_create_ignore_conflicts(directory_dtos)
+        
+        # 获取创建后的数量
+        count_after = self.repo.count_by_target(target_id)
+        return count_after - count_before
+    
+    def get_directories_by_target(self, target_id: int, filter_query: Optional[str] = None):
+        """获取目标下的所有目录"""
+        queryset = self.repo.get_by_target(target_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
+    
+    def get_all(self, filter_query: Optional[str] = None):
+        """获取所有目录"""
+        queryset = self.repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_directory_urls_by_target(self, target_id: int, chunk_size: int = 1000) -> Iterator[str]:
-        """流式获取目标下的所有目录 URL，用于导出大批量数据。"""
-        logger.debug("流式导出目标下目录 URL - Target ID: %d", target_id)
+        """流式获取目标下的所有目录 URL"""
         return self.repo.get_urls_for_export(target_id=target_id, batch_size=chunk_size)
 
+    def iter_raw_data_for_csv_export(self, target_id: int) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            target_id: 目标 ID
+        
+        Yields:
+            原始数据字典
+        """
+        return self.repo.iter_raw_data_for_export(target_id=target_id)
+
 
 __all__ = ['DirectoryService']

backend/apps/asset/services/asset/endpoint_service.py

@@ -5,10 +5,12 @@ Endpoint 服务层
 """
 
 import logging
-from typing import List, Optional, Dict, Any, Iterator
+from typing import List, Iterator, Optional
 
 from apps.asset.dtos.asset import EndpointDTO
 from apps.asset.repositories.asset import DjangoEndpointRepository
+from apps.common.validators import is_valid_url, is_url_match_target
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
@@ -20,101 +22,102 @@ class EndpointService:
     提供 Endpoint（URL/端点）相关的业务逻辑
     """
     
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'host': 'host',
+        'title': 'title',
+        'status': 'status_code',
+        'tech': 'tech',
+    }
+    
     def __init__(self):
         """初始化 Endpoint 服务"""
         self.repo = DjangoEndpointRepository()
     
-    def bulk_create_endpoints(
-        self,
-        endpoints: List[EndpointDTO],
-        ignore_conflicts: bool = True
-    ) -> int:
+    def bulk_upsert(self, endpoints: List[EndpointDTO]) -> int:
         """
-        批量创建端点记录
+        批量创建或更新端点（upsert）
+        
+        存在则更新所有字段，不存在则创建。
         
         Args:
             endpoints: 端点数据列表
-            ignore_conflicts: 是否忽略冲突（去重）
             
         Returns:
-            int: 创建的记录数
+            int: 处理的记录数
         """
         if not endpoints:
             return 0
         
         try:
-            if ignore_conflicts:
-                return self.repo.bulk_create_ignore_conflicts(endpoints)
-            else:
-                # 如果需要非忽略冲突的版本，可以在 repository 中添加
-                return self.repo.bulk_create_ignore_conflicts(endpoints)
+            return self.repo.bulk_upsert(endpoints)
         except Exception as e:
-            logger.error(f"批量创建端点失败: {e}")
+            logger.error(f"批量 upsert 端点失败: {e}")
             raise
     
-    def get_endpoints_by_website(
-        self,
-        website_id: int,
-        limit: Optional[int] = None
-    ) -> List[Dict[str, Any]]:
+    def bulk_create_urls(self, target_id: int, target_name: str, target_type: str, urls: List[str]) -> int:
         """
-        获取网站下的端点列表
+        批量创建端点（仅 URL，使用 ignore_conflicts）
         
-        Args:
-            website_id: 网站 ID
-            limit: 返回数量限制
-            
-        Returns:
-            List[Dict]: 端点列表
-        """
-        endpoints_dto = self.repo.get_by_website(website_id)
-        
-        if limit:
-            endpoints_dto = endpoints_dto[:limit]
-        
-        endpoints = []
-        for dto in endpoints_dto:
-            endpoints.append({
-                'url': dto.url,
-                'title': dto.title,
-                'status_code': dto.status_code,
-                'content_length': dto.content_length,
-                'webserver': dto.webserver
-            })
-        
-        return endpoints
-    
-    def get_endpoints_by_target(
-        self,
-        target_id: int,
-        limit: Optional[int] = None
-    ) -> List[Dict[str, Any]]:
-        """
-        获取目标下的端点列表
+        验证 URL 格式和匹配，过滤无效/不匹配 URL，去重后批量创建。
+        已存在的记录会被跳过。
         
         Args:
             target_id: 目标 ID
-            limit: 返回数量限制
+            target_name: 目标名称（用于匹配验证）
+            target_type: 目标类型 ('domain', 'ip', 'cidr')
+            urls: URL 列表
             
         Returns:
-            List[Dict]: 端点列表
+            int: 实际创建的记录数
         """
-        endpoints_dto = self.repo.get_by_target(target_id)
+        if not urls:
+            return 0
         
-        if limit:
-            endpoints_dto = endpoints_dto[:limit]
+        # 过滤有效 URL 并去重
+        valid_urls = []
+        seen = set()
         
-        endpoints = []
-        for dto in endpoints_dto:
-            endpoints.append({
-                'url': dto.url,
-                'title': dto.title,
-                'status_code': dto.status_code,
-                'content_length': dto.content_length,
-                'webserver': dto.webserver
-            })
+        for url in urls:
+            if not isinstance(url, str):
+                continue
+            url = url.strip()
+            if not url or url in seen:
+                continue
+            if not is_valid_url(url):
+                continue
+            
+            # 匹配验证（前端已阻止不匹配的提交，后端作为双重保障）
+            if not is_url_match_target(url, target_name, target_type):
+                continue
+            
+            seen.add(url)
+            valid_urls.append(url)
         
-        return endpoints
+        if not valid_urls:
+            return 0
+        
+        # 获取创建前的数量
+        count_before = self.repo.count_by_target(target_id)
+        
+        # 创建 DTO 列表并批量创建
+        endpoint_dtos = [
+            EndpointDTO(url=url, target_id=target_id)
+            for url in valid_urls
+        ]
+        self.repo.bulk_create_ignore_conflicts(endpoint_dtos)
+        
+        # 获取创建后的数量
+        count_after = self.repo.count_by_target(target_id)
+        return count_after - count_before
+    
+    def get_endpoints_by_target(self, target_id: int, filter_query: Optional[str] = None):
+        """获取目标下的所有端点"""
+        queryset = self.repo.get_by_target(target_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING, json_array_fields=['tech'])
+        return queryset
     
     def count_endpoints_by_target(self, target_id: int) -> int:
         """
@@ -127,52 +130,28 @@ class EndpointService:
             int: 端点数量
         """
         return self.repo.count_by_target(target_id)
-    
-    def get_queryset_by_target(self, target_id: int):
-        return self.repo.get_queryset_by_target(target_id)
 
-    def get_all(self):
+    def get_all(self, filter_query: Optional[str] = None):
         """获取所有端点（全局查询）"""
-        return self.repo.get_all()
+        queryset = self.repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING, json_array_fields=['tech'])
+        return queryset
     
     def iter_endpoint_urls_by_target(self, target_id: int, chunk_size: int = 1000) -> Iterator[str]:
         """流式获取目标下的所有端点 URL，用于导出。"""
-        queryset = self.repo.get_queryset_by_target(target_id)
+        queryset = self.repo.get_by_target(target_id)
         for url in queryset.values_list('url', flat=True).iterator(chunk_size=chunk_size):
             yield url
-    
-    def count_endpoints_by_website(self, website_id: int) -> int:
+
+    def iter_raw_data_for_csv_export(self, target_id: int) -> Iterator[dict]:
         """
-        统计网站下的端点数量
+        流式获取原始数据用于 CSV 导出
         
         Args:
-            website_id: 网站 ID
-            
-        Returns:
-            int: 端点数量
-        """
-        return self.repo.count_by_website(website_id)
-    
-    def soft_delete_endpoints(self, endpoint_ids: List[int]) -> int:
-        """
-        软删除端点
+            target_id: 目标 ID
         
-        Args:
-            endpoint_ids: 端点 ID 列表
-            
-        Returns:
-            int: 更新的数量
+        Yields:
+            原始数据字典
         """
-        return self.repo.soft_delete_by_ids(endpoint_ids)
-    
-    def hard_delete_endpoints(self, endpoint_ids: List[int]) -> tuple:
-        """
-        硬删除端点
-        
-        Args:
-            endpoint_ids: 端点 ID 列表
-            
-        Returns:
-            tuple: (删除总数, 详细信息)
-        """
-        return self.repo.hard_delete_by_ids(endpoint_ids)
+        return self.repo.iter_raw_data_for_export(target_id=target_id)

backend/apps/asset/services/asset/host_port_mapping_service.py

@@ -1,16 +1,31 @@
 """HostPortMapping Service - 业务逻辑层"""
 
 import logging
-from typing import List, Iterator
+from typing import List, Iterator, Optional, Dict
+
+from django.db.models import Min
 
 from apps.asset.repositories.asset import DjangoHostPortMappingRepository
 from apps.asset.dtos.asset import HostPortMappingDTO
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
 
 class HostPortMappingService:
-    """主机端口映射服务 - 负责主机端口映射数据的业务逻辑"""
+    """主机端口映射服务 - 负责主机端口映射数据的业务逻辑
+    
+    职责：
+    - 业务逻辑处理（过滤、聚合）
+    - 调用 Repository 进行数据访问
+    """
+    
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'ip': 'ip',
+        'port': 'port',
+        'host': 'host',
+    }
     
     def __init__(self):
         self.repo = DjangoHostPortMappingRepository()
@@ -49,13 +64,106 @@ class HostPortMappingService:
     def iter_host_port_by_target(self, target_id: int, batch_size: int = 1000):
         return self.repo.get_for_export(target_id=target_id, batch_size=batch_size)
 
-    def get_ip_aggregation_by_target(self, target_id: int, search: str = None):
-        return self.repo.get_ip_aggregation_by_target(target_id, search=search)
+    def get_ip_aggregation_by_target(
+        self, 
+        target_id: int, 
+        filter_query: Optional[str] = None
+    ) -> List[Dict]:
+        """获取目标下的 IP 聚合数据
+        
+        Args:
+            target_id: 目标 ID
+            filter_query: 智能过滤语法字符串
+        
+        Returns:
+            聚合后的 IP 数据列表
+        """
+        # 从 Repository 获取基础 QuerySet
+        qs = self.repo.get_queryset_by_target(target_id)
+        
+        # Service 层应用过滤逻辑
+        if filter_query:
+            qs = apply_filters(qs, filter_query, self.FILTER_FIELD_MAPPING)
+        
+        # Service 层处理聚合逻辑
+        return self._aggregate_by_ip(qs, filter_query, target_id=target_id)
 
-    def get_all_ip_aggregation(self, search: str = None):
-        """获取所有 IP 聚合数据（全局查询）"""
-        return self.repo.get_all_ip_aggregation(search=search)
+    def get_all_ip_aggregation(self, filter_query: Optional[str] = None) -> List[Dict]:
+        """获取所有 IP 聚合数据（全局查询）
+        
+        Args:
+            filter_query: 智能过滤语法字符串
+        
+        Returns:
+            聚合后的 IP 数据列表
+        """
+        # 从 Repository 获取基础 QuerySet
+        qs = self.repo.get_all_queryset()
+        
+        # Service 层应用过滤逻辑
+        if filter_query:
+            qs = apply_filters(qs, filter_query, self.FILTER_FIELD_MAPPING)
+        
+        # Service 层处理聚合逻辑
+        return self._aggregate_by_ip(qs, filter_query)
+
+    def _aggregate_by_ip(
+        self, 
+        qs, 
+        filter_query: Optional[str] = None,
+        target_id: Optional[int] = None
+    ) -> List[Dict]:
+        """按 IP 聚合数据
+        
+        Args:
+            qs: 已过滤的 QuerySet
+            filter_query: 过滤条件（用于子查询）
+            target_id: 目标 ID（用于子查询限定范围）
+        
+        Returns:
+            聚合后的数据列表
+        """
+        ip_aggregated = (
+            qs
+            .values('ip')
+            .annotate(created_at=Min('created_at'))
+            .order_by('-created_at')
+        )
+
+        results = []
+        for item in ip_aggregated:
+            ip = item['ip']
+            
+            # 获取该 IP 的所有 host 和 port（也需要应用过滤条件）
+            mappings_qs = self.repo.get_queryset_by_ip(ip, target_id=target_id)
+            if filter_query:
+                mappings_qs = apply_filters(mappings_qs, filter_query, self.FILTER_FIELD_MAPPING)
+            
+            mappings = mappings_qs.values('host', 'port').distinct()
+            hosts = sorted({m['host'] for m in mappings})
+            ports = sorted({m['port'] for m in mappings})
+            
+            results.append({
+                'ip': ip,
+                'hosts': hosts,
+                'ports': ports,
+                'created_at': item['created_at'],
+            })
+        
+        return results
 
     def iter_ips_by_target(self, target_id: int, batch_size: int = 1000) -> Iterator[str]:
         """流式获取目标下的所有唯一 IP 地址。"""
         return self.repo.get_ips_for_export(target_id=target_id, batch_size=batch_size)
+
+    def iter_raw_data_for_csv_export(self, target_id: int) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            target_id: 目标 ID
+        
+        Yields:
+            原始数据字典 {ip, host, port, created_at}
+        """
+        return self.repo.iter_raw_data_for_export(target_id=target_id)

backend/apps/asset/services/asset/subdomain_service.py

@@ -1,15 +1,33 @@
 import logging
-from typing import Tuple, List, Dict
+from typing import List, Dict, Optional
+from dataclasses import dataclass
 
 from apps.asset.repositories import DjangoSubdomainRepository
 from apps.asset.dtos import SubdomainDTO
+from apps.common.validators import is_valid_domain
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
 
+@dataclass
+class BulkCreateResult:
+    """批量创建结果"""
+    created_count: int
+    skipped_count: int
+    invalid_count: int
+    mismatched_count: int
+    total_received: int
+
+
 class SubdomainService:
     """子域名业务逻辑层"""
     
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+    }
+    
     def __init__(self, repository=None):
         """
         初始化子域名服务
@@ -21,44 +39,50 @@ class SubdomainService:
     
     # ==================== 查询操作 ====================
     
-    def get_all(self):
+    def get_all(self, filter_query: Optional[str] = None):
         """
         获取所有子域名
         
+        Args:
+            filter_query: 智能过滤语法字符串
+        
         Returns:
             QuerySet: 子域名查询集
         """
         logger.debug("获取所有子域名")
-        return self.repo.get_all()
+        queryset = self.repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
     
-    # ==================== 创建操作 ====================
-    
-    def get_or_create(self, name: str, target_id: int) -> Tuple[any, bool]:
+    def get_subdomains_by_target(self, target_id: int, filter_query: Optional[str] = None):
         """
-        获取或创建子域名
+        获取目标下的子域名
+        
+        Args:
+            target_id: 目标 ID
+            filter_query: 智能过滤语法字符串
+        
+        Returns:
+            QuerySet: 子域名查询集
+        """
+        queryset = self.repo.get_by_target(target_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
+
+    def count_subdomains_by_target(self, target_id: int) -> int:
+        """
+        统计目标下的子域名数量
         
         Args:
-            name: 子域名名称
             target_id: 目标 ID
         
         Returns:
-            (Subdomain对象, 是否新创建)
+            int: 子域名数量
         """
-        logger.debug("获取或创建子域名 - Name: %s, Target ID: %d", name, target_id)
-        return self.repo.get_or_create(name, target_id)
-
-    def bulk_create_ignore_conflicts(self, items: List[SubdomainDTO]) -> None:
-        """
-        批量创建子域名，忽略冲突
-        
-        Args:
-            items: 子域名 DTO 列表
-        
-        Note:
-            使用 ignore_conflicts 策略，重复记录会被跳过
-        """
-        logger.debug("批量创建子域名 - 数量: %d", len(items))
-        return self.repo.bulk_create_ignore_conflicts(items)
+        logger.debug("统计目标下子域名数量 - Target ID: %d", target_id)
+        return self.repo.count_by_target(target_id)
     
     def get_by_names_and_target_id(self, names: set, target_id: int) -> dict:
         """
@@ -85,25 +109,8 @@ class SubdomainService:
             List[str]: 子域名名称列表
         """
         logger.debug("获取目标下所有子域名 - Target ID: %d", target_id)
-        # 通过仓储层统一访问数据库，内部已使用 iterator() 做流式查询
         return list(self.repo.get_domains_for_export(target_id=target_id))
     
-    def get_subdomains_by_target(self, target_id: int):
-        return self.repo.get_by_target(target_id)
-    
-    def count_subdomains_by_target(self, target_id: int) -> int:
-        """
-        统计目标下的子域名数量
-        
-        Args:
-            target_id: 目标 ID
-        
-        Returns:
-            int: 子域名数量
-        """
-        logger.debug("统计目标下子域名数量 - Target ID: %d", target_id)
-        return self.repo.count_by_target(target_id)
-    
     def iter_subdomain_names_by_target(self, target_id: int, chunk_size: int = 1000):
         """
         流式获取目标下的所有子域名名称（内存优化）
@@ -116,8 +123,123 @@ class SubdomainService:
             str: 子域名名称
         """
         logger.debug("流式获取目标下所有子域名 - Target ID: %d, 批次大小: %d", target_id, chunk_size)
-        # 通过仓储层统一访问数据库，内部已使用 iterator() 做流式查询
         return self.repo.get_domains_for_export(target_id=target_id, batch_size=chunk_size)
 
+    def iter_raw_data_for_csv_export(self, target_id: int):
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            target_id: 目标 ID
+        
+        Yields:
+            原始数据字典 {name, created_at}
+        """
+        return self.repo.iter_raw_data_for_export(target_id=target_id)
 
-__all__ = ['SubdomainService']
+    # ==================== 创建操作 ====================
+
+    def bulk_create_ignore_conflicts(self, items: List[SubdomainDTO]) -> None:
+        """
+        批量创建子域名，忽略冲突
+        
+        Args:
+            items: 子域名 DTO 列表
+        
+        Note:
+            使用 ignore_conflicts 策略，重复记录会被跳过
+        """
+        logger.debug("批量创建子域名 - 数量: %d", len(items))
+        return self.repo.bulk_create_ignore_conflicts(items)
+
+    def bulk_create_subdomains(
+        self,
+        target_id: int,
+        target_name: str,
+        subdomains: List[str]
+    ) -> BulkCreateResult:
+        """
+        批量创建子域名（带验证）
+        
+        Args:
+            target_id: 目标 ID
+            target_name: 目标域名（用于匹配验证）
+            subdomains: 子域名列表
+        
+        Returns:
+            BulkCreateResult: 创建结果统计
+        """
+        total_received = len(subdomains)
+        target_name = target_name.lower().strip()
+        
+        def is_subdomain_match(subdomain: str) -> bool:
+            """验证子域名是否匹配目标域名"""
+            if subdomain == target_name:
+                return True
+            if subdomain.endswith('.' + target_name):
+                return True
+            return False
+        
+        # 过滤有效的子域名
+        valid_subdomains = []
+        invalid_count = 0
+        mismatched_count = 0
+        
+        for subdomain in subdomains:
+            if not isinstance(subdomain, str) or not subdomain.strip():
+                continue
+            
+            subdomain = subdomain.lower().strip()
+            
+            # 验证格式
+            if not is_valid_domain(subdomain):
+                invalid_count += 1
+                continue
+            
+            # 验证匹配
+            if not is_subdomain_match(subdomain):
+                mismatched_count += 1
+                continue
+            
+            valid_subdomains.append(subdomain)
+        
+        # 去重
+        unique_subdomains = list(set(valid_subdomains))
+        duplicate_count = len(valid_subdomains) - len(unique_subdomains)
+        
+        if not unique_subdomains:
+            return BulkCreateResult(
+                created_count=0,
+                skipped_count=duplicate_count,
+                invalid_count=invalid_count,
+                mismatched_count=mismatched_count,
+                total_received=total_received,
+            )
+        
+        # 获取创建前的数量
+        count_before = self.repo.count_by_target(target_id)
+        
+        # 创建 DTO 列表并批量创建
+        subdomain_dtos = [
+            SubdomainDTO(name=name, target_id=target_id)
+            for name in unique_subdomains
+        ]
+        self.repo.bulk_create_ignore_conflicts(subdomain_dtos)
+        
+        # 获取创建后的数量
+        count_after = self.repo.count_by_target(target_id)
+        created_count = count_after - count_before
+        
+        # 计算因数据库冲突跳过的数量
+        db_skipped = len(unique_subdomains) - created_count
+        
+        return BulkCreateResult(
+            created_count=created_count,
+            skipped_count=duplicate_count + db_skipped,
+            invalid_count=invalid_count,
+            mismatched_count=mismatched_count,
+            total_received=total_received,
+        )
+
+
+__all__ = ['SubdomainService', 'BulkCreateResult']

backend/apps/asset/services/asset/vulnerability_service.py

@@ -1,11 +1,13 @@
 """Vulnerability Service - 漏洞资产业务逻辑层"""
 
 import logging
-from typing import List
+from typing import List, Optional
 
 from apps.asset.models import Vulnerability
 from apps.asset.dtos.asset import VulnerabilityDTO
 from apps.common.decorators import auto_ensure_db_connection
+from apps.common.utils import deduplicate_for_bulk
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
@@ -16,10 +18,20 @@ class VulnerabilityService:
 
     当前提供基础的批量创建能力，使用 ignore_conflicts 依赖数据库唯一约束去重。
     """
+    
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'type': 'vuln_type',
+        'severity': 'severity',
+        'source': 'source',
+        'url': 'url',
+    }
 
     def bulk_create_ignore_conflicts(self, items: List[VulnerabilityDTO]) -> None:
         """批量创建漏洞资产记录，忽略冲突。
 
+        注意：会自动按 (target_id, url, vuln_type, source) 去重，保留最后一条记录。
+
         Note:
             - 是否去重取决于模型上的唯一/部分唯一约束；
             - 当前 Vulnerability 模型未定义唯一约束，因此会保留全部记录。
@@ -29,6 +41,9 @@ class VulnerabilityService:
             return
 
         try:
+            # 根据模型唯一约束自动去重（如果模型没有唯一约束则跳过）
+            unique_items = deduplicate_for_bulk(items, Vulnerability)
+            
             vulns = [
                 Vulnerability(
                     target_id=item.target_id,
@@ -40,7 +55,7 @@ class VulnerabilityService:
                     description=item.description,
                     raw_output=item.raw_output,
                 )
-                for item in items
+                for item in unique_items
             ]
 
             Vulnerability.objects.bulk_create(vulns, ignore_conflicts=True)
@@ -57,24 +72,34 @@ class VulnerabilityService:
 
     # ==================== 查询方法 ====================
 
-    def get_all(self):
+    def get_all(self, filter_query: Optional[str] = None):
         """获取所有漏洞 QuerySet（用于全局漏洞列表）。
 
-        Returns:
-            QuerySet[Vulnerability]: 所有漏洞，按发现时间倒序
-        """
-        return Vulnerability.objects.filter(deleted_at__isnull=True).order_by("-discovered_at")
+        Args:
+            filter_query: 智能过滤语法字符串
 
-    def get_queryset_by_target(self, target_id: int):
+        Returns:
+            QuerySet[Vulnerability]: 所有漏洞，按创建时间倒序
+        """
+        queryset = Vulnerability.objects.all().order_by("-created_at")
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
+
+    def get_vulnerabilities_by_target(self, target_id: int, filter_query: Optional[str] = None):
         """按目标获取漏洞 QuerySet（用于分页）。
 
         Args:
             target_id: 目标 ID
+            filter_query: 智能过滤语法字符串
 
         Returns:
-            QuerySet[Vulnerability]: 目标下的所有漏洞，按发现时间倒序
+            QuerySet[Vulnerability]: 目标下的所有漏洞，按创建时间倒序
         """
-        return Vulnerability.objects.filter(target_id=target_id).order_by("-discovered_at")
+        queryset = Vulnerability.objects.filter(target_id=target_id).order_by("-created_at")
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def count_by_target(self, target_id: int) -> int:
         """统计目标下的漏洞数量。"""

backend/apps/asset/services/asset/website_service.py

@@ -1,8 +1,12 @@
+"""WebSite Service - 网站业务逻辑层"""
+
 import logging
-from typing import Tuple, List
+from typing import List, Iterator, Optional
 
 from apps.asset.repositories import DjangoWebSiteRepository
 from apps.asset.dtos import WebSiteDTO
+from apps.common.validators import is_valid_url, is_url_match_target
+from apps.common.utils.filter_utils import apply_filters
 
 logger = logging.getLogger(__name__)
 
@@ -10,82 +14,129 @@ logger = logging.getLogger(__name__)
 class WebSiteService:
     """网站业务逻辑层"""
     
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'host': 'host',
+        'title': 'title',
+        'status': 'status_code',
+        'tech': 'tech',
+    }
+    
     def __init__(self, repository=None):
-        """
-        初始化网站服务
-        
-        Args:
-            repository: 网站仓储实例（用于依赖注入）
-        """
+        """初始化网站服务"""
         self.repo = repository or DjangoWebSiteRepository()
     
-    # ==================== 创建操作 ====================
-    
-    def bulk_create_ignore_conflicts(self, website_dtos: List[WebSiteDTO]) -> None:
+    def bulk_upsert(self, website_dtos: List[WebSiteDTO]) -> int:
         """
-        批量创建网站记录，忽略冲突（用于扫描任务）
+        批量创建或更新网站（upsert）
+        
+        存在则更新所有字段，不存在则创建。
         
         Args:
             website_dtos: WebSiteDTO 列表
-        
-        Note:
-            使用 ignore_conflicts 策略，重复记录会被跳过
-        """
-        logger.debug("批量创建网站 - 数量: %d", len(website_dtos))
-        return self.repo.bulk_create_ignore_conflicts(website_dtos)
-    
-    # ==================== 查询操作 ====================
-    
-    def get_by_url(self, url: str, target_id: int) -> int:
-        """
-        根据 URL 和 target_id 查找网站 ID
-        
-        Args:
-            url: 网站 URL
-            target_id: 目标 ID
             
         Returns:
-            int: 网站 ID，如果不存在返回 None
+            int: 处理的记录数
         """
-        return self.repo.get_by_url(url=url, target_id=target_id)
-    
-    # ==================== 查询操作 ====================
-
-    def get_all(self):
-        """
-        获取所有网站
+        if not website_dtos:
+            return 0
         
-        Returns:
-            QuerySet: 网站查询集
-        """
-        logger.debug("获取所有网站")
-        return self.repo.get_all()
+        try:
+            return self.repo.bulk_upsert(website_dtos)
+        except Exception as e:
+            logger.error(f"批量 upsert 网站失败: {e}")
+            raise
     
-    def get_websites_by_target(self, target_id: int):
-        return self.repo.get_by_target(target_id)
-    
-    def count_websites_by_scan(self, scan_id: int) -> int:
+    def bulk_create_urls(self, target_id: int, target_name: str, target_type: str, urls: List[str]) -> int:
         """
-        统计扫描下的网站数量
+        批量创建网站（仅 URL，使用 ignore_conflicts）
+        
+        验证 URL 格式和匹配，过滤无效/不匹配 URL，去重后批量创建。
+        已存在的记录会被跳过。
         
         Args:
-            scan_id: 扫描 ID
-        
+            target_id: 目标 ID
+            target_name: 目标名称（用于匹配验证）
+            target_type: 目标类型 ('domain', 'ip', 'cidr')
+            urls: URL 列表
+            
         Returns:
-            int: 网站数量
+            int: 实际创建的记录数
         """
-        logger.debug("统计扫描下网站数量 - Scan ID: %d", scan_id)
-        return self.repo.count_by_scan(scan_id)
+        if not urls:
+            return 0
+        
+        # 过滤有效 URL 并去重
+        valid_urls = []
+        seen = set()
+        
+        for url in urls:
+            if not isinstance(url, str):
+                continue
+            url = url.strip()
+            if not url or url in seen:
+                continue
+            if not is_valid_url(url):
+                continue
+            
+            # 匹配验证（前端已阻止不匹配的提交，后端作为双重保障）
+            if not is_url_match_target(url, target_name, target_type):
+                continue
+            
+            seen.add(url)
+            valid_urls.append(url)
+        
+        if not valid_urls:
+            return 0
+        
+        # 获取创建前的数量
+        count_before = self.repo.count_by_target(target_id)
+        
+        # 创建 DTO 列表并批量创建
+        website_dtos = [
+            WebSiteDTO(url=url, target_id=target_id)
+            for url in valid_urls
+        ]
+        self.repo.bulk_create_ignore_conflicts(website_dtos)
+        
+        # 获取创建后的数量
+        count_after = self.repo.count_by_target(target_id)
+        return count_after - count_before
+    
+    def get_websites_by_target(self, target_id: int, filter_query: Optional[str] = None):
+        """获取目标下的所有网站"""
+        queryset = self.repo.get_by_target(target_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING, json_array_fields=['tech'])
+        return queryset
+    
+    def get_all(self, filter_query: Optional[str] = None):
+        """获取所有网站"""
+        queryset = self.repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING, json_array_fields=['tech'])
+        return queryset
+    
+    def get_by_url(self, url: str, target_id: int) -> int:
+        """根据 URL 和 target_id 查找网站 ID"""
+        return self.repo.get_by_url(url=url, target_id=target_id)
     
     def iter_website_urls_by_target(self, target_id: int, chunk_size: int = 1000):
-        """流式获取目标下的所有站点 URL（内存优化，委托给 Repository 层）"""
-        logger.debug(
-            "流式获取目标下所有站点 URL - Target ID: %d, 批次大小: %d",
-            target_id,
-            chunk_size,
-        )
-        # 通过仓储层统一访问数据库，避免 Service 直接依赖 ORM
+        """流式获取目标下的所有站点 URL"""
         return self.repo.get_urls_for_export(target_id=target_id, batch_size=chunk_size)
 
+    def iter_raw_data_for_csv_export(self, target_id: int) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            target_id: 目标 ID
+        
+        Yields:
+            原始数据字典
+        """
+        return self.repo.iter_raw_data_for_export(target_id=target_id)
+
 
 __all__ = ['WebSiteService']

backend/apps/asset/services/snapshot/directory_snapshots_service.py

@@ -26,10 +26,9 @@ class DirectorySnapshotsService:
         2. 同步到资产表（去重，不包含 scan_id）
         
         Args:
-            items: 目录快照 DTO 列表（必须包含 website_id）
+            items: 目录快照 DTO 列表（必须包含 target_id）
         
         Raises:
-            ValueError: 如果 items 中的 website_id 为 None
             Exception: 数据库操作失败
         """
         if not items:
@@ -49,14 +48,13 @@ class DirectorySnapshotsService:
             logger.debug("步骤 1: 保存到快照表")
             self.snapshot_repo.save_snapshots(items)
             
-            # 步骤 2: 转换为资产 DTO 并保存到资产表
-            # 注意：去重是通过数据库的 UNIQUE 约束 + ignore_conflicts 实现的
+            # 步骤 2: 转换为资产 DTO 并保存到资产表（upsert）
             # - 新记录：插入资产表
-            # - 已存在的记录：自动跳过
-            logger.debug("步骤 2: 同步到资产表（通过 Service 层）")
+            # - 已存在的记录：更新字段（created_at 不更新，保留创建时间）
+            logger.debug("步骤 2: 同步到资产表（通过 Service 层，upsert）")
             asset_items = [item.to_asset_dto() for item in items]
             
-            self.asset_service.bulk_create_ignore_conflicts(asset_items)
+            self.asset_service.bulk_upsert(asset_items)
             
             logger.info("目录快照和资产数据保存成功 - 数量: %d", len(items))
             
@@ -69,15 +67,44 @@ class DirectorySnapshotsService:
             )
             raise
     
-    def get_by_scan(self, scan_id: int):
-        return self.snapshot_repo.get_by_scan(scan_id)
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'status': 'status',
+        'content_type': 'content_type',
+    }
+    
+    def get_by_scan(self, scan_id: int, filter_query: str = None):
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_by_scan(scan_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
-    def get_all(self):
+    def get_all(self, filter_query: str = None):
         """获取所有目录快照"""
-        return self.snapshot_repo.get_all()
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_directory_urls_by_scan(self, scan_id: int, chunk_size: int = 1000) -> Iterator[str]:
         """流式获取某次扫描下的所有目录 URL。"""
         queryset = self.snapshot_repo.get_by_scan(scan_id)
         for snapshot in queryset.iterator(chunk_size=chunk_size):
             yield snapshot.url
+
+    def iter_raw_data_for_csv_export(self, scan_id: int) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            scan_id: 扫描 ID
+        
+        Yields:
+            原始数据字典
+        """
+        return self.snapshot_repo.iter_raw_data_for_export(scan_id=scan_id)

backend/apps/asset/services/snapshot/endpoint_snapshots_service.py

@@ -50,13 +50,11 @@ class EndpointSnapshotsService:
             self.snapshot_repo.save_snapshots(items)
             
             # 步骤 2: 转换为资产 DTO 并保存到资产表
-            # 注意：去重是通过数据库的 UNIQUE 约束 + ignore_conflicts 实现的
-            # - 新记录：插入资产表
-            # - 已存在的记录：自动跳过
+            # 使用 upsert：新记录插入，已存在的记录更新
             logger.debug("步骤 2: 同步到资产表（通过 Service 层）")
             asset_items = [item.to_asset_dto() for item in items]
             
-            self.asset_service.bulk_create_endpoints(asset_items)
+            self.asset_service.bulk_upsert(asset_items)
             
             logger.info("端点快照和资产数据保存成功 - 数量: %d", len(items))
             
@@ -69,15 +67,47 @@ class EndpointSnapshotsService:
             )
             raise
     
-    def get_by_scan(self, scan_id: int):
-        return self.snapshot_repo.get_by_scan(scan_id)
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'host': 'host',
+        'title': 'title',
+        'status': 'status_code',
+        'webserver': 'webserver',
+        'tech': 'tech',
+    }
+    
+    def get_by_scan(self, scan_id: int, filter_query: str = None):
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_by_scan(scan_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
-    def get_all(self):
+    def get_all(self, filter_query: str = None):
         """获取所有端点快照"""
-        return self.snapshot_repo.get_all()
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_endpoint_urls_by_scan(self, scan_id: int, chunk_size: int = 1000) -> Iterator[str]:
         """流式获取某次扫描下的所有端点 URL。"""
         queryset = self.snapshot_repo.get_by_scan(scan_id)
         for snapshot in queryset.iterator(chunk_size=chunk_size):
             yield snapshot.url
+
+    def iter_raw_data_for_csv_export(self, scan_id: int) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            scan_id: 扫描 ID
+        
+        Yields:
+            原始数据字典
+        """
+        return self.snapshot_repo.iter_raw_data_for_export(scan_id=scan_id)

backend/apps/asset/services/snapshot/host_port_mapping_snapshots_service.py

@@ -69,13 +69,25 @@ class HostPortMappingSnapshotsService:
             )
             raise
     
-    def get_ip_aggregation_by_scan(self, scan_id: int, search: str = None):
-        return self.snapshot_repo.get_ip_aggregation_by_scan(scan_id, search=search)
+    def get_ip_aggregation_by_scan(self, scan_id: int, filter_query: str = None):
+        return self.snapshot_repo.get_ip_aggregation_by_scan(scan_id, filter_query=filter_query)
 
-    def get_all_ip_aggregation(self, search: str = None):
+    def get_all_ip_aggregation(self, filter_query: str = None):
         """获取所有 IP 聚合数据"""
-        return self.snapshot_repo.get_all_ip_aggregation(search=search)
+        return self.snapshot_repo.get_all_ip_aggregation(filter_query=filter_query)
 
     def iter_ips_by_scan(self, scan_id: int, batch_size: int = 1000) -> Iterator[str]:
         """流式获取某次扫描下的所有唯一 IP 地址。"""
         return self.snapshot_repo.get_ips_for_export(scan_id=scan_id, batch_size=batch_size)
+
+    def iter_raw_data_for_csv_export(self, scan_id: int) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            scan_id: 扫描 ID
+        
+        Yields:
+            原始数据字典 {ip, host, port, created_at}
+        """
+        return self.snapshot_repo.iter_raw_data_for_export(scan_id=scan_id)

backend/apps/asset/services/snapshot/subdomain_snapshots_service.py

@@ -66,14 +66,41 @@ class SubdomainSnapshotsService:
             )
             raise
     
-    def get_by_scan(self, scan_id: int):
-        return self.subdomain_snapshot_repo.get_by_scan(scan_id)
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+    }
+    
+    def get_by_scan(self, scan_id: int, filter_query: str = None):
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.subdomain_snapshot_repo.get_by_scan(scan_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
-    def get_all(self):
+    def get_all(self, filter_query: str = None):
         """获取所有子域名快照"""
-        return self.subdomain_snapshot_repo.get_all()
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.subdomain_snapshot_repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_subdomain_names_by_scan(self, scan_id: int, chunk_size: int = 1000) -> Iterator[str]:
         queryset = self.subdomain_snapshot_repo.get_by_scan(scan_id)
         for snapshot in queryset.iterator(chunk_size=chunk_size):
-            yield snapshot.name
+            yield snapshot.name
+
+    def iter_raw_data_for_csv_export(self, scan_id: int) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            scan_id: 扫描 ID
+        
+        Yields:
+            原始数据字典 {name, created_at}
+        """
+        return self.subdomain_snapshot_repo.iter_raw_data_for_export(scan_id=scan_id)

backend/apps/asset/services/snapshot/vulnerability_snapshots_service.py

@@ -66,13 +66,31 @@ class VulnerabilitySnapshotsService:
             )
             raise
 
-    def get_by_scan(self, scan_id: int):
-        """按扫描任务获取所有漏洞快照。"""
-        return self.snapshot_repo.get_by_scan(scan_id)
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'type': 'vuln_type',
+        'url': 'url',
+        'severity': 'severity',
+        'source': 'source',
+    }
 
-    def get_all(self):
+    def get_by_scan(self, scan_id: int, filter_query: str = None):
+        """按扫描任务获取所有漏洞快照。"""
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_by_scan(scan_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
+
+    def get_all(self, filter_query: str = None):
         """获取所有漏洞快照"""
-        return self.snapshot_repo.get_all()
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_vuln_urls_by_scan(self, scan_id: int, chunk_size: int = 1000) -> Iterator[str]:
         """流式获取某次扫描下的所有漏洞 URL。"""

backend/apps/asset/services/snapshot/website_snapshots_service.py

@@ -49,14 +49,13 @@ class WebsiteSnapshotsService:
             logger.debug("步骤 1: 保存到快照表")
             self.snapshot_repo.save_snapshots(items)
             
-            # 步骤 2: 转换为资产 DTO 并保存到资产表
-            # 注意：去重是通过数据库的 UNIQUE 约束 + ignore_conflicts 实现的
+            # 步骤 2: 转换为资产 DTO 并保存到资产表（upsert）
             # - 新记录：插入资产表
-            # - 已存在的记录：自动跳过
-            logger.debug("步骤 2: 同步到资产表（通过 Service 层）")
+            # - 已存在的记录：更新字段（created_at 不更新，保留创建时间）
+            logger.debug("步骤 2: 同步到资产表（通过 Service 层，upsert）")
             asset_items = [item.to_asset_dto() for item in items]
             
-            self.asset_service.bulk_create_ignore_conflicts(asset_items)
+            self.asset_service.bulk_upsert(asset_items)
             
             logger.info("网站快照和资产数据保存成功 - 数量: %d", len(items))
             
@@ -69,15 +68,47 @@ class WebsiteSnapshotsService:
             )
             raise
     
-    def get_by_scan(self, scan_id: int):
-        return self.snapshot_repo.get_by_scan(scan_id)
+    # 智能过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'url': 'url',
+        'host': 'host',
+        'title': 'title',
+        'status': 'status',
+        'webserver': 'web_server',
+        'tech': 'tech',
+    }
+    
+    def get_by_scan(self, scan_id: int, filter_query: str = None):
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_by_scan(scan_id)
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
-    def get_all(self):
+    def get_all(self, filter_query: str = None):
         """获取所有网站快照"""
-        return self.snapshot_repo.get_all()
+        from apps.common.utils.filter_utils import apply_filters
+        
+        queryset = self.snapshot_repo.get_all()
+        if filter_query:
+            queryset = apply_filters(queryset, filter_query, self.FILTER_FIELD_MAPPING)
+        return queryset
 
     def iter_website_urls_by_scan(self, scan_id: int, chunk_size: int = 1000) -> Iterator[str]:
-        """流式获取某次扫描下的所有站点 URL（按发现时间倒序）。"""
+        """流式获取某次扫描下的所有站点 URL（按创建时间倒序）。"""
         queryset = self.snapshot_repo.get_by_scan(scan_id)
         for snapshot in queryset.iterator(chunk_size=chunk_size):
             yield snapshot.url
+
+    def iter_raw_data_for_csv_export(self, scan_id: int) -> Iterator[dict]:
+        """
+        流式获取原始数据用于 CSV 导出
+        
+        Args:
+            scan_id: 扫描 ID
+        
+        Yields:
+            原始数据字典
+        """
+        return self.snapshot_repo.iter_raw_data_for_export(scan_id=scan_id)

backend/apps/common/container_bootstrap.py

@@ -14,6 +14,10 @@ import os
 import sys
 import requests
 import logging
+import urllib3
+
+# 禁用自签名证书的 SSL 警告（远程 Worker 场景）
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 logger = logging.getLogger(__name__)
 
@@ -30,21 +34,34 @@ def fetch_config_and_setup_django():
         print("[ERROR] 缺少 SERVER_URL 环境变量", file=sys.stderr)
         sys.exit(1)
     
-    config_url = f"{server_url}/api/workers/config/"
+    # 通过环境变量声明 Worker 身份（本地/远程）
+    is_local = os.environ.get("IS_LOCAL", "false").lower() == "true"
+    config_url = f"{server_url}/api/workers/config/?is_local={str(is_local).lower()}"
+    print(f"[CONFIG] 正在从配置中心获取配置: {config_url}")
+    print(f"[CONFIG] IS_LOCAL={is_local}")
     try:
-        resp = requests.get(config_url, timeout=10)
+        # 构建请求头（包含 Worker API Key）
+        headers = {}
+        worker_api_key = os.environ.get("WORKER_API_KEY", "")
+        if worker_api_key:
+            headers["X-Worker-API-Key"] = worker_api_key
+        
+        # verify=False: 远程 Worker 通过 HTTPS 访问时可能使用自签名证书
+        resp = requests.get(config_url, headers=headers, timeout=10, verify=False)
         resp.raise_for_status()
         config = resp.json()
         
         # 数据库配置（必需）
-        os.environ.setdefault("DB_HOST", config['db']['host'])
-        os.environ.setdefault("DB_PORT", config['db']['port'])
-        os.environ.setdefault("DB_NAME", config['db']['name'])
-        os.environ.setdefault("DB_USER", config['db']['user'])
-        os.environ.setdefault("DB_PASSWORD", config['db']['password'])
+        db_host = config['db']['host']
+        db_port = config['db']['port']
+        db_name = config['db']['name']
+        db_user = config['db']['user']
         
-        # Redis 配置
-        os.environ.setdefault("REDIS_URL", config['redisUrl'])
+        os.environ.setdefault("DB_HOST", db_host)
+        os.environ.setdefault("DB_PORT", db_port)
+        os.environ.setdefault("DB_NAME", db_name)
+        os.environ.setdefault("DB_USER", db_user)
+        os.environ.setdefault("DB_PASSWORD", config['db']['password'])
         
         # 日志配置
         os.environ.setdefault("LOG_DIR", config['paths']['logs'])
@@ -52,7 +69,11 @@ def fetch_config_and_setup_django():
         os.environ.setdefault("ENABLE_COMMAND_LOGGING", str(config['logging']['enableCommandLogging']).lower())
         os.environ.setdefault("DEBUG", str(config['debug']))
         
-        print(f"[CONFIG] 从配置中心获取配置成功: {config_url}")
+        print(f"[CONFIG] ✓ 配置获取成功")
+        print(f"[CONFIG]   DB_HOST: {db_host}")
+        print(f"[CONFIG]   DB_PORT: {db_port}")
+        print(f"[CONFIG]   DB_NAME: {db_name}")
+        print(f"[CONFIG]   DB_USER: {db_user}")
         
     except Exception as e:
         print(f"[ERROR] 获取配置失败: {config_url} - {e}", file=sys.stderr)

backend/apps/common/error_codes.py

@@ -0,0 +1,31 @@
+"""
+标准化错误码定义
+
+采用简化方案（参考 Stripe、GitHub 等大厂做法）：
+- 只定义 5-10 个通用错误码
+- 未知错误使用通用错误码
+- 错误码格式：大写字母和下划线组成
+"""
+
+
+class ErrorCodes:
+    """标准化错误码
+    
+    只定义通用错误码，其他错误使用通用消息。
+    这是 Stripe、GitHub 等大厂的标准做法。
+    
+    错误码格式规范：
+    - 使用大写字母和下划线
+    - 简洁明了，易于理解
+    - 前端通过错误码映射到 i18n 键
+    """
+    
+    # 通用错误码（8 个）
+    VALIDATION_ERROR = 'VALIDATION_ERROR'      # 输入验证失败
+    NOT_FOUND = 'NOT_FOUND'                    # 资源未找到
+    PERMISSION_DENIED = 'PERMISSION_DENIED'    # 权限不足
+    SERVER_ERROR = 'SERVER_ERROR'              # 服务器内部错误
+    BAD_REQUEST = 'BAD_REQUEST'                # 请求格式错误
+    CONFLICT = 'CONFLICT'                      # 资源冲突（如重复创建）
+    UNAUTHORIZED = 'UNAUTHORIZED'              # 未认证
+    RATE_LIMITED = 'RATE_LIMITED'              # 请求过于频繁

backend/apps/common/exception_handlers.py

@@ -0,0 +1,49 @@
+"""
+自定义异常处理器
+
+统一处理 DRF 异常，确保错误响应格式一致
+"""
+
+from rest_framework.views import exception_handler
+from rest_framework import status
+from rest_framework.exceptions import AuthenticationFailed, NotAuthenticated
+
+from apps.common.response_helpers import error_response
+from apps.common.error_codes import ErrorCodes
+
+
+def custom_exception_handler(exc, context):
+    """
+    自定义异常处理器
+    
+    处理认证相关异常，返回统一格式的错误响应
+    """
+    # 先调用 DRF 默认的异常处理器
+    response = exception_handler(exc, context)
+    
+    if response is not None:
+        # 处理 401 未认证错误
+        if response.status_code == status.HTTP_401_UNAUTHORIZED:
+            return error_response(
+                code=ErrorCodes.UNAUTHORIZED,
+                message='Authentication required',
+                status_code=status.HTTP_401_UNAUTHORIZED
+            )
+        
+        # 处理 403 权限不足错误
+        if response.status_code == status.HTTP_403_FORBIDDEN:
+            return error_response(
+                code=ErrorCodes.PERMISSION_DENIED,
+                message='Permission denied',
+                status_code=status.HTTP_403_FORBIDDEN
+            )
+    
+    # 处理 NotAuthenticated 和 AuthenticationFailed 异常
+    if isinstance(exc, (NotAuthenticated, AuthenticationFailed)):
+        return error_response(
+            code=ErrorCodes.UNAUTHORIZED,
+            message='Authentication required',
+            status_code=status.HTTP_401_UNAUTHORIZED
+        )
+    
+    return response

backend/apps/common/permissions.py

@@ -0,0 +1,80 @@
+"""
+集中式权限管理
+
+实现三类端点的认证逻辑：
+1. 公开端点（无需认证）：登录、登出、获取当前用户状态
+2. Worker 端点（API Key 认证）：注册、配置、心跳、回调、资源同步
+3. 业务端点（Session 认证）：其他所有 API
+"""
+
+import re
+import logging
+from django.conf import settings
+from rest_framework.permissions import BasePermission
+
+logger = logging.getLogger(__name__)
+
+# 公开端点白名单（无需任何认证）
+PUBLIC_ENDPOINTS = [
+    r'^/api/auth/login/$',
+    r'^/api/auth/logout/$',
+    r'^/api/auth/me/$',
+]
+
+# Worker API 端点（需要 API Key 认证）
+# 包括：注册、配置、心跳、回调、资源同步（字典下载）
+WORKER_ENDPOINTS = [
+    r'^/api/workers/register/$',
+    r'^/api/workers/config/$',
+    r'^/api/workers/\d+/heartbeat/$',
+    r'^/api/callbacks/',
+    # 资源同步端点（Worker 需要下载字典文件）
+    r'^/api/wordlists/download/$',
+    # 注意：指纹导出 API 使用 Session 认证（前端用户导出用）
+    # Worker 通过数据库直接获取指纹数据，不需要 HTTP API
+]
+
+
+class IsAuthenticatedOrPublic(BasePermission):
+    """
+    自定义权限类：
+    - 白名单内的端点公开访问
+    - Worker 端点需要 API Key 认证
+    - 其他端点需要 Session 认证
+    """
+    
+    def has_permission(self, request, view):
+        path = request.path
+        
+        # 检查是否在公开白名单内
+        for pattern in PUBLIC_ENDPOINTS:
+            if re.match(pattern, path):
+                return True
+        
+        # 检查是否是 Worker 端点
+        for pattern in WORKER_ENDPOINTS:
+            if re.match(pattern, path):
+                return self._check_worker_api_key(request)
+        
+        # 其他路径需要 Session 认证
+        return request.user and request.user.is_authenticated
+    
+    def _check_worker_api_key(self, request):
+        """验证 Worker API Key"""
+        api_key = request.headers.get('X-Worker-API-Key')
+        expected_key = getattr(settings, 'WORKER_API_KEY', None)
+        
+        if not expected_key:
+            # 未配置 API Key 时，拒绝所有 Worker 请求
+            logger.warning("WORKER_API_KEY 未配置，拒绝 Worker 请求")
+            return False
+        
+        if not api_key:
+            logger.warning(f"Worker 请求缺少 X-Worker-API-Key Header: {request.path}")
+            return False
+        
+        if api_key != expected_key:
+            logger.warning(f"Worker API Key 无效: {request.path}")
+            return False
+        
+        return True

backend/apps/common/prefect_django_setup.py

@@ -16,6 +16,7 @@ def setup_django_for_prefect():
     1. 添加项目根目录到 Python 路径
     2. 设置 DJANGO_SETTINGS_MODULE 环境变量
     3. 调用 django.setup() 初始化 Django
+    4. 关闭旧的数据库连接，确保使用新连接
     
     使用方式：
         from apps.common.prefect_django_setup import setup_django_for_prefect
@@ -36,6 +37,25 @@ def setup_django_for_prefect():
     # 初始化 Django
     import django
     django.setup()
+    
+    # 关闭所有旧的数据库连接，确保 Worker 进程使用新连接
+    # 解决 "server closed the connection unexpectedly" 问题
+    from django.db import connections
+    connections.close_all()
+
+
+def close_old_db_connections():
+    """
+    关闭旧的数据库连接
+    
+    在长时间运行的任务中调用此函数，可以确保使用有效的数据库连接。
+    适用于：
+    - Flow 开始前
+    - Task 开始前
+    - 长时间空闲后恢复操作前
+    """
+    from django.db import connections
+    connections.close_all()
 
 
 # 自动执行初始化（导入即生效）

backend/apps/common/response_helpers.py

@@ -0,0 +1,88 @@
+"""
+标准化 API 响应辅助函数
+
+遵循行业标准（RFC 9457 Problem Details）和大厂实践（Google、Stripe、GitHub）：
+- 成功响应只包含数据，不包含 message 字段
+- 错误响应使用机器可读的错误码，前端映射到 i18n 消息
+"""
+from typing import Any, Dict, List, Optional, Union
+
+from rest_framework import status
+from rest_framework.response import Response
+
+
+def success_response(
+    data: Optional[Union[Dict[str, Any], List[Any]]] = None,
+    status_code: int = status.HTTP_200_OK
+) -> Response:
+    """
+    标准化成功响应
+    
+    直接返回数据，不做包装，符合 Stripe/GitHub 等大厂标准。
+    
+    Args:
+        data: 响应数据（dict 或 list）
+        status_code: HTTP 状态码，默认 200
+    
+    Returns:
+        Response: DRF Response 对象
+    
+    Examples:
+        # 单个资源
+        >>> success_response(data={'id': 1, 'name': 'Test'})
+        {'id': 1, 'name': 'Test'}
+        
+        # 操作结果
+        >>> success_response(data={'count': 3, 'scans': [...]})
+        {'count': 3, 'scans': [...]}
+        
+        # 创建资源
+        >>> success_response(data={'id': 1}, status_code=201)
+    """
+    # 注意：不能使用 data or {}，因为空列表 [] 会被转换为 {}
+    if data is None:
+        data = {}
+    return Response(data, status=status_code)
+
+
+def error_response(
+    code: str,
+    message: Optional[str] = None,
+    details: Optional[List[Dict[str, Any]]] = None,
+    status_code: int = status.HTTP_400_BAD_REQUEST
+) -> Response:
+    """
+    标准化错误响应
+    
+    Args:
+        code: 错误码（如 'VALIDATION_ERROR', 'NOT_FOUND'）
+              格式：大写字母和下划线组成
+        message: 开发者调试信息（非用户显示）
+        details: 详细错误信息（如字段级验证错误）
+        status_code: HTTP 状态码，默认 400
+    
+    Returns:
+        Response: DRF Response 对象
+    
+    Examples:
+        # 简单错误
+        >>> error_response(code='NOT_FOUND', status_code=404)
+        {'error': {'code': 'NOT_FOUND'}}
+        
+        # 带调试信息
+        >>> error_response(
+        ...     code='VALIDATION_ERROR',
+        ...     message='Invalid input data',
+        ...     details=[{'field': 'name', 'message': 'Required'}]
+        ... )
+        {'error': {'code': 'VALIDATION_ERROR', 'message': '...', 'details': [...]}}
+    """
+    error_body: Dict[str, Any] = {'code': code}
+    
+    if message:
+        error_body['message'] = message
+    
+    if details:
+        error_body['details'] = details
+    
+    return Response({'error': error_body}, status=status_code)

backend/apps/common/services/__init__.py

@@ -3,8 +3,13 @@
 
 提供系统级别的公共服务，包括：
 - SystemLogService: 系统日志读取服务
+
+注意：FilterService 已移至 apps.common.utils.filter_utils
+推荐使用: from apps.common.utils.filter_utils import apply_filters
 """
 
 from .system_log_service import SystemLogService
 
-__all__ = ['SystemLogService']
+__all__ = [
+    'SystemLogService',
+]

backend/apps/common/services/system_log_service.py

@@ -4,15 +4,28 @@
 提供系统日志的读取功能，支持：
 - 从日志目录读取日志文件
 - 限制返回行数，防止内存溢出
+- 列出可用的日志文件
 """
 
+import fnmatch
 import logging
+import os
 import subprocess
+from datetime import datetime, timezone
+from typing import TypedDict
 
 
 logger = logging.getLogger(__name__)
 
 
+class LogFileInfo(TypedDict):
+    """日志文件信息"""
+    filename: str
+    category: str  # 'system' | 'error' | 'performance' | 'container'
+    size: int
+    modifiedAt: str  # ISO 8601 格式
+
+
 class SystemLogService:
     """
     系统日志服务类
@@ -20,23 +33,131 @@ class SystemLogService:
     负责读取系统日志文件，支持从容器内路径或宿主机挂载路径读取日志。
     """
     
+    # 日志文件分类规则
+    CATEGORY_RULES = [
+        ('xingrin.log', 'system'),
+        ('xingrin_error.log', 'error'),
+        ('performance.log', 'performance'),
+        ('container_*.log', 'container'),
+    ]
+    
     def __init__(self):
-        # 日志文件路径（容器内路径，通过 volume 挂载到宿主机 /opt/xingrin/logs）
-        self.log_file = "/app/backend/logs/xingrin.log"
-        self.default_lines = 200        # 默认返回行数
-        self.max_lines = 10000          # 最大返回行数限制
-        self.timeout_seconds = 3        # tail 命令超时时间
+        # 日志目录路径
+        self.log_dir = "/opt/xingrin/logs"
+        self.default_file = "xingrin.log"  # 默认日志文件
+        self.default_lines = 200           # 默认返回行数
+        self.max_lines = 10000             # 最大返回行数限制
+        self.timeout_seconds = 3           # tail 命令超时时间
 
-    def get_logs_content(self, lines: int | None = None) -> str:
+    def _categorize_file(self, filename: str) -> str | None:
+        """
+        根据文件名判断日志分类
+        
+        Returns:
+            分类名称，如果不是日志文件则返回 None
+        """
+        for pattern, category in self.CATEGORY_RULES:
+            if fnmatch.fnmatch(filename, pattern):
+                return category
+        return None
+
+    def _validate_filename(self, filename: str) -> bool:
+        """
+        验证文件名是否合法（防止路径遍历攻击）
+        
+        Args:
+            filename: 要验证的文件名
+            
+        Returns:
+            bool: 文件名是否合法
+        """
+        # 不允许包含路径分隔符
+        if '/' in filename or '\\' in filename:
+            return False
+        # 不允许 .. 路径遍历
+        if '..' in filename:
+            return False
+        # 必须是已知的日志文件类型
+        return self._categorize_file(filename) is not None
+
+    def get_log_files(self) -> list[LogFileInfo]:
+        """
+        获取所有可用的日志文件列表
+        
+        Returns:
+            日志文件信息列表，按分类和文件名排序
+        """
+        files: list[LogFileInfo] = []
+        
+        if not os.path.isdir(self.log_dir):
+            logger.warning("日志目录不存在: %s", self.log_dir)
+            return files
+        
+        for filename in os.listdir(self.log_dir):
+            filepath = os.path.join(self.log_dir, filename)
+            
+            # 只处理文件，跳过目录
+            if not os.path.isfile(filepath):
+                continue
+            
+            # 判断分类
+            category = self._categorize_file(filename)
+            if category is None:
+                continue
+            
+            # 获取文件信息
+            try:
+                stat = os.stat(filepath)
+                modified_at = datetime.fromtimestamp(
+                    stat.st_mtime, tz=timezone.utc
+                ).isoformat()
+                
+                files.append({
+                    'filename': filename,
+                    'category': category,
+                    'size': stat.st_size,
+                    'modifiedAt': modified_at,
+                })
+            except OSError as e:
+                logger.warning("获取文件信息失败 %s: %s", filepath, e)
+                continue
+        
+        # 排序：按分类优先级（system > error > performance > container），然后按文件名
+        category_order = {'system': 0, 'error': 1, 'performance': 2, 'container': 3}
+        files.sort(key=lambda f: (category_order.get(f['category'], 99), f['filename']))
+        
+        return files
+
+    def get_logs_content(self, filename: str | None = None, lines: int | None = None) -> str:
         """
         获取系统日志内容
         
         Args:
+            filename: 日志文件名，默认为 xingrin.log
             lines: 返回的日志行数，默认 200 行，最大 10000 行
             
         Returns:
             str: 日志内容，每行以换行符分隔，保持原始顺序
+            
+        Raises:
+            ValueError: 文件名不合法
+            FileNotFoundError: 日志文件不存在
         """
+        # 文件名处理
+        if filename is None:
+            filename = self.default_file
+        
+        # 验证文件名
+        if not self._validate_filename(filename):
+            raise ValueError(f"无效的文件名: {filename}")
+        
+        # 构建完整路径
+        log_file = os.path.join(self.log_dir, filename)
+        
+        # 检查文件是否存在
+        if not os.path.isfile(log_file):
+            raise FileNotFoundError(f"日志文件不存在: {filename}")
+        
         # 参数校验和默认值处理
         if lines is None:
             lines = self.default_lines
@@ -48,7 +169,7 @@ class SystemLogService:
             lines = self.max_lines
 
         # 使用 tail 命令读取日志文件末尾内容
-        cmd = ["tail", "-n", str(lines), self.log_file]
+        cmd = ["tail", "-n", str(lines), log_file]
 
         result = subprocess.run(
             cmd,

backend/apps/common/signals.py

@@ -27,3 +27,10 @@ vulnerabilities_saved = Signal()
 #   - worker_name: str Worker 名称
 #   - message: str 失败原因
 worker_delete_failed = Signal()
+
+# 所有 Worker 高负载信号
+# 参数：
+#   - worker_name: str 被选中的 Worker 名称
+#   - cpu: float CPU 使用率
+#   - mem: float 内存使用率
+all_workers_high_load = Signal()

backend/apps/common/urls.py

@@ -7,7 +7,7 @@
 """
 
 from django.urls import path
-from .views import LoginView, LogoutView, MeView, ChangePasswordView, SystemLogsView
+from .views import LoginView, LogoutView, MeView, ChangePasswordView, SystemLogsView, SystemLogFilesView
 
 urlpatterns = [
     # 认证相关
@@ -18,4 +18,5 @@ urlpatterns = [
     
     # 系统管理
     path('system/logs/', SystemLogsView.as_view(), name='system-logs'),
+    path('system/logs/files/', SystemLogFilesView.as_view(), name='system-log-files'),
 ]

backend/apps/common/utils/__init__.py

@@ -0,0 +1,28 @@
+"""Common utilities"""
+
+from .dedup import deduplicate_for_bulk, get_unique_fields
+from .hash import (
+    calc_file_sha256,
+    calc_stream_sha256,
+    safe_calc_file_sha256,
+    is_file_hash_match,
+)
+from .csv_utils import (
+    generate_csv_rows,
+    format_list_field,
+    format_datetime,
+    UTF8_BOM,
+)
+
+__all__ = [
+    'deduplicate_for_bulk',
+    'get_unique_fields',
+    'calc_file_sha256',
+    'calc_stream_sha256',
+    'safe_calc_file_sha256',
+    'is_file_hash_match',
+    'generate_csv_rows',
+    'format_list_field',
+    'format_datetime',
+    'UTF8_BOM',
+]

backend/apps/common/utils/csv_utils.py

@@ -0,0 +1,116 @@
+"""CSV 导出工具模块
+
+提供流式 CSV 生成功能，支持：
+- UTF-8 BOM（Excel 兼容）
+- RFC 4180 规范转义
+- 流式生成（内存友好）
+"""
+
+import csv
+import io
+from datetime import datetime
+from typing import Iterator, Dict, Any, List, Callable, Optional
+
+# UTF-8 BOM，确保 Excel 正确识别编码
+UTF8_BOM = '\ufeff'
+
+
+def generate_csv_rows(
+    data_iterator: Iterator[Dict[str, Any]],
+    headers: List[str],
+    field_formatters: Optional[Dict[str, Callable]] = None
+) -> Iterator[str]:
+    """
+    流式生成 CSV 行
+    
+    Args:
+        data_iterator: 数据迭代器，每个元素是一个字典
+        headers: CSV 表头列表
+        field_formatters: 字段格式化函数字典，key 为字段名，value 为格式化函数
+    
+    Yields:
+        CSV 行字符串（包含换行符）
+    
+    Example:
+        >>> data = [{'ip': '192.168.1.1', 'hosts': ['a.com', 'b.com']}]
+        >>> headers = ['ip', 'hosts']
+        >>> formatters = {'hosts': format_list_field}
+        >>> for row in generate_csv_rows(iter(data), headers, formatters):
+        ...     print(row, end='')
+    """
+    # 输出 BOM + 表头
+    output = io.StringIO()
+    writer = csv.writer(output, quoting=csv.QUOTE_MINIMAL)
+    writer.writerow(headers)
+    yield UTF8_BOM + output.getvalue()
+    
+    # 输出数据行
+    for row_data in data_iterator:
+        output = io.StringIO()
+        writer = csv.writer(output, quoting=csv.QUOTE_MINIMAL)
+        
+        row = []
+        for header in headers:
+            value = row_data.get(header, '')
+            if field_formatters and header in field_formatters:
+                value = field_formatters[header](value)
+            row.append(value if value is not None else '')
+        
+        writer.writerow(row)
+        yield output.getvalue()
+
+
+def format_list_field(values: List, separator: str = ';') -> str:
+    """
+    将列表字段格式化为分号分隔的字符串
+    
+    Args:
+        values: 值列表
+        separator: 分隔符，默认为分号
+    
+    Returns:
+        分隔符连接的字符串
+    
+    Example:
+        >>> format_list_field(['a.com', 'b.com'])
+        'a.com;b.com'
+        >>> format_list_field([80, 443])
+        '80;443'
+        >>> format_list_field([])
+        ''
+        >>> format_list_field(None)
+        ''
+    """
+    if not values:
+        return ''
+    return separator.join(str(v) for v in values)
+
+
+def format_datetime(dt: Optional[datetime]) -> str:
+    """
+    格式化日期时间为字符串（转换为本地时区）
+    
+    Args:
+        dt: datetime 对象或 None
+    
+    Returns:
+        格式化的日期时间字符串，格式为 YYYY-MM-DD HH:MM:SS（本地时区）
+    
+    Example:
+        >>> from datetime import datetime
+        >>> format_datetime(datetime(2024, 1, 15, 10, 30, 0))
+        '2024-01-15 10:30:00'
+        >>> format_datetime(None)
+        ''
+    """
+    if dt is None:
+        return ''
+    if isinstance(dt, str):
+        return dt
+    
+    # 转换为本地时区（从 Django settings 获取）
+    from django.utils import timezone
+    if timezone.is_aware(dt):
+        dt = timezone.localtime(dt)
+    
+    return dt.strftime('%Y-%m-%d %H:%M:%S')

backend/apps/common/utils/dedup.py

@@ -0,0 +1,101 @@
+"""
+批量数据去重工具
+
+用于 bulk_create 前的批次内去重，避免 PostgreSQL ON CONFLICT 错误。
+自动从 Django 模型读取唯一约束字段，无需手动指定。
+"""
+
+import logging
+from typing import List, TypeVar, Tuple, Optional
+
+from django.db import models
+
+logger = logging.getLogger(__name__)
+
+T = TypeVar('T')
+
+
+def get_unique_fields(model: type[models.Model]) -> Optional[Tuple[str, ...]]:
+    """
+    从 Django 模型获取唯一约束字段
+    
+    按优先级查找：
+    1. Meta.constraints 中的 UniqueConstraint
+    2. Meta.unique_together
+    
+    Args:
+        model: Django 模型类
+        
+    Returns:
+        唯一约束字段元组，如果没有则返回 None
+    """
+    meta = model._meta
+    
+    # 1. 优先查找 UniqueConstraint
+    for constraint in getattr(meta, 'constraints', []):
+        if isinstance(constraint, models.UniqueConstraint):
+            # 跳过条件约束（partial unique）
+            if getattr(constraint, 'condition', None) is None:
+                return tuple(constraint.fields)
+    
+    # 2. 回退到 unique_together
+    unique_together = getattr(meta, 'unique_together', None)
+    if unique_together:
+        # unique_together 可能是 (('a', 'b'),) 或 ('a', 'b')
+        if unique_together and isinstance(unique_together[0], (list, tuple)):
+            return tuple(unique_together[0])
+        return tuple(unique_together)
+    
+    return None
+
+
+def deduplicate_for_bulk(items: List[T], model: type[models.Model]) -> List[T]:
+    """
+    根据模型唯一约束对数据去重
+    
+    自动从模型读取唯一约束字段，生成去重 key。
+    保留最后一条记录（后面的数据通常是更新的）。
+    
+    Args:
+        items: 待去重的数据列表（DTO 或 Model 对象）
+        model: Django 模型类（用于读取唯一约束）
+        
+    Returns:
+        去重后的数据列表
+        
+    Example:
+        # 自动从 Endpoint 模型读取唯一约束 (url, target)
+        unique_items = deduplicate_for_bulk(items, Endpoint)
+    """
+    if not items:
+        return items
+    
+    unique_fields = get_unique_fields(model)
+    if unique_fields is None:
+        # 模型没有唯一约束，无需去重
+        logger.debug(f"{model.__name__} 没有唯一约束，跳过去重")
+        return items
+    
+    # 处理外键字段名（target -> target_id）
+    def make_key(item: T) -> tuple:
+        key_parts = []
+        for field in unique_fields:
+            # 尝试 field_id（外键）和 field 两种形式
+            value = getattr(item, f'{field}_id', None)
+            if value is None:
+                value = getattr(item, field, None)
+            key_parts.append(value)
+        return tuple(key_parts)
+    
+    # 使用字典去重，保留最后一条
+    seen = {}
+    for item in items:
+        key = make_key(item)
+        seen[key] = item
+    
+    unique_items = list(seen.values())
+    
+    if len(unique_items) < len(items):
+        logger.debug(f"{model.__name__} 去重: {len(items)} -> {len(unique_items)} 条")
+    
+    return unique_items

backend/apps/common/utils/filter_utils.py

@@ -0,0 +1,281 @@
+"""智能过滤工具 - 通用查询语法解析和 Django ORM 查询构建
+
+支持的语法：
+- field="value"     模糊匹配（包含）
+- field=="value"    精确匹配
+- field!="value"    不等于
+
+逻辑运算符：
+- AND: && 或 and 或 空格（默认）
+- OR:  || 或 or
+
+示例：
+    type="xss" || type="sqli"           # OR
+    type="xss" or type="sqli"           # OR（等价）
+    severity="high" && source="nuclei"  # AND
+    severity="high" source="nuclei"     # AND（空格默认为 AND）
+    severity="high" and source="nuclei" # AND（等价）
+
+使用示例：
+    from apps.common.utils.filter_utils import apply_filters
+    
+    field_mapping = {'ip': 'ip', 'port': 'port', 'host': 'host'}
+    queryset = apply_filters(queryset, 'ip="192" || port="80"', field_mapping)
+"""
+
+import re
+import logging
+from dataclasses import dataclass
+from typing import List, Dict, Optional, Union
+from enum import Enum
+
+from django.db.models import QuerySet, Q
+
+logger = logging.getLogger(__name__)
+
+
+class LogicalOp(Enum):
+    """逻辑运算符"""
+    AND = 'AND'
+    OR = 'OR'
+
+
+@dataclass
+class ParsedFilter:
+    """解析后的过滤条件"""
+    field: str      # 字段名
+    operator: str   # 操作符: '=', '==', '!='
+    value: str      # 原始值
+
+
+@dataclass
+class FilterGroup:
+    """过滤条件组（带逻辑运算符）"""
+    filter: ParsedFilter
+    logical_op: LogicalOp  # 与前一个条件的逻辑关系
+
+
+class QueryParser:
+    """查询语法解析器
+    
+    支持 ||/or (OR) 和 &&/and/空格 (AND) 逻辑运算符
+    """
+    
+    # 正则匹配: field="value", field=="value", field!="value"
+    FILTER_PATTERN = re.compile(r'(\w+)(==|!=|=)"([^"]*)"')
+    
+    # 逻辑运算符模式（带空格）
+    OR_PATTERN = re.compile(r'\s*(\|\||(?<![a-zA-Z])or(?![a-zA-Z]))\s*', re.IGNORECASE)
+    AND_PATTERN = re.compile(r'\s*(&&|(?<![a-zA-Z])and(?![a-zA-Z]))\s*', re.IGNORECASE)
+    
+    @classmethod
+    def parse(cls, query_string: str) -> List[FilterGroup]:
+        """解析查询语法字符串
+        
+        Args:
+            query_string: 查询语法字符串
+        
+        Returns:
+            解析后的过滤条件组列表
+        
+        Examples:
+            >>> QueryParser.parse('type="xss" || type="sqli"')
+            [FilterGroup(filter=..., logical_op=AND),  # 第一个默认 AND
+             FilterGroup(filter=..., logical_op=OR)]
+        """
+        if not query_string or not query_string.strip():
+            return []
+        
+        # 标准化逻辑运算符
+        # 先处理 || 和 or -> __OR__
+        normalized = cls.OR_PATTERN.sub(' __OR__ ', query_string)
+        # 再处理 && 和 and -> __AND__
+        normalized = cls.AND_PATTERN.sub(' __AND__ ', normalized)
+        
+        # 分词：按空格分割，保留逻辑运算符标记
+        tokens = normalized.split()
+        
+        groups = []
+        pending_op = LogicalOp.AND  # 默认 AND
+        
+        for token in tokens:
+            if token == '__OR__':
+                pending_op = LogicalOp.OR
+            elif token == '__AND__':
+                pending_op = LogicalOp.AND
+            else:
+                # 尝试解析为过滤条件
+                match = cls.FILTER_PATTERN.match(token)
+                if match:
+                    field, operator, value = match.groups()
+                    groups.append(FilterGroup(
+                        filter=ParsedFilter(
+                            field=field.lower(),
+                            operator=operator,
+                            value=value
+                        ),
+                        logical_op=pending_op if groups else LogicalOp.AND  # 第一个条件默认 AND
+                    ))
+                    pending_op = LogicalOp.AND  # 重置为默认 AND
+        
+        return groups
+
+
+class QueryBuilder:
+    """Django ORM 查询构建器
+    
+    将解析后的过滤条件转换为 Django ORM 查询，支持 AND/OR 逻辑
+    """
+    
+    @classmethod
+    def build_query(
+        cls,
+        queryset: QuerySet,
+        filter_groups: List[FilterGroup],
+        field_mapping: Dict[str, str],
+        json_array_fields: List[str] = None
+    ) -> QuerySet:
+        """构建 Django ORM 查询
+        
+        Args:
+            queryset: Django QuerySet
+            filter_groups: 解析后的过滤条件组列表
+            field_mapping: 字段映射
+            json_array_fields: JSON 数组字段列表（使用 __contains 查询）
+        
+        Returns:
+            过滤后的 QuerySet
+        """
+        if not filter_groups:
+            return queryset
+        
+        json_array_fields = json_array_fields or []
+        
+        # 构建 Q 对象
+        combined_q = None
+        
+        for group in filter_groups:
+            f = group.filter
+            
+            # 字段映射
+            db_field = field_mapping.get(f.field)
+            if not db_field:
+                logger.debug(f"忽略未知字段: {f.field}")
+                continue
+            
+            # 判断是否为 JSON 数组字段
+            is_json_array = db_field in json_array_fields
+            
+            # 构建单个条件的 Q 对象
+            q = cls._build_single_q(db_field, f.operator, f.value, is_json_array)
+            if q is None:
+                continue
+            
+            # 组合 Q 对象
+            if combined_q is None:
+                combined_q = q
+            elif group.logical_op == LogicalOp.OR:
+                combined_q = combined_q | q
+            else:  # AND
+                combined_q = combined_q & q
+        
+        if combined_q is not None:
+            return queryset.filter(combined_q)
+        return queryset
+    
+    @classmethod
+    def _build_single_q(cls, field: str, operator: str, value: str, is_json_array: bool = False) -> Optional[Q]:
+        """构建单个条件的 Q 对象"""
+        if is_json_array:
+            # JSON 数组字段使用 __contains 查询
+            return Q(**{f'{field}__contains': [value]})
+        
+        if operator == '!=':
+            return cls._build_not_equal_q(field, value)
+        elif operator == '==':
+            return cls._build_exact_q(field, value)
+        else:  # '='
+            return cls._build_fuzzy_q(field, value)
+    
+    @classmethod
+    def _try_convert_to_int(cls, value: str) -> Optional[int]:
+        """尝试将值转换为整数"""
+        try:
+            return int(value.strip())
+        except (ValueError, TypeError):
+            return None
+    
+    @classmethod
+    def _build_fuzzy_q(cls, field: str, value: str) -> Q:
+        """模糊匹配: 包含"""
+        return Q(**{f'{field}__icontains': value})
+    
+    @classmethod
+    def _build_exact_q(cls, field: str, value: str) -> Q:
+        """精确匹配"""
+        int_val = cls._try_convert_to_int(value)
+        if int_val is not None:
+            return Q(**{f'{field}__exact': int_val})
+        return Q(**{f'{field}__exact': value})
+    
+    @classmethod
+    def _build_not_equal_q(cls, field: str, value: str) -> Q:
+        """不等于"""
+        int_val = cls._try_convert_to_int(value)
+        if int_val is not None:
+            return ~Q(**{f'{field}__exact': int_val})
+        return ~Q(**{f'{field}__exact': value})
+
+
+def apply_filters(
+    queryset: QuerySet,
+    query_string: str,
+    field_mapping: Dict[str, str],
+    json_array_fields: List[str] = None
+) -> QuerySet:
+    """应用过滤条件到 QuerySet
+    
+    Args:
+        queryset: Django QuerySet
+        query_string: 查询语法字符串
+        field_mapping: 字段映射
+        json_array_fields: JSON 数组字段列表（使用 __contains 查询）
+    
+    Returns:
+        过滤后的 QuerySet
+    
+    Examples:
+        # OR 查询
+        apply_filters(qs, 'type="xss" || type="sqli"', mapping)
+        apply_filters(qs, 'type="xss" or type="sqli"', mapping)
+        
+        # AND 查询
+        apply_filters(qs, 'severity="high" && source="nuclei"', mapping)
+        apply_filters(qs, 'severity="high" source="nuclei"', mapping)
+        
+        # 混合查询
+        apply_filters(qs, 'type="xss" || type="sqli" && severity="high"', mapping)
+        
+        # JSON 数组字段查询
+        apply_filters(qs, 'implies="PHP"', mapping, json_array_fields=['implies'])
+    """
+    if not query_string or not query_string.strip():
+        return queryset
+    
+    try:
+        filter_groups = QueryParser.parse(query_string)
+        if not filter_groups:
+            logger.debug(f"未解析到有效过滤条件: {query_string}")
+            return queryset
+        
+        logger.debug(f"解析过滤条件: {filter_groups}")
+        return QueryBuilder.build_query(
+            queryset, 
+            filter_groups, 
+            field_mapping,
+            json_array_fields=json_array_fields
+        )
+    
+    except Exception as e:
+        logger.warning(f"过滤解析错误: {e}, query: {query_string}")
+        return queryset  # 静默降级

backend/apps/common/utils/hash.py

@@ -7,7 +7,6 @@
 
 import hashlib
 import logging
-from pathlib import Path
 from typing import Optional, BinaryIO
 
 logger = logging.getLogger(__name__)
@@ -91,11 +90,3 @@ def is_file_hash_match(file_path: str, expected_hash: str) -> bool:
         return False
 
     return actual_hash.lower() == expected_hash.lower()
-
-
-__all__ = [
-    "calc_file_sha256",
-    "calc_stream_sha256",
-    "safe_calc_file_sha256",
-    "is_file_hash_match",
-]

backend/apps/common/validators.py

@@ -1,6 +1,8 @@
-"""域名、IP、端口和目标验证工具函数"""
+"""域名、IP、端口、URL 和目标验证工具函数"""
 import ipaddress
 import logging
+from urllib.parse import urlparse
+
 import validators
 
 logger = logging.getLogger(__name__)
@@ -25,6 +27,21 @@ def validate_domain(domain: str) -> None:
         raise ValueError(f"域名格式无效: {domain}")
 
 
+def is_valid_domain(domain: str) -> bool:
+    """
+    判断是否为有效域名（不抛异常）
+    
+    Args:
+        domain: 域名字符串
+        
+    Returns:
+        bool: 是否为有效域名
+    """
+    if not domain or len(domain) > 253:
+        return False
+    return bool(validators.domain(domain))
+
+
 def validate_ip(ip: str) -> None:
     """
     验证 IP 地址格式（支持 IPv4 和 IPv6）
@@ -44,6 +61,25 @@ def validate_ip(ip: str) -> None:
         raise ValueError(f"IP 地址格式无效: {ip}")
 
 
+def is_valid_ip(ip: str) -> bool:
+    """
+    判断是否为有效 IP 地址（不抛异常）
+    
+    Args:
+        ip: IP 地址字符串
+        
+    Returns:
+        bool: 是否为有效 IP 地址
+    """
+    if not ip:
+        return False
+    try:
+        ipaddress.ip_address(ip)
+        return True
+    except ValueError:
+        return False
+
+
 def validate_cidr(cidr: str) -> None:
     """
     验证 CIDR 格式（支持 IPv4 和 IPv6）
@@ -140,3 +176,136 @@ def validate_port(port: any) -> tuple[bool, int | None]:
     except (ValueError, TypeError):
         logger.warning("端口号格式错误，无法转换为整数: %s", port)
         return False, None
+
+
+# ==================== URL 验证函数 ====================
+
+def validate_url(url: str) -> None:
+    """
+    验证 URL 格式，必须包含 scheme（http:// 或 https://）
+    
+    Args:
+        url: URL 字符串
+        
+    Raises:
+        ValueError: URL 格式无效或缺少 scheme
+    """
+    if not url:
+        raise ValueError("URL 不能为空")
+    
+    # 检查是否包含 scheme
+    if not url.startswith('http://') and not url.startswith('https://'):
+        raise ValueError("URL 必须包含协议（http:// 或 https://）")
+    
+    try:
+        parsed = urlparse(url)
+        if not parsed.hostname:
+            raise ValueError("URL 必须包含主机名")
+    except Exception:
+        raise ValueError(f"URL 格式无效: {url}")
+
+
+def is_valid_url(url: str, max_length: int = 2000) -> bool:
+    """
+    判断是否为有效 URL（不抛异常）
+    
+    Args:
+        url: URL 字符串
+        max_length: URL 最大长度，默认 2000
+        
+    Returns:
+        bool: 是否为有效 URL
+    """
+    if not url or len(url) > max_length:
+        return False
+    try:
+        validate_url(url)
+        return True
+    except ValueError:
+        return False
+
+
+def is_url_match_target(url: str, target_name: str, target_type: str) -> bool:
+    """
+    判断 URL 是否匹配目标
+    
+    Args:
+        url: URL 字符串
+        target_name: 目标名称（域名、IP 或 CIDR）
+        target_type: 目标类型 ('domain', 'ip', 'cidr')
+        
+    Returns:
+        bool: 是否匹配
+    """
+    try:
+        parsed = urlparse(url)
+        hostname = parsed.hostname
+        if not hostname:
+            return False
+        
+        hostname = hostname.lower()
+        target_name = target_name.lower()
+        
+        if target_type == 'domain':
+            # 域名类型：hostname 等于 target_name 或以 .target_name 结尾
+            return hostname == target_name or hostname.endswith('.' + target_name)
+        
+        elif target_type == 'ip':
+            # IP 类型：hostname 必须完全等于 target_name
+            return hostname == target_name
+        
+        elif target_type == 'cidr':
+            # CIDR 类型：hostname 必须是 IP 且在 CIDR 范围内
+            try:
+                ip = ipaddress.ip_address(hostname)
+                network = ipaddress.ip_network(target_name, strict=False)
+                return ip in network
+            except ValueError:
+                # hostname 不是有效 IP
+                return False
+        
+        return False
+    except Exception:
+        return False
+
+
+def detect_input_type(input_str: str) -> str:
+    """
+    检测输入类型（用于快速扫描输入解析）
+    
+    Args:
+        input_str: 输入字符串（应该已经 strip）
+        
+    Returns:
+        str: 输入类型 ('url', 'domain', 'ip', 'cidr')
+    """
+    if not input_str:
+        raise ValueError("输入不能为空")
+    
+    # 1. 包含 :// 一定是 URL
+    if '://' in input_str:
+        return 'url'
+    
+    # 2. 包含 / 需要判断是 CIDR 还是 URL（缺少 scheme）
+    if '/' in input_str:
+        # CIDR 格式: IP/prefix，如 10.0.0.0/8
+        parts = input_str.split('/')
+        if len(parts) == 2:
+            ip_part, prefix_part = parts
+            # 如果斜杠后是纯数字且在 0-32 范围内，检查是否是 CIDR
+            if prefix_part.isdigit() and 0 <= int(prefix_part) <= 32:
+                ip_parts = ip_part.split('.')
+                if len(ip_parts) == 4 and all(p.isdigit() for p in ip_parts):
+                    return 'cidr'
+        # 不是 CIDR，视为 URL（缺少 scheme，后续验证会报错）
+        return 'url'
+    
+    # 3. 检查是否是 IP 地址
+    try:
+        ipaddress.ip_address(input_str)
+        return 'ip'
+    except ValueError:
+        pass
+    
+    # 4. 默认为域名
+    return 'domain'

backend/apps/common/views/__init__.py

@@ -7,6 +7,6 @@
 """
 
 from .auth_views import LoginView, LogoutView, MeView, ChangePasswordView
-from .system_log_views import SystemLogsView
+from .system_log_views import SystemLogsView, SystemLogFilesView
 
-__all__ = ['LoginView', 'LogoutView', 'MeView', 'ChangePasswordView', 'SystemLogsView']
+__all__ = ['LoginView', 'LogoutView', 'MeView', 'ChangePasswordView', 'SystemLogsView', 'SystemLogFilesView']

backend/apps/common/views/auth_views.py

@@ -9,7 +9,10 @@ from django.utils.decorators import method_decorator
 from rest_framework import status
 from rest_framework.views import APIView
 from rest_framework.response import Response
-from rest_framework.permissions import AllowAny, IsAuthenticated
+from rest_framework.permissions import AllowAny
+
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
 
 logger = logging.getLogger(__name__)
 
@@ -28,9 +31,10 @@ class LoginView(APIView):
         password = request.data.get('password')
         
         if not username or not password:
-            return Response(
-                {'error': '请提供用户名和密码'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Username and password are required',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         user = authenticate(request, username=username, password=password)
@@ -38,20 +42,22 @@ class LoginView(APIView):
         if user is not None:
             login(request, user)
             logger.info(f"用户 {username} 登录成功")
-            return Response({
-                'message': '登录成功',
-                'user': {
-                    'id': user.id,
-                    'username': user.username,
-                    'isStaff': user.is_staff,
-                    'isSuperuser': user.is_superuser,
+            return success_response(
+                data={
+                    'user': {
+                        'id': user.id,
+                        'username': user.username,
+                        'isStaff': user.is_staff,
+                        'isSuperuser': user.is_superuser,
+                    }
                 }
-            })
+            )
         else:
             logger.warning(f"用户 {username} 登录失败：用户名或密码错误")
-            return Response(
-                {'error': '用户名或密码错误'},
-                status=status.HTTP_401_UNAUTHORIZED
+            return error_response(
+                code=ErrorCodes.UNAUTHORIZED,
+                message='Invalid username or password',
+                status_code=status.HTTP_401_UNAUTHORIZED
             )
 
 
@@ -79,7 +85,7 @@ class LogoutView(APIView):
                 logout(request)
         else:
             logout(request)
-        return Response({'message': '已登出'})
+        return success_response()
 
 
 @method_decorator(csrf_exempt, name='dispatch')
@@ -100,22 +106,26 @@ class MeView(APIView):
         if user_id:
             try:
                 user = User.objects.get(pk=user_id)
-                return Response({
-                    'authenticated': True,
-                    'user': {
-                        'id': user.id,
-                        'username': user.username,
-                        'isStaff': user.is_staff,
-                        'isSuperuser': user.is_superuser,
+                return success_response(
+                    data={
+                        'authenticated': True,
+                        'user': {
+                            'id': user.id,
+                            'username': user.username,
+                            'isStaff': user.is_staff,
+                            'isSuperuser': user.is_superuser,
+                        }
                     }
-                })
+                )
             except User.DoesNotExist:
                 pass
         
-        return Response({
-            'authenticated': False,
-            'user': None
-        })
+        return success_response(
+            data={
+                'authenticated': False,
+                'user': None
+            }
+        )
 
 
 @method_decorator(csrf_exempt, name='dispatch')
@@ -124,43 +134,27 @@ class ChangePasswordView(APIView):
     修改密码
     POST /api/auth/change-password/
     """
-    authentication_classes = []  # 禁用认证（绕过 CSRF）
-    permission_classes = [AllowAny]  # 手动检查登录状态
     
     def post(self, request):
-        # 手动检查登录状态（从 session 获取用户）
-        from django.contrib.auth import get_user_model
-        User = get_user_model()
-        
-        user_id = request.session.get('_auth_user_id')
-        if not user_id:
-            return Response(
-                {'error': '请先登录'},
-                status=status.HTTP_401_UNAUTHORIZED
-            )
-        
-        try:
-            user = User.objects.get(pk=user_id)
-        except User.DoesNotExist:
-            return Response(
-                {'error': '用户不存在'},
-                status=status.HTTP_401_UNAUTHORIZED
-            )
+        # 使用全局权限类验证，request.user 已经是认证用户
+        user = request.user
         
         # CamelCaseParser 将 oldPassword -> old_password
         old_password = request.data.get('old_password')
         new_password = request.data.get('new_password')
         
         if not old_password or not new_password:
-            return Response(
-                {'error': '请提供旧密码和新密码'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Old password and new password are required',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         if not user.check_password(old_password):
-            return Response(
-                {'error': '旧密码错误'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Old password is incorrect',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         user.set_password(new_password)
@@ -170,4 +164,4 @@ class ChangePasswordView(APIView):
         update_session_auth_hash(request, user)
         
         logger.info(f"用户 {user.username} 已修改密码")
-        return Response({'message': '密码修改成功'})
+        return success_response()

backend/apps/common/views/system_log_views.py

@@ -9,16 +9,57 @@ import logging
 from django.utils.decorators import method_decorator
 from django.views.decorators.csrf import csrf_exempt
 from rest_framework import status
-from rest_framework.permissions import AllowAny
 from rest_framework.response import Response
 from rest_framework.views import APIView
 
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
 from apps.common.services.system_log_service import SystemLogService
 
 
 logger = logging.getLogger(__name__)
 
 
+@method_decorator(csrf_exempt, name="dispatch")
+class SystemLogFilesView(APIView):
+    """
+    日志文件列表 API 视图
+    
+    GET /api/system/logs/files/
+        获取所有可用的日志文件列表
+        
+    Response:
+        {
+            "files": [
+                {
+                    "filename": "xingrin.log",
+                    "category": "system",
+                    "size": 1048576,
+                    "modifiedAt": "2025-01-15T10:30:00+00:00"
+                },
+                ...
+            ]
+        }
+    """
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self.service = SystemLogService()
+
+    def get(self, request):
+        """获取日志文件列表"""
+        try:
+            files = self.service.get_log_files()
+            return success_response(data={"files": files})
+        except Exception:
+            logger.exception("获取日志文件列表失败")
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to get log files',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
+
+
 @method_decorator(csrf_exempt, name="dispatch")
 class SystemLogsView(APIView):
     """
@@ -28,21 +69,14 @@ class SystemLogsView(APIView):
         获取系统日志内容
         
     Query Parameters:
+        file (str, optional): 日志文件名，默认 xingrin.log
         lines (int, optional): 返回的日志行数，默认 200，最大 10000
         
     Response:
         {
             "content": "日志内容字符串..."
         }
-        
-    Note:
-        - 当前为开发阶段，暂时允许匿名访问
-        - 生产环境应添加管理员权限验证
     """
-    
-    # TODO: 生产环境应改为 IsAdminUser 权限
-    authentication_classes = []
-    permission_classes = [AllowAny]
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
@@ -52,18 +86,33 @@ class SystemLogsView(APIView):
         """
         获取系统日志
         
-        支持通过 lines 参数控制返回行数，用于前端分页或实时刷新场景。
+        支持通过 file 和 lines 参数控制返回内容。
         """
         try:
-            # 解析 lines 参数
+            # 解析参数
+            filename = request.query_params.get("file")
             lines_raw = request.query_params.get("lines")
             lines = int(lines_raw) if lines_raw is not None else None
 
             # 调用服务获取日志内容
-            content = self.service.get_logs_content(lines=lines)
-            return Response({"content": content})
-        except ValueError:
-            return Response({"error": "lines 参数必须是整数"}, status=status.HTTP_400_BAD_REQUEST)
+            content = self.service.get_logs_content(filename=filename, lines=lines)
+            return success_response(data={"content": content})
+        except ValueError as e:
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=str(e) if 'file' in str(e).lower() else 'lines must be an integer',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
+        except FileNotFoundError as e:
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                message=str(e),
+                status_code=status.HTTP_404_NOT_FOUND
+            )
         except Exception:
             logger.exception("获取系统日志失败")
-            return Response({"error": "获取系统日志失败"}, status=status.HTTP_500_INTERNAL_SERVER_ERROR)
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to get system logs',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )

backend/apps/common/websocket_auth.py

@@ -0,0 +1,44 @@
+"""
+WebSocket 认证基类
+
+提供需要认证的 WebSocket Consumer 基类
+"""
+
+import logging
+from channels.generic.websocket import AsyncWebsocketConsumer
+
+logger = logging.getLogger(__name__)
+
+
+class AuthenticatedWebsocketConsumer(AsyncWebsocketConsumer):
+    """
+    需要认证的 WebSocket Consumer 基类
+    
+    子类应该重写 on_connect() 方法实现具体的连接逻辑
+    """
+    
+    async def connect(self):
+        """
+        连接时验证用户认证状态
+        
+        未认证时使用 close(code=4001) 拒绝连接
+        """
+        user = self.scope.get('user')
+        
+        if not user or not user.is_authenticated:
+            logger.warning(
+                f"WebSocket 连接被拒绝：用户未认证 - Path: {self.scope.get('path')}"
+            )
+            await self.close(code=4001)
+            return
+        
+        # 调用子类的连接逻辑
+        await self.on_connect()
+    
+    async def on_connect(self):
+        """
+        子类实现具体的连接逻辑
+        
+        默认实现：接受连接
+        """
+        await self.accept()

backend/apps/engine/consumers/worker_deploy_consumer.py

@@ -6,17 +6,17 @@ import json
 import logging
 import asyncio
 import os
-from channels.generic.websocket import AsyncWebsocketConsumer
 from asgiref.sync import sync_to_async
 
 from django.conf import settings
 
+from apps.common.websocket_auth import AuthenticatedWebsocketConsumer
 from apps.engine.services import WorkerService
 
 logger = logging.getLogger(__name__)
 
 
-class WorkerDeployConsumer(AsyncWebsocketConsumer):
+class WorkerDeployConsumer(AuthenticatedWebsocketConsumer):
     """
     Worker 交互式终端 WebSocket Consumer
     
@@ -31,8 +31,8 @@ class WorkerDeployConsumer(AsyncWebsocketConsumer):
         self.read_task = None
         self.worker_service = WorkerService()
     
-    async def connect(self):
-        """连接时加入对应 Worker 的组并自动建立 SSH 连接"""
+    async def on_connect(self):
+        """连接时加入对应 Worker 的组并自动建立 SSH 连接（已通过认证）"""
         self.worker_id = self.scope['url_route']['kwargs']['worker_id']
         self.group_name = f'worker_deploy_{self.worker_id}'
         
@@ -241,8 +241,10 @@ class WorkerDeployConsumer(AsyncWebsocketConsumer):
             }))
             return
 
-        django_host = f"{public_host}:{server_port}"   # Django / 心跳上报使用
-        heartbeat_api_url = f"http://{django_host}"  # 基础 URL，agent 会加 /api/...
+        # 远程 Worker 通过 nginx HTTPS 访问（nginx 反代到后端 8888）
+        # 使用 https://{PUBLIC_HOST}:{PUBLIC_PORT} 而不是直连 8888 端口
+        public_port = getattr(settings, 'PUBLIC_PORT', '8083')
+        heartbeat_api_url = f"https://{public_host}:{public_port}"
 
         session_name = f'xingrin_deploy_{self.worker_id}'
         remote_script_path = '/tmp/xingrin_deploy.sh'

backend/apps/engine/management/commands/init_default_engine.py

@@ -90,6 +90,7 @@ class Command(BaseCommand):
                     single_config,
                     sort_keys=False,
                     allow_unicode=True,
+                    default_flow_style=None,
                 )
             except yaml.YAMLError as e:
                 self.stdout.write(self.style.ERROR(f'生成子引擎 {scan_type} 配置失败: {e}'))

backend/apps/engine/management/commands/init_fingerprints.py

@@ -0,0 +1,205 @@
+"""初始化内置指纹库
+
+- EHole 指纹: ehole.json -> 导入到数据库
+- Goby 指纹: goby.json -> 导入到数据库
+- Wappalyzer 指纹: wappalyzer.json -> 导入到数据库
+- Fingers 指纹: fingers_http.json -> 导入到数据库
+- FingerPrintHub 指纹: fingerprinthub_web.json -> 导入到数据库
+- ARL 指纹: ARL.yaml -> 导入到数据库
+
+可重复执行：如果数据库已有数据则跳过，只在空库时导入。
+"""
+
+import json
+import logging
+from pathlib import Path
+
+import yaml
+from django.conf import settings
+from django.core.management.base import BaseCommand
+
+from apps.engine.models import (
+    EholeFingerprint,
+    GobyFingerprint,
+    WappalyzerFingerprint,
+    FingersFingerprint,
+    FingerPrintHubFingerprint,
+    ARLFingerprint,
+)
+from apps.engine.services.fingerprints import (
+    EholeFingerprintService,
+    GobyFingerprintService,
+    WappalyzerFingerprintService,
+    FingersFingerprintService,
+    FingerPrintHubFingerprintService,
+    ARLFingerprintService,
+)
+
+
+logger = logging.getLogger(__name__)
+
+
+# 内置指纹配置
+DEFAULT_FINGERPRINTS = [
+    {
+        "type": "ehole",
+        "filename": "ehole.json",
+        "model": EholeFingerprint,
+        "service": EholeFingerprintService,
+        "data_key": "fingerprint",  # JSON 中指纹数组的 key
+        "file_format": "json",
+    },
+    {
+        "type": "goby",
+        "filename": "goby.json",
+        "model": GobyFingerprint,
+        "service": GobyFingerprintService,
+        "data_key": None,  # Goby 是数组格式，直接使用整个 JSON
+        "file_format": "json",
+    },
+    {
+        "type": "wappalyzer",
+        "filename": "wappalyzer.json",
+        "model": WappalyzerFingerprint,
+        "service": WappalyzerFingerprintService,
+        "data_key": "apps",  # Wappalyzer 使用 apps 对象
+        "file_format": "json",
+    },
+    {
+        "type": "fingers",
+        "filename": "fingers_http.json",
+        "model": FingersFingerprint,
+        "service": FingersFingerprintService,
+        "data_key": None,  # Fingers 是数组格式
+        "file_format": "json",
+    },
+    {
+        "type": "fingerprinthub",
+        "filename": "fingerprinthub_web.json",
+        "model": FingerPrintHubFingerprint,
+        "service": FingerPrintHubFingerprintService,
+        "data_key": None,  # FingerPrintHub 是数组格式
+        "file_format": "json",
+    },
+    {
+        "type": "arl",
+        "filename": "ARL.yaml",
+        "model": ARLFingerprint,
+        "service": ARLFingerprintService,
+        "data_key": None,  # ARL 是 YAML 数组格式
+        "file_format": "yaml",
+    },
+]
+
+
+class Command(BaseCommand):
+    help = "初始化内置指纹库"
+
+    def handle(self, *args, **options):
+        project_base = Path(settings.BASE_DIR).parent  # /app/backend -> /app
+        fingerprints_dir = project_base / "backend" / "fingerprints"
+
+        initialized = 0
+        skipped = 0
+        failed = 0
+
+        for item in DEFAULT_FINGERPRINTS:
+            fp_type = item["type"]
+            filename = item["filename"]
+            model = item["model"]
+            service_class = item["service"]
+            data_key = item["data_key"]
+            file_format = item.get("file_format", "json")
+
+            # 检查数据库是否已有数据
+            existing_count = model.objects.count()
+            if existing_count > 0:
+                self.stdout.write(self.style.SUCCESS(
+                    f"[{fp_type}] 数据库已有 {existing_count} 条记录，跳过初始化"
+                ))
+                skipped += 1
+                continue
+
+            # 查找源文件
+            src_path = fingerprints_dir / filename
+            if not src_path.exists():
+                self.stdout.write(self.style.WARNING(
+                    f"[{fp_type}] 未找到内置指纹文件: {src_path}，跳过"
+                ))
+                failed += 1
+                continue
+
+            # 读取并解析文件（支持 JSON 和 YAML）
+            try:
+                with open(src_path, "r", encoding="utf-8") as f:
+                    if file_format == "yaml":
+                        file_data = yaml.safe_load(f)
+                    else:
+                        file_data = json.load(f)
+            except (json.JSONDecodeError, yaml.YAMLError, OSError) as exc:
+                self.stdout.write(self.style.ERROR(
+                    f"[{fp_type}] 读取指纹文件失败: {exc}"
+                ))
+                failed += 1
+                continue
+
+            # 提取指纹数据（根据不同格式处理）
+            fingerprints = self._extract_fingerprints(file_data, data_key, fp_type)
+            if not fingerprints:
+                self.stdout.write(self.style.WARNING(
+                    f"[{fp_type}] 指纹文件中没有有效数据，跳过"
+                ))
+                failed += 1
+                continue
+
+            # 使用 Service 批量导入
+            try:
+                service = service_class()
+                result = service.batch_create_fingerprints(fingerprints)
+                created = result.get("created", 0)
+                failed_count = result.get("failed", 0)
+
+                self.stdout.write(self.style.SUCCESS(
+                    f"[{fp_type}] 导入成功: 创建 {created} 条，失败 {failed_count} 条"
+                ))
+                initialized += 1
+            except Exception as exc:
+                self.stdout.write(self.style.ERROR(
+                    f"[{fp_type}] 导入失败: {exc}"
+                ))
+                failed += 1
+                continue
+
+        self.stdout.write(self.style.SUCCESS(
+            f"指纹初始化完成: 成功 {initialized}, 已存在跳过 {skipped}, 失败 {failed}"
+        ))
+
+    def _extract_fingerprints(self, json_data, data_key, fp_type):
+        """
+        根据不同格式提取指纹数据，兼容数组和对象两种格式
+        
+        支持的格式：
+        - 数组格式: [...] 或 {"key": [...]}
+        - 对象格式: {...} 或 {"key": {...}} -> 转换为 [{"name": k, ...v}]
+        """
+        # 获取目标数据
+        if data_key is None:
+            # 直接使用整个 JSON
+            target = json_data
+        else:
+            # 从指定 key 获取，支持多个可能的 key（如 apps/technologies）
+            if data_key == "apps":
+                target = json_data.get("apps") or json_data.get("technologies") or {}
+            else:
+                target = json_data.get(data_key, [])
+        
+        # 根据数据类型处理
+        if isinstance(target, list):
+            # 已经是数组格式，直接返回
+            return target
+        elif isinstance(target, dict):
+            # 对象格式，转换为数组 [{"name": key, ...value}]
+            return [{"name": name, **data} if isinstance(data, dict) else {"name": name}
+                    for name, data in target.items()]
+        
+        return []

backend/apps/engine/management/commands/init_nuclei_templates.py

@@ -3,12 +3,17 @@
 项目安装后执行此命令，自动创建官方模板仓库记录。
 
 使用方式：
-    python manage.py init_nuclei_templates           # 只创建记录
+    python manage.py init_nuclei_templates           # 只创建记录（检测本地已有仓库）
     python manage.py init_nuclei_templates --sync    # 创建并同步（git clone）
 """
 
 import logging
+import subprocess
+from pathlib import Path
+
+from django.conf import settings
 from django.core.management.base import BaseCommand
+from django.utils import timezone
 
 from apps.engine.models import NucleiTemplateRepo
 from apps.engine.services import NucleiTemplateRepoService
@@ -26,6 +31,20 @@ DEFAULT_REPOS = [
 ]
 
 
+def get_local_commit_hash(local_path: Path) -> str:
+    """获取本地 Git 仓库的 commit hash"""
+    if not (local_path / ".git").is_dir():
+        return ""
+    result = subprocess.run(
+        ["git", "-C", str(local_path), "rev-parse", "HEAD"],
+        check=False,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        text=True,
+    )
+    return result.stdout.strip() if result.returncode == 0 else ""
+
+
 class Command(BaseCommand):
     help = "初始化 Nuclei 模板仓库（创建官方模板仓库记录）"
 
@@ -46,6 +65,8 @@ class Command(BaseCommand):
         force = options.get("force", False)
 
         service = NucleiTemplateRepoService()
+        base_dir = Path(getattr(settings, "NUCLEI_TEMPLATES_REPOS_BASE_DIR", "/opt/xingrin/nuclei-repos"))
+        
         created = 0
         skipped = 0
         synced = 0
@@ -87,20 +108,30 @@ class Command(BaseCommand):
 
             # 创建新仓库记录
             try:
+                # 检查本地是否已有仓库（由 install.sh 预下载）
+                local_path = base_dir / name
+                local_commit = get_local_commit_hash(local_path)
+                
                 repo = NucleiTemplateRepo.objects.create(
                     name=name,
                     repo_url=repo_url,
+                    local_path=str(local_path) if local_commit else "",
+                    commit_hash=local_commit,
+                    last_synced_at=timezone.now() if local_commit else None,
                 )
-                self.stdout.write(self.style.SUCCESS(
-                    f"[{name}] 创建成功: id={repo.id}"
-                ))
+                
+                if local_commit:
+                    self.stdout.write(self.style.SUCCESS(
+                        f"[{name}] 创建成功（检测到本地仓库）: commit={local_commit[:8]}"
+                    ))
+                else:
+                    self.stdout.write(self.style.SUCCESS(
+                        f"[{name}] 创建成功: id={repo.id}"
+                    ))
                 created += 1
 
-                # 初始化本地路径
-                service.ensure_local_path(repo)
-
-                # 如果需要同步
-                if do_sync:
+                # 如果本地没有仓库且需要同步
+                if not local_commit and do_sync:
                     try:
                         self.stdout.write(self.style.WARNING(
                             f"[{name}] 正在同步（首次可能需要几分钟）..."

backend/apps/engine/management/commands/init_wordlists.py

@@ -1,7 +1,8 @@
 """初始化所有内置字典 Wordlist 记录
 
-- 目录扫描默认字典: dir_default.txt -> /app/backend/wordlist/dir_default.txt
-- 子域名爆破默认字典: subdomains-top1million-110000.txt -> /app/backend/wordlist/subdomains-top1million-110000.txt
+内置字典从镜像内 /app/backend/wordlist/ 复制到运行时目录 /opt/xingrin/wordlists/：
+- 目录扫描默认字典: dir_default.txt
+- 子域名爆破默认字典: subdomains-top1million-110000.txt
 
 可重复执行：如果已存在同名记录且文件有效则跳过，只在缺失或文件丢失时创建/修复。
 """
@@ -13,7 +14,7 @@ from pathlib import Path
 from django.conf import settings
 from django.core.management.base import BaseCommand
 
-from apps.common.hash_utils import safe_calc_file_sha256
+from apps.common.utils import safe_calc_file_sha256
 from apps.engine.models import Wordlist
 
 

backend/apps/engine/models/__init__.py

@@ -0,0 +1,29 @@
+"""Engine Models
+
+导出所有 Engine 模块的 Models
+"""
+
+from .engine import WorkerNode, ScanEngine, Wordlist, NucleiTemplateRepo
+from .fingerprints import (
+    EholeFingerprint,
+    GobyFingerprint,
+    WappalyzerFingerprint,
+    FingersFingerprint,
+    FingerPrintHubFingerprint,
+    ARLFingerprint,
+)
+
+__all__ = [
+    # 核心 Models
+    "WorkerNode",
+    "ScanEngine",
+    "Wordlist",
+    "NucleiTemplateRepo",
+    # 指纹 Models
+    "EholeFingerprint",
+    "GobyFingerprint",
+    "WappalyzerFingerprint",
+    "FingersFingerprint",
+    "FingerPrintHubFingerprint",
+    "ARLFingerprint",
+]

backend/apps/engine/models/engine.py

@@ -1,3 +1,8 @@
+"""Engine 模块核心 Models
+
+包含 WorkerNode, ScanEngine, Wordlist, NucleiTemplateRepo
+"""
+
 from django.db import models
 
 
@@ -10,6 +15,8 @@ class WorkerNode(models.Model):
         ('deploying', '部署中'),
         ('online', '在线'),
         ('offline', '离线'),
+        ('updating', '更新中'),
+        ('outdated', '版本过低'),
     ]
     
     name = models.CharField(max_length=100, help_text='节点名称')
@@ -76,6 +83,7 @@ class ScanEngine(models.Model):
         indexes = [
             models.Index(fields=['-created_at']),
         ]
+
     def __str__(self):
         return str(self.name or f'ScanEngine {self.id}')
 

backend/apps/engine/models/fingerprints.py

@@ -0,0 +1,195 @@
+"""指纹相关 Models
+
+包含 EHole、Goby、Wappalyzer 等指纹格式的数据模型
+"""
+
+from django.db import models
+
+
+class GobyFingerprint(models.Model):
+    """Goby 格式指纹规则
+    
+    Goby 使用逻辑表达式和规则数组进行匹配：
+    - logic: 逻辑表达式，如 "a||b", "(a&&b)||c"
+    - rule: 规则数组，每条规则包含 label, feature, is_equal
+    """
+    
+    name = models.CharField(max_length=300, unique=True, help_text='产品名称')
+    logic = models.CharField(max_length=500, help_text='逻辑表达式')
+    rule = models.JSONField(default=list, help_text='规则数组')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'goby_fingerprint'
+        verbose_name = 'Goby 指纹'
+        verbose_name_plural = 'Goby 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['name']),
+            models.Index(fields=['logic']),
+            models.Index(fields=['-created_at']),
+        ]
+    
+    def __str__(self) -> str:
+        return f"{self.name} ({self.logic})"
+
+
+class EholeFingerprint(models.Model):
+    """EHole 格式指纹规则（字段与 ehole.json 一致）"""
+    
+    cms = models.CharField(max_length=200, help_text='产品/CMS名称')
+    method = models.CharField(max_length=200, default='keyword', help_text='匹配方式')
+    location = models.CharField(max_length=200, default='body', help_text='匹配位置')
+    keyword = models.JSONField(default=list, help_text='关键词列表')
+    is_important = models.BooleanField(default=False, help_text='是否重点资产')
+    type = models.CharField(max_length=100, blank=True, default='-', help_text='分类')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'ehole_fingerprint'
+        verbose_name = 'EHole 指纹'
+        verbose_name_plural = 'EHole 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            # 搜索过滤字段索引
+            models.Index(fields=['cms']),
+            models.Index(fields=['method']),
+            models.Index(fields=['location']),
+            models.Index(fields=['type']),
+            models.Index(fields=['is_important']),
+            # 排序字段索引
+            models.Index(fields=['-created_at']),
+        ]
+        constraints = [
+            # 唯一约束：cms + method + location 组合不能重复
+            models.UniqueConstraint(
+                fields=['cms', 'method', 'location'],
+                name='unique_ehole_fingerprint'
+            ),
+        ]
+    
+    def __str__(self) -> str:
+        return f"{self.cms} ({self.method}@{self.location})"
+
+
+class WappalyzerFingerprint(models.Model):
+    """Wappalyzer 格式指纹规则
+    
+    Wappalyzer 支持多种检测方式：cookies, headers, scriptSrc, js, meta, html 等
+    """
+    
+    name = models.CharField(max_length=300, unique=True, help_text='应用名称')
+    cats = models.JSONField(default=list, help_text='分类 ID 数组')
+    cookies = models.JSONField(default=dict, blank=True, help_text='Cookie 检测规则')
+    headers = models.JSONField(default=dict, blank=True, help_text='HTTP Header 检测规则')
+    script_src = models.JSONField(default=list, blank=True, help_text='脚本 URL 正则数组')
+    js = models.JSONField(default=list, blank=True, help_text='JavaScript 变量检测规则')
+    implies = models.JSONField(default=list, blank=True, help_text='依赖关系数组')
+    meta = models.JSONField(default=dict, blank=True, help_text='HTML meta 标签检测规则')
+    html = models.JSONField(default=list, blank=True, help_text='HTML 内容正则数组')
+    description = models.TextField(blank=True, default='', help_text='应用描述')
+    website = models.URLField(max_length=500, blank=True, default='', help_text='官网链接')
+    cpe = models.CharField(max_length=300, blank=True, default='', help_text='CPE 标识符')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'wappalyzer_fingerprint'
+        verbose_name = 'Wappalyzer 指纹'
+        verbose_name_plural = 'Wappalyzer 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['name']),
+            models.Index(fields=['website']),
+            models.Index(fields=['cpe']),
+            models.Index(fields=['-created_at']),
+        ]
+    
+    def __str__(self) -> str:
+        return f"{self.name}"
+
+
+class FingersFingerprint(models.Model):
+    """Fingers 格式指纹规则 (fingers_http.json)
+    
+    使用正则表达式和标签进行匹配，支持 favicon hash、header、body 等多种检测方式
+    """
+    
+    name = models.CharField(max_length=300, unique=True, help_text='指纹名称')
+    link = models.URLField(max_length=500, blank=True, default='', help_text='相关链接')
+    rule = models.JSONField(default=list, help_text='匹配规则数组')
+    tag = models.JSONField(default=list, help_text='标签数组')
+    focus = models.BooleanField(default=False, help_text='是否重点关注')
+    default_port = models.JSONField(default=list, blank=True, help_text='默认端口数组')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'fingers_fingerprint'
+        verbose_name = 'Fingers 指纹'
+        verbose_name_plural = 'Fingers 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['name']),
+            models.Index(fields=['link']),
+            models.Index(fields=['focus']),
+            models.Index(fields=['-created_at']),
+        ]
+    
+    def __str__(self) -> str:
+        return f"{self.name}"
+
+
+class FingerPrintHubFingerprint(models.Model):
+    """FingerPrintHub 格式指纹规则 (fingerprinthub_web.json)
+    
+    基于 nuclei 模板格式，使用 HTTP 请求和响应特征进行匹配
+    """
+    
+    fp_id = models.CharField(max_length=200, unique=True, help_text='指纹ID')
+    name = models.CharField(max_length=300, help_text='指纹名称')
+    author = models.CharField(max_length=200, blank=True, default='', help_text='作者')
+    tags = models.CharField(max_length=500, blank=True, default='', help_text='标签')
+    severity = models.CharField(max_length=50, blank=True, default='info', help_text='严重程度')
+    metadata = models.JSONField(default=dict, blank=True, help_text='元数据')
+    http = models.JSONField(default=list, help_text='HTTP 匹配规则')
+    source_file = models.CharField(max_length=500, blank=True, default='', help_text='来源文件')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'fingerprinthub_fingerprint'
+        verbose_name = 'FingerPrintHub 指纹'
+        verbose_name_plural = 'FingerPrintHub 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['fp_id']),
+            models.Index(fields=['name']),
+            models.Index(fields=['author']),
+            models.Index(fields=['severity']),
+            models.Index(fields=['-created_at']),
+        ]
+    
+    def __str__(self) -> str:
+        return f"{self.name} ({self.fp_id})"
+
+
+class ARLFingerprint(models.Model):
+    """ARL 格式指纹规则 (ARL.yaml)
+    
+    使用简单的 name + rule 表达式格式
+    """
+    
+    name = models.CharField(max_length=300, unique=True, help_text='指纹名称')
+    rule = models.TextField(help_text='匹配规则表达式')
+    created_at = models.DateTimeField(auto_now_add=True)
+    
+    class Meta:
+        db_table = 'arl_fingerprint'
+        verbose_name = 'ARL 指纹'
+        verbose_name_plural = 'ARL 指纹'
+        ordering = ['-created_at']
+        indexes = [
+            models.Index(fields=['name']),
+            models.Index(fields=['-created_at']),
+        ]
+    
+    def __str__(self) -> str:
+        return f"{self.name}"

backend/apps/engine/serializers/fingerprints/__init__.py

@@ -0,0 +1,20 @@
+"""指纹管理 Serializers
+
+导出所有指纹相关的 Serializer 类
+"""
+
+from .ehole import EholeFingerprintSerializer
+from .goby import GobyFingerprintSerializer
+from .wappalyzer import WappalyzerFingerprintSerializer
+from .fingers import FingersFingerprintSerializer
+from .fingerprinthub import FingerPrintHubFingerprintSerializer
+from .arl import ARLFingerprintSerializer
+
+__all__ = [
+    "EholeFingerprintSerializer",
+    "GobyFingerprintSerializer",
+    "WappalyzerFingerprintSerializer",
+    "FingersFingerprintSerializer",
+    "FingerPrintHubFingerprintSerializer",
+    "ARLFingerprintSerializer",
+]

backend/apps/engine/serializers/fingerprints/arl.py

@@ -0,0 +1,31 @@
+"""ARL 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import ARLFingerprint
+
+
+class ARLFingerprintSerializer(serializers.ModelSerializer):
+    """ARL 指纹序列化器
+    
+    字段映射:
+    - name: 指纹名称 (必填, 唯一)
+    - rule: 匹配规则表达式 (必填)
+    """
+    
+    class Meta:
+        model = ARLFingerprint
+        fields = ['id', 'name', 'rule', 'created_at']
+        read_only_fields = ['id', 'created_at']
+    
+    def validate_name(self, value):
+        """校验 name 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("name 字段不能为空")
+        return value.strip()
+    
+    def validate_rule(self, value):
+        """校验 rule 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("rule 字段不能为空")
+        return value.strip()

backend/apps/engine/serializers/fingerprints/ehole.py

@@ -0,0 +1,27 @@
+"""EHole 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import EholeFingerprint
+
+
+class EholeFingerprintSerializer(serializers.ModelSerializer):
+    """EHole 指纹序列化器"""
+    
+    class Meta:
+        model = EholeFingerprint
+        fields = ['id', 'cms', 'method', 'location', 'keyword', 
+                  'is_important', 'type', 'created_at']
+        read_only_fields = ['id', 'created_at']
+    
+    def validate_cms(self, value):
+        """校验 cms 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("cms 字段不能为空")
+        return value.strip()
+    
+    def validate_keyword(self, value):
+        """校验 keyword 字段"""
+        if not isinstance(value, list):
+            raise serializers.ValidationError("keyword 必须是数组")
+        return value

backend/apps/engine/serializers/fingerprints/fingerprinthub.py

@@ -0,0 +1,50 @@
+"""FingerPrintHub 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import FingerPrintHubFingerprint
+
+
+class FingerPrintHubFingerprintSerializer(serializers.ModelSerializer):
+    """FingerPrintHub 指纹序列化器
+    
+    字段映射:
+    - fp_id: 指纹ID (必填, 唯一)
+    - name: 指纹名称 (必填)
+    - author: 作者 (可选)
+    - tags: 标签字符串 (可选)
+    - severity: 严重程度 (可选, 默认 'info')
+    - metadata: 元数据 JSON (可选)
+    - http: HTTP 匹配规则数组 (必填)
+    - source_file: 来源文件 (可选)
+    """
+    
+    class Meta:
+        model = FingerPrintHubFingerprint
+        fields = ['id', 'fp_id', 'name', 'author', 'tags', 'severity',
+                  'metadata', 'http', 'source_file', 'created_at']
+        read_only_fields = ['id', 'created_at']
+    
+    def validate_fp_id(self, value):
+        """校验 fp_id 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("fp_id 字段不能为空")
+        return value.strip()
+    
+    def validate_name(self, value):
+        """校验 name 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("name 字段不能为空")
+        return value.strip()
+    
+    def validate_http(self, value):
+        """校验 http 字段"""
+        if not isinstance(value, list):
+            raise serializers.ValidationError("http 必须是数组")
+        return value
+    
+    def validate_metadata(self, value):
+        """校验 metadata 字段"""
+        if not isinstance(value, dict):
+            raise serializers.ValidationError("metadata 必须是对象")
+        return value

backend/apps/engine/serializers/fingerprints/fingers.py

@@ -0,0 +1,48 @@
+"""Fingers 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import FingersFingerprint
+
+
+class FingersFingerprintSerializer(serializers.ModelSerializer):
+    """Fingers 指纹序列化器
+    
+    字段映射:
+    - name: 指纹名称 (必填, 唯一)
+    - link: 相关链接 (可选)
+    - rule: 匹配规则数组 (必填)
+    - tag: 标签数组 (可选)
+    - focus: 是否重点关注 (可选, 默认 False)
+    - default_port: 默认端口数组 (可选)
+    """
+    
+    class Meta:
+        model = FingersFingerprint
+        fields = ['id', 'name', 'link', 'rule', 'tag', 'focus', 
+                  'default_port', 'created_at']
+        read_only_fields = ['id', 'created_at']
+    
+    def validate_name(self, value):
+        """校验 name 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("name 字段不能为空")
+        return value.strip()
+    
+    def validate_rule(self, value):
+        """校验 rule 字段"""
+        if not isinstance(value, list):
+            raise serializers.ValidationError("rule 必须是数组")
+        return value
+    
+    def validate_tag(self, value):
+        """校验 tag 字段"""
+        if not isinstance(value, list):
+            raise serializers.ValidationError("tag 必须是数组")
+        return value
+    
+    def validate_default_port(self, value):
+        """校验 default_port 字段"""
+        if not isinstance(value, list):
+            raise serializers.ValidationError("default_port 必须是数组")
+        return value

backend/apps/engine/serializers/fingerprints/goby.py

@@ -0,0 +1,26 @@
+"""Goby 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import GobyFingerprint
+
+
+class GobyFingerprintSerializer(serializers.ModelSerializer):
+    """Goby 指纹序列化器"""
+    
+    class Meta:
+        model = GobyFingerprint
+        fields = ['id', 'name', 'logic', 'rule', 'created_at']
+        read_only_fields = ['id', 'created_at']
+    
+    def validate_name(self, value):
+        """校验 name 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("name 字段不能为空")
+        return value.strip()
+    
+    def validate_rule(self, value):
+        """校验 rule 字段"""
+        if not isinstance(value, list):
+            raise serializers.ValidationError("rule 必须是数组")
+        return value

backend/apps/engine/serializers/fingerprints/wappalyzer.py

@@ -0,0 +1,24 @@
+"""Wappalyzer 指纹 Serializer"""
+
+from rest_framework import serializers
+
+from apps.engine.models import WappalyzerFingerprint
+
+
+class WappalyzerFingerprintSerializer(serializers.ModelSerializer):
+    """Wappalyzer 指纹序列化器"""
+    
+    class Meta:
+        model = WappalyzerFingerprint
+        fields = [
+            'id', 'name', 'cats', 'cookies', 'headers', 'script_src',
+            'js', 'implies', 'meta', 'html', 'description', 'website',
+            'cpe', 'created_at'
+        ]
+        read_only_fields = ['id', 'created_at']
+    
+    def validate_name(self, value):
+        """校验 name 字段"""
+        if not value or not value.strip():
+            raise serializers.ValidationError("name 字段不能为空")
+        return value.strip()

backend/apps/engine/services/deploy_service.py

@@ -66,6 +66,7 @@ def get_start_agent_script(
     # 替换变量
     script = script.replace("{{HEARTBEAT_API_URL}}", heartbeat_api_url or '')
     script = script.replace("{{WORKER_ID}}", str(worker_id) if worker_id else '')
+    script = script.replace("{{WORKER_API_KEY}}", getattr(settings, 'WORKER_API_KEY', ''))
     
     # 注入镜像版本配置（确保远程节点使用相同版本）
     docker_user = getattr(settings, 'DOCKER_USER', 'yyhuni')

backend/apps/engine/services/fingerprints/__init__.py

@@ -0,0 +1,22 @@
+"""指纹管理 Services
+
+导出所有指纹相关的 Service 类
+"""
+
+from .base import BaseFingerprintService
+from .ehole import EholeFingerprintService
+from .goby import GobyFingerprintService
+from .wappalyzer import WappalyzerFingerprintService
+from .fingers_service import FingersFingerprintService
+from .fingerprinthub_service import FingerPrintHubFingerprintService
+from .arl_service import ARLFingerprintService
+
+__all__ = [
+    "BaseFingerprintService",
+    "EholeFingerprintService",
+    "GobyFingerprintService",
+    "WappalyzerFingerprintService",
+    "FingersFingerprintService",
+    "FingerPrintHubFingerprintService",
+    "ARLFingerprintService",
+]

backend/apps/engine/services/fingerprints/arl_service.py

@@ -0,0 +1,110 @@
+"""ARL 指纹管理 Service
+
+实现 ARL 格式指纹的校验、转换和导出逻辑
+支持 YAML 格式的导入导出
+"""
+
+import logging
+import yaml
+
+from apps.engine.models import ARLFingerprint
+from .base import BaseFingerprintService
+
+logger = logging.getLogger(__name__)
+
+
+class ARLFingerprintService(BaseFingerprintService):
+    """ARL 指纹管理服务（继承基类，实现 ARL 特定逻辑）"""
+    
+    model = ARLFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 ARL 指纹
+        
+        校验规则：
+        - name 字段必须存在且非空
+        - rule 字段必须存在且非空
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        name = item.get('name', '')
+        rule = item.get('rule', '')
+        return bool(name and str(name).strip()) and bool(rule and str(rule).strip())
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 ARL YAML 格式为 Model 字段
+        
+        Args:
+            item: 原始 ARL YAML 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        return {
+            'name': str(item.get('name', '')).strip(),
+            'rule': str(item.get('rule', '')).strip(),
+        }
+    
+    def get_export_data(self) -> list:
+        """
+        获取导出数据（ARL 格式 - 数组，用于 YAML 导出）
+        
+        Returns:
+            list: ARL 格式的数据（数组格式）
+            [
+                {"name": "...", "rule": "..."},
+                ...
+            ]
+        """
+        fingerprints = self.model.objects.all()
+        return [
+            {
+                'name': fp.name,
+                'rule': fp.rule,
+            }
+            for fp in fingerprints
+        ]
+    
+    def export_to_yaml(self, output_path: str) -> int:
+        """
+        导出所有指纹到 YAML 文件
+        
+        Args:
+            output_path: 输出文件路径
+            
+        Returns:
+            int: 导出的指纹数量
+        """
+        data = self.get_export_data()
+        with open(output_path, 'w', encoding='utf-8') as f:
+            yaml.dump(data, f, allow_unicode=True, default_flow_style=False, sort_keys=False)
+        count = len(data)
+        logger.info("导出 ARL 指纹文件: %s, 数量: %d", output_path, count)
+        return count
+    
+    def parse_yaml_import(self, yaml_content: str) -> list:
+        """
+        解析 YAML 格式的导入内容
+        
+        Args:
+            yaml_content: YAML 格式的字符串内容
+            
+        Returns:
+            list: 解析后的指纹数据列表
+            
+        Raises:
+            ValueError: 当 YAML 格式无效时
+        """
+        try:
+            data = yaml.safe_load(yaml_content)
+            if not isinstance(data, list):
+                raise ValueError("ARL YAML 文件必须是数组格式")
+            return data
+        except yaml.YAMLError as e:
+            raise ValueError(f"无效的 YAML 格式: {e}")

backend/apps/engine/services/fingerprints/base.py

@@ -0,0 +1,144 @@
+"""指纹管理基类 Service
+
+提供通用的批量操作和缓存逻辑，供 EHole/Goby/Wappalyzer 等子类继承
+"""
+
+import json
+import logging
+from typing import Any
+
+logger = logging.getLogger(__name__)
+
+
+class BaseFingerprintService:
+    """指纹管理基类 Service，提供通用的批量操作和缓存逻辑"""
+    
+    model = None  # 子类必须指定
+    BATCH_SIZE = 1000  # 每批处理数量
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条指纹，子类必须实现
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        raise NotImplementedError("子类必须实现 validate_fingerprint 方法")
+    
+    def validate_fingerprints(self, raw_data: list) -> tuple[list, list]:
+        """
+        批量校验指纹数据
+        
+        Args:
+            raw_data: 原始指纹数据列表
+            
+        Returns:
+            tuple: (valid_items, invalid_items)
+        """
+        valid, invalid = [], []
+        for item in raw_data:
+            if self.validate_fingerprint(item):
+                valid.append(item)
+            else:
+                invalid.append(item)
+        return valid, invalid
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换为 Model 字段，子类必须实现
+        
+        Args:
+            item: 原始指纹数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        raise NotImplementedError("子类必须实现 to_model_data 方法")
+
+    def bulk_create(self, fingerprints: list) -> int:
+        """
+        批量创建指纹记录（已校验的数据）
+        
+        Args:
+            fingerprints: 已校验的指纹数据列表
+            
+        Returns:
+            int: 成功创建数量
+        """
+        if not fingerprints:
+            return 0
+        
+        objects = [self.model(**self.to_model_data(item)) for item in fingerprints]
+        created = self.model.objects.bulk_create(objects, ignore_conflicts=True)
+        return len(created)
+    
+    def batch_create_fingerprints(self, raw_data: list) -> dict:
+        """
+        完整流程：分批校验 + 批量创建
+        
+        Args:
+            raw_data: 原始指纹数据列表
+            
+        Returns:
+            dict: {'created': int, 'failed': int}
+        """
+        total_created = 0
+        total_failed = 0
+        
+        for i in range(0, len(raw_data), self.BATCH_SIZE):
+            batch = raw_data[i:i + self.BATCH_SIZE]
+            valid, invalid = self.validate_fingerprints(batch)
+            total_created += self.bulk_create(valid)
+            total_failed += len(invalid)
+        
+        logger.info(
+            "批量创建指纹完成: created=%d, failed=%d, total=%d",
+            total_created, total_failed, len(raw_data)
+        )
+        return {'created': total_created, 'failed': total_failed}
+    
+    def get_export_data(self) -> dict:
+        """
+        获取导出数据，子类必须实现
+        
+        Returns:
+            dict: 导出的 JSON 数据
+        """
+        raise NotImplementedError("子类必须实现 get_export_data 方法")
+    
+    def export_to_file(self, output_path: str) -> int:
+        """
+        导出所有指纹到 JSON 文件
+        
+        Args:
+            output_path: 输出文件路径
+            
+        Returns:
+            int: 导出的指纹数量
+        """
+        data = self.get_export_data()
+        with open(output_path, 'w', encoding='utf-8') as f:
+            json.dump(data, f, ensure_ascii=False)
+        count = len(data.get('fingerprint', []))
+        logger.info("导出指纹文件: %s, 数量: %d", output_path, count)
+        return count
+    
+    def get_fingerprint_version(self) -> str:
+        """
+        获取指纹库版本标识（用于缓存校验）
+        
+        Returns:
+            str: 版本标识，格式 "{count}_{latest_timestamp}"
+        
+        版本变化场景：
+        - 新增记录 → count 变化
+        - 删除记录 → count 变化
+        - 清空全部 → count 变为 0
+        """
+        count = self.model.objects.count()
+        latest = self.model.objects.order_by('-created_at').first()
+        latest_ts = int(latest.created_at.timestamp()) if latest else 0
+        return f"{count}_{latest_ts}"

backend/apps/engine/services/fingerprints/ehole.py

@@ -0,0 +1,84 @@
+"""EHole 指纹管理 Service
+
+实现 EHole 格式指纹的校验、转换和导出逻辑
+"""
+
+from apps.engine.models import EholeFingerprint
+from .base import BaseFingerprintService
+
+
+class EholeFingerprintService(BaseFingerprintService):
+    """EHole 指纹管理服务（继承基类，实现 EHole 特定逻辑）"""
+    
+    model = EholeFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 EHole 指纹
+        
+        校验规则：
+        - cms 字段必须存在且非空
+        - keyword 字段必须是数组
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        cms = item.get('cms', '')
+        keyword = item.get('keyword')
+        return bool(cms and str(cms).strip()) and isinstance(keyword, list)
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 EHole JSON 格式为 Model 字段
+        
+        字段映射：
+        - isImportant (JSON) → is_important (Model)
+        
+        Args:
+            item: 原始 EHole JSON 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        return {
+            'cms': str(item.get('cms', '')).strip(),
+            'method': item.get('method', 'keyword'),
+            'location': item.get('location', 'body'),
+            'keyword': item.get('keyword', []),
+            'is_important': item.get('isImportant', False),
+            'type': item.get('type', '-'),
+        }
+    
+    def get_export_data(self) -> dict:
+        """
+        获取导出数据（EHole JSON 格式）
+        
+        Returns:
+            dict: EHole 格式的 JSON 数据
+            {
+                "fingerprint": [
+                    {"cms": "...", "method": "...", "location": "...", 
+                     "keyword": [...], "isImportant": false, "type": "..."},
+                    ...
+                ],
+                "version": "1000_1703836800"
+            }
+        """
+        fingerprints = self.model.objects.all()
+        data = []
+        for fp in fingerprints:
+            data.append({
+                'cms': fp.cms,
+                'method': fp.method,
+                'location': fp.location,
+                'keyword': fp.keyword,
+                'isImportant': fp.is_important,  # 转回 JSON 格式
+                'type': fp.type,
+            })
+        return {
+            'fingerprint': data,
+            'version': self.get_fingerprint_version(),
+        }

backend/apps/engine/services/fingerprints/fingerprinthub_service.py

@@ -0,0 +1,110 @@
+"""FingerPrintHub 指纹管理 Service
+
+实现 FingerPrintHub 格式指纹的校验、转换和导出逻辑
+"""
+
+from apps.engine.models import FingerPrintHubFingerprint
+from .base import BaseFingerprintService
+
+
+class FingerPrintHubFingerprintService(BaseFingerprintService):
+    """FingerPrintHub 指纹管理服务（继承基类，实现 FingerPrintHub 特定逻辑）"""
+    
+    model = FingerPrintHubFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 FingerPrintHub 指纹
+        
+        校验规则：
+        - id 字段必须存在且非空
+        - info 字段必须存在且包含 name
+        - http 字段必须是数组
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        fp_id = item.get('id', '')
+        info = item.get('info', {})
+        http = item.get('http')
+        
+        if not fp_id or not str(fp_id).strip():
+            return False
+        if not isinstance(info, dict) or not info.get('name'):
+            return False
+        if not isinstance(http, list):
+            return False
+        
+        return True
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 FingerPrintHub JSON 格式为 Model 字段
+        
+        字段映射（嵌套结构转扁平）：
+        - id (JSON) → fp_id (Model)
+        - info.name (JSON) → name (Model)
+        - info.author (JSON) → author (Model)
+        - info.tags (JSON) → tags (Model)
+        - info.severity (JSON) → severity (Model)
+        - info.metadata (JSON) → metadata (Model)
+        - http (JSON) → http (Model)
+        - _source_file (JSON) → source_file (Model)
+        
+        Args:
+            item: 原始 FingerPrintHub JSON 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        info = item.get('info', {})
+        return {
+            'fp_id': str(item.get('id', '')).strip(),
+            'name': str(info.get('name', '')).strip(),
+            'author': info.get('author', ''),
+            'tags': info.get('tags', ''),
+            'severity': info.get('severity', 'info'),
+            'metadata': info.get('metadata', {}),
+            'http': item.get('http', []),
+            'source_file': item.get('_source_file', ''),
+        }
+    
+    def get_export_data(self) -> list:
+        """
+        获取导出数据（FingerPrintHub JSON 格式 - 数组）
+        
+        Returns:
+            list: FingerPrintHub 格式的 JSON 数据（数组格式）
+            [
+                {
+                    "id": "...",
+                    "info": {"name": "...", "author": "...", "tags": "...", 
+                             "severity": "...", "metadata": {...}},
+                    "http": [...],
+                    "_source_file": "..."
+                },
+                ...
+            ]
+        """
+        fingerprints = self.model.objects.all()
+        data = []
+        for fp in fingerprints:
+            item = {
+                'id': fp.fp_id,
+                'info': {
+                    'name': fp.name,
+                    'author': fp.author,
+                    'tags': fp.tags,
+                    'severity': fp.severity,
+                    'metadata': fp.metadata,
+                },
+                'http': fp.http,
+            }
+            # 只有当 source_file 非空时才添加该字段
+            if fp.source_file:
+                item['_source_file'] = fp.source_file
+            data.append(item)
+        return data

backend/apps/engine/services/fingerprints/fingers_service.py

@@ -0,0 +1,83 @@
+"""Fingers 指纹管理 Service
+
+实现 Fingers 格式指纹的校验、转换和导出逻辑
+"""
+
+from apps.engine.models import FingersFingerprint
+from .base import BaseFingerprintService
+
+
+class FingersFingerprintService(BaseFingerprintService):
+    """Fingers 指纹管理服务（继承基类，实现 Fingers 特定逻辑）"""
+    
+    model = FingersFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 Fingers 指纹
+        
+        校验规则：
+        - name 字段必须存在且非空
+        - rule 字段必须是数组
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        name = item.get('name', '')
+        rule = item.get('rule')
+        return bool(name and str(name).strip()) and isinstance(rule, list)
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 Fingers JSON 格式为 Model 字段
+        
+        字段映射：
+        - default_port (JSON) → default_port (Model)
+        
+        Args:
+            item: 原始 Fingers JSON 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        return {
+            'name': str(item.get('name', '')).strip(),
+            'link': item.get('link', ''),
+            'rule': item.get('rule', []),
+            'tag': item.get('tag', []),
+            'focus': item.get('focus', False),
+            'default_port': item.get('default_port', []),
+        }
+    
+    def get_export_data(self) -> list:
+        """
+        获取导出数据（Fingers JSON 格式 - 数组）
+        
+        Returns:
+            list: Fingers 格式的 JSON 数据（数组格式）
+            [
+                {"name": "...", "link": "...", "rule": [...], "tag": [...], 
+                 "focus": false, "default_port": [...]},
+                ...
+            ]
+        """
+        fingerprints = self.model.objects.all()
+        data = []
+        for fp in fingerprints:
+            item = {
+                'name': fp.name,
+                'link': fp.link,
+                'rule': fp.rule,
+                'tag': fp.tag,
+            }
+            # 只有当 focus 为 True 时才添加该字段（保持与原始格式一致）
+            if fp.focus:
+                item['focus'] = fp.focus
+            # 只有当 default_port 非空时才添加该字段
+            if fp.default_port:
+                item['default_port'] = fp.default_port
+            data.append(item)
+        return data

backend/apps/engine/services/fingerprints/goby.py

@@ -0,0 +1,70 @@
+"""Goby 指纹管理 Service
+
+实现 Goby 格式指纹的校验、转换和导出逻辑
+"""
+
+from apps.engine.models import GobyFingerprint
+from .base import BaseFingerprintService
+
+
+class GobyFingerprintService(BaseFingerprintService):
+    """Goby 指纹管理服务（继承基类，实现 Goby 特定逻辑）"""
+    
+    model = GobyFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 Goby 指纹
+        
+        校验规则：
+        - name 字段必须存在且非空
+        - logic 字段必须存在
+        - rule 字段必须是数组
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        name = item.get('name', '')
+        logic = item.get('logic', '')
+        rule = item.get('rule')
+        return bool(name and str(name).strip()) and bool(logic) and isinstance(rule, list)
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 Goby JSON 格式为 Model 字段
+        
+        Args:
+            item: 原始 Goby JSON 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        return {
+            'name': str(item.get('name', '')).strip(),
+            'logic': item.get('logic', ''),
+            'rule': item.get('rule', []),
+        }
+    
+    def get_export_data(self) -> list:
+        """
+        获取导出数据（Goby JSON 格式 - 数组）
+        
+        Returns:
+            list: Goby 格式的 JSON 数据（数组格式）
+            [
+                {"name": "...", "logic": "...", "rule": [...]},
+                ...
+            ]
+        """
+        fingerprints = self.model.objects.all()
+        return [
+            {
+                'name': fp.name,
+                'logic': fp.logic,
+                'rule': fp.rule,
+            }
+            for fp in fingerprints
+        ]

backend/apps/engine/services/fingerprints/wappalyzer.py

@@ -0,0 +1,99 @@
+"""Wappalyzer 指纹管理 Service
+
+实现 Wappalyzer 格式指纹的校验、转换和导出逻辑
+"""
+
+from apps.engine.models import WappalyzerFingerprint
+from .base import BaseFingerprintService
+
+
+class WappalyzerFingerprintService(BaseFingerprintService):
+    """Wappalyzer 指纹管理服务（继承基类，实现 Wappalyzer 特定逻辑）"""
+    
+    model = WappalyzerFingerprint
+    
+    def validate_fingerprint(self, item: dict) -> bool:
+        """
+        校验单条 Wappalyzer 指纹
+        
+        校验规则：
+        - name 字段必须存在且非空（从 apps 对象的 key 传入）
+        
+        Args:
+            item: 单条指纹数据
+            
+        Returns:
+            bool: 是否有效
+        """
+        name = item.get('name', '')
+        return bool(name and str(name).strip())
+    
+    def to_model_data(self, item: dict) -> dict:
+        """
+        转换 Wappalyzer JSON 格式为 Model 字段
+        
+        字段映射：
+        - scriptSrc (JSON) → script_src (Model)
+        
+        Args:
+            item: 原始 Wappalyzer JSON 数据
+            
+        Returns:
+            dict: Model 字段数据
+        """
+        return {
+            'name': str(item.get('name', '')).strip(),
+            'cats': item.get('cats', []),
+            'cookies': item.get('cookies', {}),
+            'headers': item.get('headers', {}),
+            'script_src': item.get('scriptSrc', []),  # JSON: scriptSrc -> Model: script_src
+            'js': item.get('js', []),
+            'implies': item.get('implies', []),
+            'meta': item.get('meta', {}),
+            'html': item.get('html', []),
+            'description': item.get('description', ''),
+            'website': item.get('website', ''),
+            'cpe': item.get('cpe', ''),
+        }
+    
+    def get_export_data(self) -> dict:
+        """
+        获取导出数据（Wappalyzer JSON 格式）
+        
+        Returns:
+            dict: Wappalyzer 格式的 JSON 数据
+            {
+                "apps": {
+                    "AppName": {"cats": [...], "cookies": {...}, ...},
+                    ...
+                }
+            }
+        """
+        fingerprints = self.model.objects.all()
+        apps = {}
+        for fp in fingerprints:
+            app_data = {}
+            if fp.cats:
+                app_data['cats'] = fp.cats
+            if fp.cookies:
+                app_data['cookies'] = fp.cookies
+            if fp.headers:
+                app_data['headers'] = fp.headers
+            if fp.script_src:
+                app_data['scriptSrc'] = fp.script_src  # Model: script_src -> JSON: scriptSrc
+            if fp.js:
+                app_data['js'] = fp.js
+            if fp.implies:
+                app_data['implies'] = fp.implies
+            if fp.meta:
+                app_data['meta'] = fp.meta
+            if fp.html:
+                app_data['html'] = fp.html
+            if fp.description:
+                app_data['description'] = fp.description
+            if fp.website:
+                app_data['website'] = fp.website
+            if fp.cpe:
+                app_data['cpe'] = fp.cpe
+            apps[fp.name] = app_data
+        return {'apps': apps}

backend/apps/engine/services/nuclei_template_repo_service.py

@@ -196,17 +196,39 @@ class NucleiTemplateRepoService:
         cmd: List[str]
         action: str
 
+        # 直接使用原始 URL（不再使用 Git 加速）
+        repo_url = obj.repo_url
+
         # 判断是 clone 还是 pull
         if git_dir.is_dir():
-            # 已有仓库，执行 pull
-            cmd = ["git", "-C", str(local_path), "pull", "--ff-only"]
-            action = "pull"
+            # 检查远程地址是否变化
+            current_remote = subprocess.run(
+                ["git", "-C", str(local_path), "remote", "get-url", "origin"],
+                check=False,
+                stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE,
+                text=True,
+            )
+            current_url = current_remote.stdout.strip() if current_remote.returncode == 0 else ""
+            
+            # 检查是否需要重新 clone
+            if current_url != repo_url:
+                # 远程地址变化，删除旧目录重新 clone
+                logger.info("nuclei 模板仓库 %s 远程地址变化，重新 clone: %s -> %s", obj.id, current_url, repo_url)
+                shutil.rmtree(local_path)
+                local_path.mkdir(parents=True, exist_ok=True)
+                cmd = ["git", "clone", "--depth", "1", repo_url, str(local_path)]
+                action = "clone"
+            else:
+                # 已有仓库且地址未变，执行 pull
+                cmd = ["git", "-C", str(local_path), "pull", "--ff-only"]
+                action = "pull"
         else:
             # 新仓库，执行 clone
             if local_path.exists() and not local_path.is_dir():
                 raise RuntimeError(f"本地路径已存在且不是目录: {local_path}")
             # --depth 1 浅克隆，只获取最新提交，节省空间和时间
-            cmd = ["git", "clone", "--depth", "1", obj.repo_url, str(local_path)]
+            cmd = ["git", "clone", "--depth", "1", repo_url, str(local_path)]
             action = "clone"
 
         # 执行 Git 命令

backend/apps/engine/services/task_distributor.py

@@ -76,8 +76,8 @@ class TaskDistributor:
         self.docker_image = settings.TASK_EXECUTOR_IMAGE
         if not self.docker_image:
             raise ValueError("TASK_EXECUTOR_IMAGE 未配置，请确保 IMAGE_TAG 环境变量已设置")
-        self.results_mount = getattr(settings, 'CONTAINER_RESULTS_MOUNT', '/app/backend/results')
-        self.logs_mount = getattr(settings, 'CONTAINER_LOGS_MOUNT', '/app/backend/logs')
+        # 统一使用 /opt/xingrin 下的路径
+        self.logs_mount = "/opt/xingrin/logs"
         self.submit_interval = getattr(settings, 'TASK_SUBMIT_INTERVAL', 5)
     
     def get_online_workers(self) -> list[WorkerNode]:
@@ -153,11 +153,68 @@ class TaskDistributor:
             else:
                 scored_workers.append((worker, score, cpu, mem))
         
-        # 降级策略：如果没有正常负载的，使用高负载中最低的
+        # 降级策略：如果没有正常负载的，循环等待后重新检测
         if not scored_workers:
             if high_load_workers:
-                logger.warning("所有 Worker 高负载，降级选择负载最低的")
-                scored_workers = high_load_workers
+                # 高负载等待参数（默认每 60 秒检测一次，最多 10 次）
+                high_load_wait = getattr(settings, 'HIGH_LOAD_WAIT_SECONDS', 60)
+                high_load_max_retries = getattr(settings, 'HIGH_LOAD_MAX_RETRIES', 10)
+                
+                # 开始等待前发送高负载通知
+                high_load_workers.sort(key=lambda x: x[1])
+                _, _, first_cpu, first_mem = high_load_workers[0]
+                from apps.common.signals import all_workers_high_load
+                all_workers_high_load.send(
+                    sender=self.__class__,
+                    worker_name="所有节点",
+                    cpu=first_cpu,
+                    mem=first_mem
+                )
+                
+                for retry in range(high_load_max_retries):
+                    logger.warning(
+                        "所有 Worker 高负载，等待 %d 秒后重试... (%d/%d)",
+                        high_load_wait, retry + 1, high_load_max_retries
+                    )
+                    time.sleep(high_load_wait)
+                    
+                    # 重新获取负载数据
+                    loads = worker_load_service.get_all_loads(worker_ids)
+                    
+                    # 重新评估
+                    scored_workers = []
+                    high_load_workers = []
+                    
+                    for worker in workers:
+                        load = loads.get(worker.id)
+                        if not load:
+                            continue
+                        
+                        cpu = load.get('cpu', 0)
+                        mem = load.get('mem', 0)
+                        score = cpu * 0.7 + mem * 0.3
+                        
+                        if cpu > 85 or mem > 85:
+                            high_load_workers.append((worker, score, cpu, mem))
+                        else:
+                            scored_workers.append((worker, score, cpu, mem))
+                    
+                    # 如果有正常负载的 Worker，跳出循环
+                    if scored_workers:
+                        logger.info("检测到正常负载 Worker，结束等待")
+                        break
+                
+                # 超时或仍然高负载，选择负载最低的
+                if not scored_workers and high_load_workers:
+                    high_load_workers.sort(key=lambda x: x[1])
+                    best_worker, _, cpu, mem = high_load_workers[0]
+                    
+                    logger.warning(
+                        "等待超时，强制分发到高负载 Worker: %s (CPU: %.1f%%, MEM: %.1f%%)",
+                        best_worker.name, cpu, mem
+                    )
+                    return best_worker
+                    return best_worker
             else:
                 logger.warning("没有可用的 Worker")
                 return None
@@ -213,26 +270,30 @@ class TaskDistributor:
             network_arg = f"--network {settings.DOCKER_NETWORK_NAME}"
             server_url = f"http://server:{settings.SERVER_PORT}"
         else:
-            # 远程：无需指定网络，使用公网地址
+            # 远程：通过 Nginx 反向代理访问（HTTPS，不直连 8888 端口）
             network_arg = ""
-            server_url = f"http://{settings.PUBLIC_HOST}:{settings.SERVER_PORT}"
+            server_url = f"https://{settings.PUBLIC_HOST}:{settings.PUBLIC_PORT}"
         
-        # 挂载路径（所有节点统一使用固定路径）
-        host_results_dir = settings.HOST_RESULTS_DIR  # /opt/xingrin/results
-        host_logs_dir = settings.HOST_LOGS_DIR  # /opt/xingrin/logs
+        # 挂载路径（统一挂载 /opt/xingrin，扫描工具在 /opt/xingrin-tools/bin 不受影响）
+        host_xingrin_dir = "/opt/xingrin"
         
-        # 环境变量：只需 SERVER_URL，其他配置容器启动时从配置中心获取
-        # Prefect 本地模式配置：禁用 API server 和事件系统
+        # 环境变量：SERVER_URL + IS_LOCAL，其他配置容器启动时从配置中心获取
+        # IS_LOCAL 用于 Worker 向配置中心声明身份，决定返回的数据库地址
+        # Prefect 本地模式配置：启用 ephemeral server（本地临时服务器）
+        is_local_str = "true" if worker.is_local else "false"
         env_vars = [
             f"-e SERVER_URL={shlex.quote(server_url)}",
-            "-e PREFECT_API_URL=",  # 禁用 API server
-            "-e PREFECT_LOGGING_EXTRA_LOGGERS=",  # 禁用 Prefect 的额外内部日志器
+            f"-e IS_LOCAL={is_local_str}",
+            "-e PREFECT_HOME=/tmp/.prefect",  # 设置 Prefect 数据目录到可写位置
+            "-e PREFECT_SERVER_EPHEMERAL_ENABLED=true",  # 启用 ephemeral server（本地临时服务器）
+            "-e PREFECT_SERVER_EPHEMERAL_STARTUP_TIMEOUT_SECONDS=120",  # 增加启动超时时间
+            "-e PREFECT_SERVER_DATABASE_CONNECTION_URL=sqlite+aiosqlite:////tmp/.prefect/prefect.db",  # 使用 /tmp 下的 SQLite
+            "-e PREFECT_LOGGING_LEVEL=WARNING",  # 日志级别（减少 DEBUG 噪音）
         ]
         
-        # 挂载卷
+        # 挂载卷（统一挂载整个 /opt/xingrin 目录）
         volumes = [
-            f"-v {host_results_dir}:{self.results_mount}",
-            f"-v {host_logs_dir}:{self.logs_mount}",
+            f"-v {host_xingrin_dir}:{host_xingrin_dir}",
         ]
         
         # 构建命令行参数
@@ -250,11 +311,10 @@ class TaskDistributor:
         # - 本地 Worker：install.sh 已预拉取镜像，直接使用本地版本
         # - 远程 Worker：deploy 时已预拉取镜像，直接使用本地版本
         # - 避免每次任务都检查 Docker Hub，提升性能和稳定性
-        # 使用双引号包裹 sh -c 命令，内部 shlex.quote 生成的单引号参数可正确解析
-        cmd = f'''docker run --rm -d --pull=missing {network_arg} \
-            {' '.join(env_vars)} \
-            {' '.join(volumes)} \
-            {self.docker_image} \
+        cmd = f'''docker run --rm -d --pull=missing {network_arg} \\
+            {' '.join(env_vars)} \\
+            {' '.join(volumes)} \\
+            {self.docker_image} \\
             sh -c "{inner_cmd}"'''
         
         return cmd
@@ -407,8 +467,20 @@ class TaskDistributor:
         Note:
             engine_config 由 Flow 内部通过 scan_id 查询数据库获取
         """
+        logger.info("="*60)
+        logger.info("execute_scan_flow 开始")
+        logger.info("  scan_id: %s", scan_id)
+        logger.info("  target_name: %s", target_name)
+        logger.info("  target_id: %s", target_id)
+        logger.info("  scan_workspace_dir: %s", scan_workspace_dir)
+        logger.info("  engine_name: %s", engine_name)
+        logger.info("  docker_image: %s", self.docker_image)
+        logger.info("="*60)
+        
         # 1. 等待提交间隔（后台线程执行，不阻塞 API）
+        logger.info("等待提交间隔...")
         self._wait_for_submit_interval()
+        logger.info("提交间隔等待完成")
         
         # 2. 选择最佳 Worker
         worker = self.select_best_worker()
@@ -481,7 +553,7 @@ class TaskDistributor:
             try:
                 # 构建 docker run 命令（清理过期扫描结果目录）
                 script_args = {
-                    'results_dir': '/app/backend/results',
+                    'results_dir': '/opt/xingrin/results',
                     'retention_days': retention_days,
                 }
                 

backend/apps/engine/services/wordlist_service.py

@@ -13,7 +13,7 @@ from django.conf import settings
 from django.core.exceptions import ValidationError
 from django.core.files.uploadedfile import UploadedFile
 
-from apps.common.hash_utils import safe_calc_file_sha256
+from apps.common.utils import safe_calc_file_sha256
 from apps.engine.models import Wordlist
 from apps.engine.repositories import DjangoWordlistRepository
 

backend/apps/engine/services/worker_service.py

@@ -134,5 +134,57 @@ class WorkerService:
             logger.warning(f"[卸载] Worker {worker_id} 远程卸载异常: {e}")
             return False, f"远程卸载异常: {str(e)}"
 
+    def execute_remote_command(
+        self,
+        ip_address: str,
+        ssh_port: int,
+        username: str,
+        password: str | None,
+        command: str
+    ) -> tuple[bool, str]:
+        """
+        在远程主机上执行命令
+        
+        Args:
+            ip_address: SSH 主机地址
+            ssh_port: SSH 端口
+            username: SSH 用户名
+            password: SSH 密码
+            command: 要执行的命令
+            
+        Returns:
+            (success, message) 元组
+        """
+        if not password:
+            return False, "未配置 SSH 密码"
+        
+        try:
+            import paramiko
+            
+            ssh = paramiko.SSHClient()
+            ssh.set_missing_host_key_policy(paramiko.AutoAddPolicy())
+            
+            ssh.connect(
+                ip_address,
+                port=ssh_port,
+                username=username,
+                password=password,
+                timeout=30
+            )
+            
+            stdin, stdout, stderr = ssh.exec_command(command, timeout=120)
+            exit_status = stdout.channel.recv_exit_status()
+            
+            ssh.close()
+            
+            if exit_status == 0:
+                return True, stdout.read().decode().strip()
+            else:
+                error = stderr.read().decode().strip()
+                return False, error
+                
+        except Exception as e:
+            return False, str(e)
+
 
 __all__ = ["WorkerService"]

backend/apps/engine/urls.py

@@ -7,6 +7,14 @@ from .views import (
     WordlistViewSet,
     NucleiTemplateRepoViewSet,
 )
+from .views.fingerprints import (
+    EholeFingerprintViewSet,
+    GobyFingerprintViewSet,
+    WappalyzerFingerprintViewSet,
+    FingersFingerprintViewSet,
+    FingerPrintHubFingerprintViewSet,
+    ARLFingerprintViewSet,
+)
 
 
 # 创建路由器
@@ -15,6 +23,13 @@ router.register(r"engines", ScanEngineViewSet, basename="engine")
 router.register(r"workers", WorkerNodeViewSet, basename="worker")
 router.register(r"wordlists", WordlistViewSet, basename="wordlist")
 router.register(r"nuclei/repos", NucleiTemplateRepoViewSet, basename="nuclei-repos")
+# 指纹管理
+router.register(r"fingerprints/ehole", EholeFingerprintViewSet, basename="ehole-fingerprint")
+router.register(r"fingerprints/goby", GobyFingerprintViewSet, basename="goby-fingerprint")
+router.register(r"fingerprints/wappalyzer", WappalyzerFingerprintViewSet, basename="wappalyzer-fingerprint")
+router.register(r"fingerprints/fingers", FingersFingerprintViewSet, basename="fingers-fingerprint")
+router.register(r"fingerprints/fingerprinthub", FingerPrintHubFingerprintViewSet, basename="fingerprinthub-fingerprint")
+router.register(r"fingerprints/arl", ARLFingerprintViewSet, basename="arl-fingerprint")
 
 urlpatterns = [
     path("", include(router.urls)),

backend/apps/engine/views/fingerprints/__init__.py

@@ -0,0 +1,22 @@
+"""指纹管理 ViewSets
+
+导出所有指纹相关的 ViewSet 类
+"""
+
+from .base import BaseFingerprintViewSet
+from .ehole import EholeFingerprintViewSet
+from .goby import GobyFingerprintViewSet
+from .wappalyzer import WappalyzerFingerprintViewSet
+from .fingers import FingersFingerprintViewSet
+from .fingerprinthub import FingerPrintHubFingerprintViewSet
+from .arl import ARLFingerprintViewSet
+
+__all__ = [
+    "BaseFingerprintViewSet",
+    "EholeFingerprintViewSet",
+    "GobyFingerprintViewSet",
+    "WappalyzerFingerprintViewSet",
+    "FingersFingerprintViewSet",
+    "FingerPrintHubFingerprintViewSet",
+    "ARLFingerprintViewSet",
+]

backend/apps/engine/views/fingerprints/arl.py

@@ -0,0 +1,122 @@
+"""ARL 指纹管理 ViewSet"""
+
+import yaml
+from django.http import HttpResponse
+from rest_framework.decorators import action
+from rest_framework.exceptions import ValidationError
+
+from apps.common.pagination import BasePagination
+from apps.common.response_helpers import success_response
+from apps.engine.models import ARLFingerprint
+from apps.engine.serializers.fingerprints import ARLFingerprintSerializer
+from apps.engine.services.fingerprints import ARLFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class ARLFingerprintViewSet(BaseFingerprintViewSet):
+    """ARL 指纹管理 ViewSet
+    
+    继承自 BaseFingerprintViewSet，提供以下 API：
+    
+    标准 CRUD（ModelViewSet）：
+    - GET    /                  列表查询（分页）
+    - POST   /                  创建单条
+    - GET    /{id}/             获取详情
+    - PUT    /{id}/             更新
+    - DELETE /{id}/             删除
+    
+    批量操作（继承自基类）：
+    - POST   /batch_create/     批量创建（JSON body）
+    - POST   /import_file/      文件导入（multipart/form-data，支持 YAML）
+    - POST   /bulk-delete/      批量删除
+    - POST   /delete-all/       删除所有
+    - GET    /export/           导出下载（YAML 格式）
+    
+    智能过滤语法（filter 参数）：
+    - name="word"        模糊匹配 name 字段
+    - name=="WordPress"  精确匹配
+    - rule="body="       按规则内容筛选
+    """
+    
+    queryset = ARLFingerprint.objects.all()
+    serializer_class = ARLFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = ARLFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'name']
+    ordering = ['-created_at']
+    
+    # ARL 过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+        'rule': 'rule',
+    }
+    
+    def parse_import_data(self, json_data) -> list:
+        """
+        解析 ARL 格式的导入数据（JSON 格式）
+        
+        输入格式：[{...}, {...}] 数组格式
+        返回：指纹列表
+        """
+        if isinstance(json_data, list):
+            return json_data
+        return []
+    
+    def get_export_filename(self) -> str:
+        """导出文件名"""
+        return 'ARL.yaml'
+    
+    @action(detail=False, methods=['post'])
+    def import_file(self, request):
+        """
+        文件导入（支持 YAML 和 JSON 格式）
+        POST /api/engine/fingerprints/arl/import_file/
+        
+        请求格式：multipart/form-data
+        - file: YAML 或 JSON 文件
+        
+        返回：同 batch_create
+        """
+        file = request.FILES.get('file')
+        if not file:
+            raise ValidationError('缺少文件')
+        
+        filename = file.name.lower()
+        content = file.read().decode('utf-8')
+        
+        try:
+            if filename.endswith('.yaml') or filename.endswith('.yml'):
+                # YAML 格式
+                fingerprints = yaml.safe_load(content)
+            else:
+                # JSON 格式
+                import json
+                fingerprints = json.loads(content)
+        except (yaml.YAMLError, json.JSONDecodeError) as e:
+            raise ValidationError(f'无效的文件格式: {e}')
+        
+        if not isinstance(fingerprints, list):
+            raise ValidationError('文件内容必须是数组格式')
+        
+        if not fingerprints:
+            raise ValidationError('文件中没有有效的指纹数据')
+        
+        result = self.get_service().batch_create_fingerprints(fingerprints)
+        return success_response(data=result)
+    
+    @action(detail=False, methods=['get'])
+    def export(self, request):
+        """
+        导出指纹（YAML 格式）
+        GET /api/engine/fingerprints/arl/export/
+        
+        返回：YAML 文件下载
+        """
+        data = self.get_service().get_export_data()
+        content = yaml.dump(data, allow_unicode=True, default_flow_style=False, sort_keys=False)
+        response = HttpResponse(content, content_type='application/x-yaml')
+        response['Content-Disposition'] = f'attachment; filename="{self.get_export_filename()}"'
+        return response

backend/apps/engine/views/fingerprints/base.py

@@ -0,0 +1,203 @@
+"""指纹管理基类 ViewSet
+
+提供通用的 CRUD 和批量操作，供 EHole/Goby/Wappalyzer 等子类继承
+"""
+
+import json
+import logging
+
+from django.http import HttpResponse
+from rest_framework import viewsets, status, filters
+from rest_framework.decorators import action
+from rest_framework.response import Response
+from rest_framework.exceptions import ValidationError
+
+from apps.common.pagination import BasePagination
+from apps.common.response_helpers import success_response
+from apps.common.utils.filter_utils import apply_filters
+
+logger = logging.getLogger(__name__)
+
+
+class BaseFingerprintViewSet(viewsets.ModelViewSet):
+    """指纹管理基类 ViewSet，供 EHole/Goby/Wappalyzer 等子类继承
+    
+    提供的 API：
+    
+    标准 CRUD（继承自 ModelViewSet）：
+    - GET    /                  列表查询（分页 + 智能过滤）
+    - POST   /                  创建单条
+    - GET    /{id}/             获取详情
+    - PUT    /{id}/             更新
+    - DELETE /{id}/             删除
+    
+    批量操作（本类实现）：
+    - POST   /batch_create/     批量创建（JSON body）
+    - POST   /import_file/      文件导入（multipart/form-data，适合 10MB+ 大文件）
+    - POST   /bulk-delete/      批量删除
+    - POST   /delete-all/       删除所有
+    - GET    /export/           导出下载
+    
+    智能过滤语法（filter 参数）：
+    - field="value"      模糊匹配（包含）
+    - field=="value"     精确匹配
+    - 多条件空格分隔     AND 关系
+    - || 或 or           OR 关系
+    
+    子类必须实现：
+    - service_class      Service 类
+    - parse_import_data  解析导入数据格式
+    - get_export_filename 导出文件名
+    """
+    
+    pagination_class = BasePagination
+    filter_backends = [filters.OrderingFilter]
+    ordering = ['-created_at']
+    
+    # 子类必须指定
+    service_class = None  # Service 类
+    
+    # 智能过滤字段映射，子类必须覆盖
+    FILTER_FIELD_MAPPING = {}
+    
+    # JSON 数组字段列表（使用 __contains 查询），子类可覆盖
+    JSON_ARRAY_FIELDS = []
+    
+    def get_queryset(self):
+        """支持智能过滤语法"""
+        queryset = super().get_queryset()
+        filter_query = self.request.query_params.get('filter', None)
+        if filter_query:
+            queryset = apply_filters(
+                queryset, 
+                filter_query, 
+                self.FILTER_FIELD_MAPPING,
+                json_array_fields=getattr(self, 'JSON_ARRAY_FIELDS', [])
+            )
+        return queryset
+    
+    def get_service(self):
+        """获取 Service 实例"""
+        if self.service_class is None:
+            raise NotImplementedError("子类必须指定 service_class")
+        return self.service_class()
+    
+    def parse_import_data(self, json_data: dict) -> list:
+        """
+        解析导入数据，子类必须实现
+        
+        Args:
+            json_data: 解析后的 JSON 数据
+            
+        Returns:
+            list: 指纹数据列表
+        """
+        raise NotImplementedError("子类必须实现 parse_import_data 方法")
+    
+    def get_export_filename(self) -> str:
+        """
+        导出文件名，子类必须实现
+        
+        Returns:
+            str: 文件名
+        """
+        raise NotImplementedError("子类必须实现 get_export_filename 方法")
+
+    @action(detail=False, methods=['post'])
+    def batch_create(self, request):
+        """
+        批量创建指纹规则
+        POST /api/engine/fingerprints/{type}/batch_create/
+        
+        请求格式：
+        {
+            "fingerprints": [
+                {"cms": "WordPress", "method": "keyword", ...},
+                ...
+            ]
+        }
+        
+        返回：
+        {
+            "created": 2,
+            "failed": 0
+        }
+        """
+        fingerprints = request.data.get('fingerprints', [])
+        if not fingerprints:
+            raise ValidationError('fingerprints 不能为空')
+        if not isinstance(fingerprints, list):
+            raise ValidationError('fingerprints 必须是数组')
+        
+        result = self.get_service().batch_create_fingerprints(fingerprints)
+        return success_response(data=result, status_code=status.HTTP_201_CREATED)
+    
+    @action(detail=False, methods=['post'])
+    def import_file(self, request):
+        """
+        文件导入（适合大文件，10MB+）
+        POST /api/engine/fingerprints/{type}/import_file/
+        
+        请求格式：multipart/form-data
+        - file: JSON 文件
+        
+        返回：同 batch_create
+        """
+        file = request.FILES.get('file')
+        if not file:
+            raise ValidationError('缺少文件')
+        
+        try:
+            json_data = json.load(file)
+        except json.JSONDecodeError as e:
+            raise ValidationError(f'无效的 JSON 格式: {e}')
+        
+        fingerprints = self.parse_import_data(json_data)
+        if not fingerprints:
+            raise ValidationError('文件中没有有效的指纹数据')
+        
+        result = self.get_service().batch_create_fingerprints(fingerprints)
+        return success_response(data=result, status_code=status.HTTP_201_CREATED)
+    
+    @action(detail=False, methods=['post'], url_path='bulk-delete')
+    def bulk_delete(self, request):
+        """
+        批量删除
+        POST /api/engine/fingerprints/{type}/bulk-delete/
+        
+        请求格式：{"ids": [1, 2, 3]}
+        返回：{"deleted": 3}
+        """
+        ids = request.data.get('ids', [])
+        if not ids:
+            raise ValidationError('ids 不能为空')
+        if not isinstance(ids, list):
+            raise ValidationError('ids 必须是数组')
+        
+        deleted_count = self.queryset.model.objects.filter(id__in=ids).delete()[0]
+        return success_response(data={'deleted': deleted_count})
+    
+    @action(detail=False, methods=['post'], url_path='delete-all')
+    def delete_all(self, request):
+        """
+        删除所有指纹
+        POST /api/engine/fingerprints/{type}/delete-all/
+        
+        返回：{"deleted": 1000}
+        """
+        deleted_count = self.queryset.model.objects.all().delete()[0]
+        return success_response(data={'deleted': deleted_count})
+    
+    @action(detail=False, methods=['get'])
+    def export(self, request):
+        """
+        导出指纹（前端下载）
+        GET /api/engine/fingerprints/{type}/export/
+        
+        返回：JSON 文件下载
+        """
+        data = self.get_service().get_export_data()
+        content = json.dumps(data, ensure_ascii=False, indent=2)
+        response = HttpResponse(content, content_type='application/json')
+        response['Content-Disposition'] = f'attachment; filename="{self.get_export_filename()}"'
+        return response

backend/apps/engine/views/fingerprints/ehole.py

@@ -0,0 +1,67 @@
+"""EHole 指纹管理 ViewSet"""
+
+from apps.common.pagination import BasePagination
+from apps.engine.models import EholeFingerprint
+from apps.engine.serializers.fingerprints import EholeFingerprintSerializer
+from apps.engine.services.fingerprints import EholeFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class EholeFingerprintViewSet(BaseFingerprintViewSet):
+    """EHole 指纹管理 ViewSet
+    
+    继承自 BaseFingerprintViewSet，提供以下 API：
+    
+    标准 CRUD（ModelViewSet）：
+    - GET    /                  列表查询（分页）
+    - POST   /                  创建单条
+    - GET    /{id}/             获取详情
+    - PUT    /{id}/             更新
+    - DELETE /{id}/             删除
+    
+    批量操作（继承自基类）：
+    - POST   /batch_create/     批量创建（JSON body）
+    - POST   /import_file/      文件导入（multipart/form-data）
+    - POST   /bulk-delete/      批量删除
+    - POST   /delete-all/       删除所有
+    - GET    /export/           导出下载
+    
+    智能过滤语法（filter 参数）：
+    - cms="word"         模糊匹配 cms 字段
+    - cms=="WordPress"   精确匹配
+    - type="CMS"         按类型筛选
+    - method="keyword"   按匹配方式筛选
+    - location="body"    按匹配位置筛选
+    """
+    
+    queryset = EholeFingerprint.objects.all()
+    serializer_class = EholeFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = EholeFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'cms']
+    ordering = ['-created_at']
+    
+    # EHole 过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'cms': 'cms',
+        'method': 'method',
+        'location': 'location',
+        'type': 'type',
+        'isImportant': 'is_important',
+    }
+    
+    def parse_import_data(self, json_data: dict) -> list:
+        """
+        解析 EHole JSON 格式的导入数据
+        
+        输入格式：{"fingerprint": [...]}
+        返回：指纹列表
+        """
+        return json_data.get('fingerprint', [])
+    
+    def get_export_filename(self) -> str:
+        """导出文件名"""
+        return 'ehole.json'

backend/apps/engine/views/fingerprints/fingerprinthub.py

@@ -0,0 +1,73 @@
+"""FingerPrintHub 指纹管理 ViewSet"""
+
+from apps.common.pagination import BasePagination
+from apps.engine.models import FingerPrintHubFingerprint
+from apps.engine.serializers.fingerprints import FingerPrintHubFingerprintSerializer
+from apps.engine.services.fingerprints import FingerPrintHubFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class FingerPrintHubFingerprintViewSet(BaseFingerprintViewSet):
+    """FingerPrintHub 指纹管理 ViewSet
+    
+    继承自 BaseFingerprintViewSet，提供以下 API：
+    
+    标准 CRUD（ModelViewSet）：
+    - GET    /                  列表查询（分页）
+    - POST   /                  创建单条
+    - GET    /{id}/             获取详情
+    - PUT    /{id}/             更新
+    - DELETE /{id}/             删除
+    
+    批量操作（继承自基类）：
+    - POST   /batch_create/     批量创建（JSON body）
+    - POST   /import_file/      文件导入（multipart/form-data）
+    - POST   /bulk-delete/      批量删除
+    - POST   /delete-all/       删除所有
+    - GET    /export/           导出下载
+    
+    智能过滤语法（filter 参数）：
+    - name="word"        模糊匹配 name 字段
+    - fp_id=="xxx"       精确匹配指纹ID
+    - author="xxx"       按作者筛选
+    - severity="info"    按严重程度筛选
+    - tags="cms"         按标签筛选
+    """
+    
+    queryset = FingerPrintHubFingerprint.objects.all()
+    serializer_class = FingerPrintHubFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = FingerPrintHubFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'name', 'severity']
+    ordering = ['-created_at']
+    
+    # FingerPrintHub 过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'fp_id': 'fp_id',
+        'name': 'name',
+        'author': 'author',
+        'tags': 'tags',
+        'severity': 'severity',
+        'source_file': 'source_file',
+    }
+    
+    # JSON 数组字段（使用 __contains 查询）
+    JSON_ARRAY_FIELDS = ['http']
+    
+    def parse_import_data(self, json_data) -> list:
+        """
+        解析 FingerPrintHub JSON 格式的导入数据
+        
+        输入格式：[{...}, {...}] 数组格式
+        返回：指纹列表
+        """
+        if isinstance(json_data, list):
+            return json_data
+        return []
+    
+    def get_export_filename(self) -> str:
+        """导出文件名"""
+        return 'fingerprinthub_web.json'

backend/apps/engine/views/fingerprints/fingers.py

@@ -0,0 +1,69 @@
+"""Fingers 指纹管理 ViewSet"""
+
+from apps.common.pagination import BasePagination
+from apps.engine.models import FingersFingerprint
+from apps.engine.serializers.fingerprints import FingersFingerprintSerializer
+from apps.engine.services.fingerprints import FingersFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class FingersFingerprintViewSet(BaseFingerprintViewSet):
+    """Fingers 指纹管理 ViewSet
+    
+    继承自 BaseFingerprintViewSet，提供以下 API：
+    
+    标准 CRUD（ModelViewSet）：
+    - GET    /                  列表查询（分页）
+    - POST   /                  创建单条
+    - GET    /{id}/             获取详情
+    - PUT    /{id}/             更新
+    - DELETE /{id}/             删除
+    
+    批量操作（继承自基类）：
+    - POST   /batch_create/     批量创建（JSON body）
+    - POST   /import_file/      文件导入（multipart/form-data）
+    - POST   /bulk-delete/      批量删除
+    - POST   /delete-all/       删除所有
+    - GET    /export/           导出下载
+    
+    智能过滤语法（filter 参数）：
+    - name="word"        模糊匹配 name 字段
+    - name=="WordPress"  精确匹配
+    - tag="cms"          按标签筛选
+    - focus="true"       按重点关注筛选
+    """
+    
+    queryset = FingersFingerprint.objects.all()
+    serializer_class = FingersFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = FingersFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'name']
+    ordering = ['-created_at']
+    
+    # Fingers 过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+        'link': 'link',
+        'focus': 'focus',
+    }
+    
+    # JSON 数组字段（使用 __contains 查询）
+    JSON_ARRAY_FIELDS = ['tag', 'rule', 'default_port']
+    
+    def parse_import_data(self, json_data) -> list:
+        """
+        解析 Fingers JSON 格式的导入数据
+        
+        输入格式：[{...}, {...}] 数组格式
+        返回：指纹列表
+        """
+        if isinstance(json_data, list):
+            return json_data
+        return []
+    
+    def get_export_filename(self) -> str:
+        """导出文件名"""
+        return 'fingers_http.json'

backend/apps/engine/views/fingerprints/goby.py

@@ -0,0 +1,65 @@
+"""Goby 指纹管理 ViewSet"""
+
+from apps.common.pagination import BasePagination
+from apps.engine.models import GobyFingerprint
+from apps.engine.serializers.fingerprints import GobyFingerprintSerializer
+from apps.engine.services.fingerprints import GobyFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class GobyFingerprintViewSet(BaseFingerprintViewSet):
+    """Goby 指纹管理 ViewSet
+    
+    继承自 BaseFingerprintViewSet，提供以下 API：
+    
+    标准 CRUD（ModelViewSet）：
+    - GET    /                  列表查询（分页）
+    - POST   /                  创建单条
+    - GET    /{id}/             获取详情
+    - PUT    /{id}/             更新
+    - DELETE /{id}/             删除
+    
+    批量操作（继承自基类）：
+    - POST   /batch_create/     批量创建（JSON body）
+    - POST   /import_file/      文件导入（multipart/form-data）
+    - POST   /bulk-delete/      批量删除
+    - POST   /delete-all/       删除所有
+    - GET    /export/           导出下载
+    
+    智能过滤语法（filter 参数）：
+    - name="word"        模糊匹配 name 字段
+    - name=="ProductName" 精确匹配
+    """
+    
+    queryset = GobyFingerprint.objects.all()
+    serializer_class = GobyFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = GobyFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'name']
+    ordering = ['-created_at']
+    
+    # Goby 过滤字段映射
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+        'logic': 'logic',
+    }
+    
+    def parse_import_data(self, json_data) -> list:
+        """
+        解析 Goby JSON 格式的导入数据
+        
+        Goby 格式是数组格式：[{...}, {...}, ...]
+        
+        输入格式：[{"name": "...", "logic": "...", "rule": [...]}, ...]
+        返回：指纹列表
+        """
+        if isinstance(json_data, list):
+            return json_data
+        return []
+    
+    def get_export_filename(self) -> str:
+        """导出文件名"""
+        return 'goby.json'

backend/apps/engine/views/fingerprints/wappalyzer.py

@@ -0,0 +1,75 @@
+"""Wappalyzer 指纹管理 ViewSet"""
+
+from apps.common.pagination import BasePagination
+from apps.engine.models import WappalyzerFingerprint
+from apps.engine.serializers.fingerprints import WappalyzerFingerprintSerializer
+from apps.engine.services.fingerprints import WappalyzerFingerprintService
+
+from .base import BaseFingerprintViewSet
+
+
+class WappalyzerFingerprintViewSet(BaseFingerprintViewSet):
+    """Wappalyzer 指纹管理 ViewSet
+    
+    继承自 BaseFingerprintViewSet，提供以下 API：
+    
+    标准 CRUD（ModelViewSet）：
+    - GET    /                  列表查询（分页）
+    - POST   /                  创建单条
+    - GET    /{id}/             获取详情
+    - PUT    /{id}/             更新
+    - DELETE /{id}/             删除
+    
+    批量操作（继承自基类）：
+    - POST   /batch_create/     批量创建（JSON body）
+    - POST   /import_file/      文件导入（multipart/form-data）
+    - POST   /bulk-delete/      批量删除
+    - POST   /delete-all/       删除所有
+    - GET    /export/           导出下载
+    
+    智能过滤语法（filter 参数）：
+    - name="word"        模糊匹配 name 字段
+    - name=="AppName"    精确匹配
+    """
+    
+    queryset = WappalyzerFingerprint.objects.all()
+    serializer_class = WappalyzerFingerprintSerializer
+    pagination_class = BasePagination
+    service_class = WappalyzerFingerprintService
+    
+    # 排序配置
+    ordering_fields = ['created_at', 'name']
+    ordering = ['-created_at']
+    
+    # Wappalyzer 过滤字段映射
+    # 注意：implies 是 JSON 数组字段，使用 __contains 查询
+    FILTER_FIELD_MAPPING = {
+        'name': 'name',
+        'description': 'description',
+        'website': 'website',
+        'cpe': 'cpe',
+        'implies': 'implies',  # JSON 数组字段
+    }
+    
+    # JSON 数组字段列表（使用 __contains 查询）
+    JSON_ARRAY_FIELDS = ['implies']
+    
+    def parse_import_data(self, json_data: dict) -> list:
+        """
+        解析 Wappalyzer JSON 格式的导入数据
+        
+        Wappalyzer 格式是 apps 对象格式：{"apps": {"AppName": {...}, ...}}
+        
+        输入格式：{"apps": {"1C-Bitrix": {"cats": [...], ...}, ...}}
+        返回：指纹列表（每个 app 转换为带 name 字段的 dict）
+        """
+        apps = json_data.get('apps', {})
+        fingerprints = []
+        for name, data in apps.items():
+            item = {'name': name, **data}
+            fingerprints.append(item)
+        return fingerprints
+    
+    def get_export_filename(self) -> str:
+        """导出文件名"""
+        return 'wappalyzer.json'

backend/apps/engine/views/nuclei_template_repo_views.py

@@ -31,6 +31,8 @@ from rest_framework.decorators import action
 from rest_framework.request import Request
 from rest_framework.response import Response
 
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
 from apps.engine.models import NucleiTemplateRepo
 from apps.engine.serializers import NucleiTemplateRepoSerializer
 from apps.engine.services import NucleiTemplateRepoService
@@ -107,18 +109,30 @@ class NucleiTemplateRepoViewSet(viewsets.ModelViewSet):
         try:
             repo_id = int(pk) if pk is not None else None
         except (TypeError, ValueError):
-            return Response({"message": "无效的仓库 ID"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Invalid repository ID',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         # 调用 Service 层
         try:
             result = self.service.refresh_repo(repo_id)
         except ValidationError as exc:
-            return Response({"message": str(exc)}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=str(exc),
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
         except Exception as exc:  # noqa: BLE001
             logger.error("刷新 Nuclei 模板仓库失败: %s", exc, exc_info=True)
-            return Response({"message": "刷新仓库失败"}, status=status.HTTP_500_INTERNAL_SERVER_ERROR)
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message=f'Refresh failed: {exc}',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
 
-        return Response({"message": "刷新成功", "result": result}, status=status.HTTP_200_OK)
+        return success_response(data={'result': result})
 
     # ==================== 自定义 Action: 模板只读浏览 ====================
 
@@ -142,18 +156,30 @@ class NucleiTemplateRepoViewSet(viewsets.ModelViewSet):
         try:
             repo_id = int(pk) if pk is not None else None
         except (TypeError, ValueError):
-            return Response({"message": "无效的仓库 ID"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Invalid repository ID',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         # 调用 Service 层，仅从当前本地目录读取目录树
         try:
             roots = self.service.get_template_tree(repo_id)
         except ValidationError as exc:
-            return Response({"message": str(exc)}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=str(exc),
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
         except Exception as exc:  # noqa: BLE001
             logger.error("获取 Nuclei 模板目录树失败: %s", exc, exc_info=True)
-            return Response({"message": "获取模板目录树失败"}, status=status.HTTP_500_INTERNAL_SERVER_ERROR)
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to get template tree',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
 
-        return Response({"roots": roots})
+        return success_response(data={'roots': roots})
 
     @action(detail=True, methods=["get"], url_path="templates/content")
     def templates_content(self, request: Request, pk: str | None = None) -> Response:
@@ -174,23 +200,43 @@ class NucleiTemplateRepoViewSet(viewsets.ModelViewSet):
         try:
             repo_id = int(pk) if pk is not None else None
         except (TypeError, ValueError):
-            return Response({"message": "无效的仓库 ID"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Invalid repository ID',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         # 解析 path 参数
         rel_path = (request.query_params.get("path", "") or "").strip()
         if not rel_path:
-            return Response({"message": "缺少 path 参数"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Missing path parameter',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         # 调用 Service 层
         try:
             result = self.service.get_template_content(repo_id, rel_path)
         except ValidationError as exc:
-            return Response({"message": str(exc)}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=str(exc),
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
         except Exception as exc:  # noqa: BLE001
             logger.error("获取 Nuclei 模板内容失败: %s", exc, exc_info=True)
-            return Response({"message": "获取模板内容失败"}, status=status.HTTP_500_INTERNAL_SERVER_ERROR)
+            return error_response(
+                code=ErrorCodes.SERVER_ERROR,
+                message='Failed to get template content',
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR
+            )
 
         # 文件不存在
         if result is None:
-            return Response({"message": "模板不存在或无法读取"}, status=status.HTTP_404_NOT_FOUND)
-        return Response(result)
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                message='Template not found or unreadable',
+                status_code=status.HTTP_404_NOT_FOUND
+            )
+        return success_response(data=result)

backend/apps/engine/views/wordlist_views.py

@@ -9,6 +9,8 @@ from rest_framework.decorators import action
 from rest_framework.response import Response
 
 from apps.common.pagination import BasePagination
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
 from apps.engine.serializers.wordlist_serializer import WordlistSerializer
 from apps.engine.services.wordlist_service import WordlistService
 
@@ -46,7 +48,11 @@ class WordlistViewSet(viewsets.ViewSet):
         uploaded_file = request.FILES.get("file")
 
         if not uploaded_file:
-            return Response({"error": "缺少字典文件"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Missing wordlist file',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         try:
             wordlist = self.service.create_wordlist(
@@ -55,21 +61,32 @@ class WordlistViewSet(viewsets.ViewSet):
                 uploaded_file=uploaded_file,
             )
         except ValidationError as exc:
-            return Response({"error": str(exc)}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message=str(exc),
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         serializer = WordlistSerializer(wordlist)
-        return Response(serializer.data, status=status.HTTP_201_CREATED)
+        return success_response(data=serializer.data, status_code=status.HTTP_201_CREATED)
 
     def destroy(self, request, pk=None):
         """删除字典记录"""
         try:
             wordlist_id = int(pk)
         except (TypeError, ValueError):
-            return Response({"error": "无效的 ID"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Invalid ID',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         success = self.service.delete_wordlist(wordlist_id)
         if not success:
-            return Response({"error": "字典不存在"}, status=status.HTTP_404_NOT_FOUND)
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                status_code=status.HTTP_404_NOT_FOUND
+            )
 
         return Response(status=status.HTTP_204_NO_CONTENT)
 
@@ -82,15 +99,27 @@ class WordlistViewSet(viewsets.ViewSet):
         """
         name = (request.query_params.get("wordlist", "") or "").strip()
         if not name:
-            return Response({"error": "缺少参数 wordlist"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Missing parameter: wordlist',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         wordlist = self.service.get_wordlist_by_name(name)
         if not wordlist:
-            return Response({"error": "字典不存在"}, status=status.HTTP_404_NOT_FOUND)
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                message='Wordlist not found',
+                status_code=status.HTTP_404_NOT_FOUND
+            )
 
         file_path = wordlist.file_path
         if not file_path or not os.path.exists(file_path):
-            return Response({"error": "字典文件不存在"}, status=status.HTTP_404_NOT_FOUND)
+            return error_response(
+                code=ErrorCodes.NOT_FOUND,
+                message='Wordlist file not found',
+                status_code=status.HTTP_404_NOT_FOUND
+            )
 
         filename = os.path.basename(file_path)
         response = FileResponse(open(file_path, "rb"), as_attachment=True, filename=filename)
@@ -106,22 +135,38 @@ class WordlistViewSet(viewsets.ViewSet):
         try:
             wordlist_id = int(pk)
         except (TypeError, ValueError):
-            return Response({"error": "无效的 ID"}, status=status.HTTP_400_BAD_REQUEST)
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Invalid ID',
+                status_code=status.HTTP_400_BAD_REQUEST
+            )
 
         if request.method == "GET":
             content = self.service.get_wordlist_content(wordlist_id)
             if content is None:
-                return Response({"error": "字典不存在或文件无法读取"}, status=status.HTTP_404_NOT_FOUND)
-            return Response({"content": content})
+                return error_response(
+                    code=ErrorCodes.NOT_FOUND,
+                    message='Wordlist not found or file unreadable',
+                    status_code=status.HTTP_404_NOT_FOUND
+                )
+            return success_response(data={"content": content})
 
         elif request.method == "PUT":
             content = request.data.get("content")
             if content is None:
-                return Response({"error": "缺少 content 参数"}, status=status.HTTP_400_BAD_REQUEST)
+                return error_response(
+                    code=ErrorCodes.VALIDATION_ERROR,
+                    message='Missing content parameter',
+                    status_code=status.HTTP_400_BAD_REQUEST
+                )
 
             wordlist = self.service.update_wordlist_content(wordlist_id, content)
             if not wordlist:
-                return Response({"error": "字典不存在或更新失败"}, status=status.HTTP_404_NOT_FOUND)
+                return error_response(
+                    code=ErrorCodes.NOT_FOUND,
+                    message='Wordlist not found or update failed',
+                    status_code=status.HTTP_404_NOT_FOUND
+                )
 
             serializer = WordlistSerializer(wordlist)
-            return Response(serializer.data)
+            return success_response(data=serializer.data)

backend/apps/engine/views/worker_views.py

@@ -9,6 +9,8 @@ from rest_framework import viewsets, status
 from rest_framework.decorators import action
 from rest_framework.response import Response
 
+from apps.common.response_helpers import success_response, error_response
+from apps.common.error_codes import ErrorCodes
 from apps.engine.serializers import WorkerNodeSerializer
 from apps.engine.services import WorkerService
 from apps.common.signals import worker_delete_failed
@@ -111,15 +113,42 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
         threading.Thread(target=_async_remote_uninstall, daemon=True).start()
         
         # 3. 立即返回成功
-        return Response(
-            {"message": f"节点 {worker_name} 已删除"},
-            status=status.HTTP_200_OK
+        return success_response(
+            data={'name': worker_name}
         )
     
     @action(detail=True, methods=['post'])
     def heartbeat(self, request, pk=None):
-        """接收心跳上报（写 Redis，首次心跳更新部署状态）"""
+        """
+        接收心跳上报（写 Redis，首次心跳更新部署状态，检查版本）
+        
+        请求体:
+        {
+            "cpu_percent": 50.0,
+            "memory_percent": 60.0,
+            "version": "v1.0.9"
+        }
+        
+        返回:
+        {
+            "status": "ok",
+            "need_update": true/false,
+            "server_version": "v1.0.19"
+        }
+        
+        状态流转:
+        ┌─────────────────────────────────────────────────────────────────────┐
+        │ 场景                        │ 状态变化                              │
+        ├─────────────────────────────┼───────────────────────────────────────┤
+        │ 首次心跳                    │ pending/deploying → online            │
+        │ 远程 Worker 版本不匹配      │ online → updating → (更新成功) online │
+        │ 远程 Worker 更新失败        │ updating → outdated                   │
+        │ 本地 Worker 版本不匹配      │ online → outdated (需手动 update.sh)  │
+        │ 版本匹配                    │ updating/outdated → online            │
+        └─────────────────────────────┴───────────────────────────────────────┘
+        """
         from apps.engine.services.worker_load_service import worker_load_service
+        from django.conf import settings
         
         worker = self.get_object()
         info = request.data if request.data else {}
@@ -134,7 +163,124 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
             worker.status = 'online'
             worker.save(update_fields=['status'])
         
-        return Response({'status': 'ok'})
+        # 3. 版本检查：比较 agent 版本与 server 版本
+        agent_version = info.get('version', '')
+        server_version = settings.IMAGE_TAG  # Server 当前版本
+        need_update = False
+        
+        if agent_version and agent_version != 'unknown':
+            # 版本不匹配时通知 agent 更新
+            need_update = agent_version != server_version
+            if need_update:
+                logger.info(
+                    f"Worker {worker.name} 版本不匹配: agent={agent_version}, server={server_version}"
+                )
+                
+                # 远程 Worker：服务端主动通过 SSH 触发更新
+                if not worker.is_local and worker.ip_address:
+                    self._trigger_remote_agent_update(worker, server_version)
+                else:
+                    # 本地 Worker 版本不匹配：标记为 outdated
+                    # 需要用户手动执行 update.sh 更新
+                    if worker.status != 'outdated':
+                        worker.status = 'outdated'
+                        worker.save(update_fields=['status'])
+            else:
+                # 版本匹配，确保状态为 online
+                if worker.status in ('updating', 'outdated'):
+                    worker.status = 'online'
+                    worker.save(update_fields=['status'])
+        
+        return success_response(
+            data={
+                'status': 'ok',
+                'needUpdate': need_update,
+                'serverVersion': server_version
+            }
+        )
+    
+    def _trigger_remote_agent_update(self, worker, target_version: str):
+        """
+        通过 SSH 触发远程 agent 更新（后台执行，不阻塞心跳响应）
+        
+        使用 Redis 锁防止重复触发（同一 worker 60秒内只触发一次）
+        """
+        import redis
+        from django.conf import settings as django_settings
+        
+        redis_url = f"redis://{django_settings.REDIS_HOST}:{django_settings.REDIS_PORT}/{django_settings.REDIS_DB}"
+        redis_client = redis.from_url(redis_url)
+        lock_key = f"agent_update_lock:{worker.id}"
+        
+        # 尝试获取锁（60秒过期，防止重复触发）
+        if not redis_client.set(lock_key, "1", nx=True, ex=60):
+            logger.debug(f"Worker {worker.name} 更新已在进行中，跳过")
+            return
+        
+        # 获取锁成功，设置状态为 updating
+        self._set_worker_status(worker.id, 'updating')
+        
+        # 提取数据避免后台线程访问 ORM
+        worker_id = worker.id
+        worker_name = worker.name
+        ip_address = worker.ip_address
+        ssh_port = worker.ssh_port
+        username = worker.username
+        password = worker.password
+        
+        def _async_update():
+            try:
+                logger.info(f"开始远程更新 Worker {worker_name} 到 {target_version}")
+                
+                # 构建更新命令：拉取新镜像并重启 agent
+                docker_user = getattr(django_settings, 'DOCKER_USER', 'yyhuni')
+                update_cmd = f'''
+                    docker pull {docker_user}/xingrin-agent:{target_version} && \
+                    docker stop xingrin-agent 2>/dev/null || true && \
+                    docker rm xingrin-agent 2>/dev/null || true && \
+                    docker run -d --pull=always \
+                        --name xingrin-agent \
+                        --restart always \
+                        -e HEARTBEAT_API_URL="https://{django_settings.PUBLIC_HOST}:{getattr(django_settings, 'PUBLIC_PORT', '8083')}" \
+                        -e WORKER_ID="{worker_id}" \
+                        -e IMAGE_TAG="{target_version}" \
+                        -v /proc:/host/proc:ro \
+                        {docker_user}/xingrin-agent:{target_version}
+                '''
+                
+                success, message = self.worker_service.execute_remote_command(
+                    ip_address=ip_address,
+                    ssh_port=ssh_port,
+                    username=username,
+                    password=password,
+                    command=update_cmd
+                )
+                
+                if success:
+                    logger.info(f"Worker {worker_name} 远程更新成功")
+                    # 更新成功后，新 agent 心跳会自动把状态改回 online
+                else:
+                    logger.warning(f"Worker {worker_name} 远程更新失败: {message}")
+                    # 更新失败，标记为 outdated
+                    self._set_worker_status(worker_id, 'outdated')
+                    
+            except Exception as e:
+                logger.error(f"Worker {worker_name} 远程更新异常: {e}")
+                self._set_worker_status(worker_id, 'outdated')
+            finally:
+                # 释放锁
+                redis_client.delete(lock_key)
+        
+        # 后台执行，不阻塞心跳响应
+        threading.Thread(target=_async_update, daemon=True).start()
+    
+    def _set_worker_status(self, worker_id: int, status: str):
+        """更新 Worker 状态（用于后台线程）"""
+        try:
+            from apps.engine.models import WorkerNode
+            WorkerNode.objects.filter(id=worker_id).update(status=status)
+        except Exception as e:
+            logger.error(f"更新 Worker {worker_id} 状态失败: {e}")
     
     @action(detail=False, methods=['post'])
     def register(self, request):
@@ -161,9 +307,10 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
         is_local = request.data.get('is_local', True)
         
         if not name:
-            return Response(
-                {'error': '缺少 name 参数'},
-                status=status.HTTP_400_BAD_REQUEST
+            return error_response(
+                code=ErrorCodes.VALIDATION_ERROR,
+                message='Missing name parameter',
+                status_code=status.HTTP_400_BAD_REQUEST
             )
         
         worker, created = self.worker_service.register_worker(
@@ -171,39 +318,13 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
             is_local=is_local
         )
         
-        return Response({
-            'worker_id': worker.id,
-            'name': worker.name,
-            'created': created
-        })
-    
-    def _get_client_ip(self, request) -> str:
-        """获取客户端真实 IP"""
-        x_forwarded_for = request.META.get('HTTP_X_FORWARDED_FOR')
-        if x_forwarded_for:
-            return x_forwarded_for.split(',')[0].strip()
-        return request.META.get('REMOTE_ADDR', '')
-    
-    def _is_local_request(self, client_ip: str) -> bool:
-        """
-        判断是否为本地请求（Docker 网络内部）
-        
-        本地请求特征：
-        - 来自 Docker 网络内部（172.x.x.x）
-        - 来自 localhost（127.0.0.1）
-        """
-        if not client_ip:
-            return True  # 无法获取 IP 时默认为本地
-        
-        # Docker 默认网络段
-        if client_ip.startswith('172.') or client_ip.startswith('10.'):
-            return True
-        
-        # localhost
-        if client_ip in ('127.0.0.1', '::1', 'localhost'):
-            return True
-        
-        return False
+        return success_response(
+            data={
+                'workerId': worker.id,
+                'name': worker.name,
+                'created': created
+            }
+        )
     
     @action(detail=False, methods=['get'])
     def config(self, request):
@@ -211,92 +332,73 @@ class WorkerNodeViewSet(viewsets.ModelViewSet):
         获取任务容器配置（配置中心 API）
         
         Worker 启动时调用此接口获取完整配置，实现配置中心化管理。
-        Worker 只需知道 SERVER_URL，其他配置由此 API 动态返回。
+        Worker 通过 IS_LOCAL 环境变量声明身份，请求时带上 ?is_local=true/false 参数。
         
-        ┌─────────────────────────────────────────────────────────────┐
-        │                    配置分发流程                              │
-        ├─────────────────────────────────────────────────────────────┤
-        │                                                             │
-        │   Worker 启动                                               │
-        │       │                                                     │
-        │       ▼                                                     │
-        │   GET /api/workers/config/                                  │
-        │       │                                                     │
-        │       ▼                                                     │
-        │   ┌─────────────────────┐                                   │
-        │   │ _get_client_ip()    │ ← 获取请求来源 IP                  │
-        │   │ (X-Forwarded-For    │   (支持 Nginx 代理场景)            │
-        │   │  或 REMOTE_ADDR)    │                                   │
-        │   └─────────┬───────────┘                                   │
-        │             │                                               │
-        │             ▼                                               │
-        │   ┌─────────────────────┐                                   │
-        │   │ _is_local_request() │ ← 判断是否为 Docker 网络内部请求   │
-        │   │ 172.x.x.x / 10.x.x.x│   (Docker 默认网段)               │
-        │   │ 127.0.0.1 / ::1     │   (localhost)                     │
-        │   └─────────┬───────────┘                                   │
-        │             │                                               │
-        │     ┌───────┴───────┐                                       │
-        │     ▼               ▼                                       │
-        │  本地 Worker     远程 Worker                                 │
-        │  (Docker内)      (公网访问)                                  │
-        │     │               │                                       │
-        │     ▼               ▼                                       │
-        │  db: postgres    db: PUBLIC_HOST                            │
-        │  redis: redis    redis: PUBLIC_HOST:6379                    │
-        │                                                             │
-        └─────────────────────────────────────────────────────────────┘
+        请求参数:
+            is_local: true/false - Worker 是否为本地节点（Docker 网络内）
         
         返回:
         {
             "db": {"host": "...", "port": "...", ...},
-            "redisUrl": "...",
             "paths": {"results": "...", "logs": "..."}
         }
+        
+        配置逻辑:
+            - 本地 Worker (is_local=true): db_host=postgres
+            - 远程 Worker (is_local=false): db_host=PUBLIC_HOST
         """
         from django.conf import settings
+        import logging
+        logger = logging.getLogger(__name__)
         
-        # 判断请求来源：本地 Worker 还是远程 Worker
-        # 本地 Worker 在 Docker 网络内，可以直接访问 postgres 服务
-        # 远程 Worker 需要通过公网 IP 访问
-        client_ip = self._get_client_ip(request)
-        is_local_worker = self._is_local_request(client_ip)
+        # 从请求参数获取 Worker 身份（由 Worker 自己声明）
+        # 不再依赖 IP 判断，避免不同网络环境下的兼容性问题
+        is_local_param = request.query_params.get('is_local', '').lower()
+        is_local_worker = is_local_param == 'true'
         
         # 根据请求来源返回不同的数据库地址
         db_host = settings.DATABASES['default']['HOST']
         _is_internal_db = db_host in ('postgres', 'localhost', '127.0.0.1')
         
+        logger.info(
+            "Worker 配置请求 - is_local_param: %s, is_local_worker: %s, db_host: %s, is_internal_db: %s",
+            is_local_param, is_local_worker, db_host, _is_internal_db
+        )
+        
         if _is_internal_db:
             # 本地数据库场景
             if is_local_worker:
                 # 本地 Worker：直接用 Docker 内部服务名
                 worker_db_host = 'postgres'
-                worker_redis_url = 'redis://redis:6379/0'
             else:
                 # 远程 Worker：通过公网 IP 访问
-                worker_db_host = settings.PUBLIC_HOST
-                worker_redis_url = f'redis://{settings.PUBLIC_HOST}:6379/0'
+                public_host = settings.PUBLIC_HOST
+                if public_host in ('server', 'localhost', '127.0.0.1'):
+                    logger.warning("远程 Worker 请求配置，但 PUBLIC_HOST=%s 不是有效的公网地址", public_host)
+                worker_db_host = public_host
         else:
             # 远程数据库场景：所有 Worker 都用 DB_HOST
             worker_db_host = db_host
-            worker_redis_url = getattr(settings, 'WORKER_REDIS_URL', 'redis://redis:6379/0')
         
-        return Response({
-            'db': {
-                'host': worker_db_host,
-                'port': str(settings.DATABASES['default']['PORT']),
-                'name': settings.DATABASES['default']['NAME'],
-                'user': settings.DATABASES['default']['USER'],
-                'password': settings.DATABASES['default']['PASSWORD'],
-            },
-            'redisUrl': worker_redis_url,
-            'paths': {
-                'results': getattr(settings, 'CONTAINER_RESULTS_MOUNT', '/app/backend/results'),
-                'logs': getattr(settings, 'CONTAINER_LOGS_MOUNT', '/app/backend/logs'),
-            },
-            'logging': {
-                'level': os.getenv('LOG_LEVEL', 'INFO'),
-                'enableCommandLogging': os.getenv('ENABLE_COMMAND_LOGGING', 'true').lower() == 'true',
-            },
-            'debug': settings.DEBUG
-        })
+        logger.info("返回 Worker 配置 - db_host: %s", worker_db_host)
+        
+        return success_response(
+            data={
+                'db': {
+                    'host': worker_db_host,
+                    'port': str(settings.DATABASES['default']['PORT']),
+                    'name': settings.DATABASES['default']['NAME'],
+                    'user': settings.DATABASES['default']['USER'],
+                    'password': settings.DATABASES['default']['PASSWORD'],
+                },
+                'paths': {
+                    'results': getattr(settings, 'CONTAINER_RESULTS_MOUNT', '/opt/xingrin/results'),
+                    'logs': getattr(settings, 'CONTAINER_LOGS_MOUNT', '/opt/xingrin/logs'),
+                },
+                'logging': {
+                    'level': os.getenv('LOG_LEVEL', 'INFO'),
+                    'enableCommandLogging': os.getenv('ENABLE_COMMAND_LOGGING', 'true').lower() == 'true',
+                },
+                'debug': settings.DEBUG,
+            }
+        )

backend/apps/scan/configs/command_templates.py

@@ -7,7 +7,7 @@
 from django.conf import settings
 
 # ==================== 路径配置 ====================
-SCAN_TOOLS_BASE_PATH = getattr(settings, 'SCAN_TOOLS_BASE_PATH', '/opt/xingrin/tools')
+SCAN_TOOLS_BASE_PATH = getattr(settings, 'SCAN_TOOLS_BASE_PATH', '/usr/local/bin')
 
 # ==================== 子域名发现 ====================
 
@@ -16,7 +16,7 @@ SUBDOMAIN_DISCOVERY_COMMANDS = {
         # 默认使用所有数据源（更全面，略慢），并始终开启递归
         # -all       使用所有数据源
         # -recursive 对支持递归的源启用递归枚举（默认开启）
-        'base': 'subfinder -d {domain} -all -recursive -o {output_file} -silent',
+        'base': "subfinder -d {domain} -all -recursive -o '{output_file}' -silent",
         'optional': {
             'threads': '-t {threads}',              # 控制并发 goroutine 数
         }
@@ -25,31 +25,31 @@ SUBDOMAIN_DISCOVERY_COMMANDS = {
     'amass_passive': {
         # 先执行被动枚举，将结果写入 amass 内部数据库，然后从数据库中导出纯域名（names）到 output_file
         # -silent 禁用进度条和其他输出
-        'base': 'amass enum -passive -silent -d {domain} && amass subs -names -d {domain} > {output_file}'
+        'base': "amass enum -passive -silent -d {domain} && amass subs -names -d {domain} > '{output_file}'"
     },
     
     'amass_active': {
         # 先执行主动枚举 + 爆破，将结果写入 amass 内部数据库，然后从数据库中导出纯域名（names）到 output_file
         # -silent 禁用进度条和其他输出
-        'base': 'amass enum -active -silent -d {domain} -brute && amass subs -names -d {domain} > {output_file}'
+        'base': "amass enum -active -silent -d {domain} -brute && amass subs -names -d {domain} > '{output_file}'"
     },
     
     'sublist3r': {
-        'base': 'python3 {scan_tools_base}/Sublist3r/sublist3r.py -d {domain} -o {output_file}',
+        'base': "python3 '/usr/local/share/Sublist3r/sublist3r.py' -d {domain} -o '{output_file}'",
         'optional': {
             'threads': '-t {threads}'
         }
     },
     
     'assetfinder': {
-        'base': 'assetfinder --subs-only {domain} > {output_file}',
+        'base': "assetfinder --subs-only {domain} > '{output_file}'",
     },
     
     # === 主动字典爆破 ===
     'subdomain_bruteforce': {
         # 使用字典对目标域名进行 DNS 爆破
         # -d 目标域名，-w 字典文件，-o 输出文件
-        'base': 'puredns bruteforce {wordlist} {domain} -r /app/backend/resources/resolvers.txt --write {output_file} --quiet',
+        'base': "puredns bruteforce '{wordlist}' {domain} -r /app/backend/resources/resolvers.txt --write '{output_file}' --quiet",
         'optional': {},
     },
     
@@ -57,7 +57,7 @@ SUBDOMAIN_DISCOVERY_COMMANDS = {
     'subdomain_resolve': {
         # 验证子域名是否能解析（存活验证）
         # 输入文件为候选子域列表，输出为存活子域列表
-        'base': 'puredns resolve {input_file} -r /app/backend/resources/resolvers.txt --write {output_file} --wildcard-tests 50 --wildcard-batch 1000000 --quiet',
+        'base': "puredns resolve '{input_file}' -r /app/backend/resources/resolvers.txt --write '{output_file}' --wildcard-tests 50 --wildcard-batch 1000000 --quiet",
         'optional': {},
     },
     
@@ -65,7 +65,7 @@ SUBDOMAIN_DISCOVERY_COMMANDS = {
     'subdomain_permutation_resolve': {
         # 流式管道：dnsgen 生成变异域名 | puredns resolve 验证存活
         # 不落盘中间文件，避免内存爆炸；不做通配符过滤
-        'base': 'cat {input_file} | dnsgen - | puredns resolve -r /app/backend/resources/resolvers.txt --write {output_file} --wildcard-tests 50 --wildcard-batch 1000000 --quiet',
+        'base': "cat '{input_file}' | dnsgen - | puredns resolve -r /app/backend/resources/resolvers.txt --write '{output_file}' --wildcard-tests 50 --wildcard-batch 1000000 --quiet",
         'optional': {},
     },
 }
@@ -75,7 +75,7 @@ SUBDOMAIN_DISCOVERY_COMMANDS = {
 
 PORT_SCAN_COMMANDS = {
     'naabu_active': {
-        'base': 'naabu -exclude-cdn -warm-up-time 5 -verify -list {domains_file} -json -silent',
+        'base': "naabu -exclude-cdn -warm-up-time 5 -verify -list '{domains_file}' -json -silent",
         'optional': {
             'threads': '-c {threads}',
             'ports': '-p {ports}',
@@ -85,7 +85,7 @@ PORT_SCAN_COMMANDS = {
     },
     
     'naabu_passive': {
-        'base': 'naabu -list {domains_file} -passive -json -silent'
+        'base': "naabu -list '{domains_file}' -passive -json -silent"
     },
 }
 
@@ -95,7 +95,7 @@ PORT_SCAN_COMMANDS = {
 SITE_SCAN_COMMANDS = {
     'httpx': {
         'base': (
-            'httpx -l {url_file} '
+            "'{scan_tools_base}/httpx' -l '{url_file}' "
             '-status-code -content-type -content-length '
             '-location -title -server -body-preview '
             '-tech-detect -cdn -vhost '
@@ -115,7 +115,7 @@ SITE_SCAN_COMMANDS = {
 
 DIRECTORY_SCAN_COMMANDS = {
     'ffuf': {
-        'base': 'ffuf -u {url}/FUZZ -se -ac -sf -json -w {wordlist}',  
+        'base': "'{scan_tools_base}/ffuf' -u '{url}FUZZ' -se -ac -sf -json -w '{wordlist}'",  
         'optional': {
             'delay': '-p {delay}',
             'threads': '-t {threads}',
@@ -131,13 +131,13 @@ DIRECTORY_SCAN_COMMANDS = {
 
 URL_FETCH_COMMANDS = {
     'waymore': {
-        'base': 'waymore -i {domain_name} -mode U -oU {output_file}',
+        'base': "waymore -i {domain_name} -mode U -oU '{output_file}'",
         'input_type': 'domain_name'
     },
     
     'katana': {
         'base': (
-            'katana -list {sites_file} -o {output_file} '
+            "katana -list '{sites_file}' -o '{output_file}' "
             '-jc '                   # 开启 JavaScript 爬取 + 自动解析 .js 文件里的所有端点（最重要）
             '-xhr '                  # 额外从 JS 中提取 XHR/Fetch 请求的 API 路径（再多挖 10-20% 隐藏接口）
             '-kf all '               # 在每个目录下自动 fuzz 所有已知敏感文件（.env、.git、backup、config、ds_store 等 5000+ 条）
@@ -157,7 +157,7 @@ URL_FETCH_COMMANDS = {
     },
     
     'uro': {
-        'base': 'uro -i {input_file} -o {output_file}',
+        'base': "uro -i '{input_file}' -o '{output_file}'",
         'optional': {
             'whitelist': '-w {whitelist}',      # 只保留指定扩展名的 URL（空格分隔）
             'blacklist': '-b {blacklist}',      # 排除指定扩展名的 URL（空格分隔）
@@ -167,7 +167,7 @@ URL_FETCH_COMMANDS = {
     
     'httpx': {
         'base': (
-            'httpx -l {url_file} '
+            "'{scan_tools_base}/httpx' -l '{url_file}' "
             '-status-code -content-type -content-length '
             '-location -title -server -body-preview '
             '-tech-detect -cdn -vhost '
@@ -187,7 +187,7 @@ VULN_SCAN_COMMANDS = {
         'base': (
             'dalfox --silence --no-color --no-spinner '
             '--skip-bav '
-            'file {endpoints_file} '
+            "file '{endpoints_file}' "
             '--waf-evasion '
             '--format json'
         ),
@@ -205,11 +205,11 @@ VULN_SCAN_COMMANDS = {
     },
     'nuclei': {
         # nuclei 漏洞扫描
-        # -j: JSON 输出
+        # -j: JSON 输出（每行一条完整 JSON）
         # -silent: 静默模式
         # -l: 输入 URL 列表文件
         # -t: 模板目录路径（支持多个仓库，多次 -t 由 template_args 直接拼接）
-        'base': 'nuclei -j -silent -l {endpoints_file} {template_args}',
+        'base': "nuclei -j -silent -l '{endpoints_file}' {template_args}",
         'optional': {
             'concurrency': '-c {concurrency}',           # 并发数（默认 25）
             'rate_limit': '-rl {rate_limit}',            # 每秒请求数限制
@@ -225,12 +225,35 @@ VULN_SCAN_COMMANDS = {
 }
 
 
+# ==================== 指纹识别 ====================
+
+FINGERPRINT_DETECT_COMMANDS = {
+    'xingfinger': {
+        # 流式输出模式（不使用 -o，输出到 stdout）
+        # -l: URL 列表文件输入
+        # -s: 静默模式，只输出命中结果
+        # --json: JSON 格式输出（每行一条）
+        'base': "xingfinger -l '{urls_file}' -s --json",
+        'optional': {
+            # 自定义指纹库路径
+            'ehole': '--ehole {ehole}',
+            'goby': '--goby {goby}',
+            'wappalyzer': '--wappalyzer {wappalyzer}',
+            'fingers': '--fingers {fingers}',
+            'fingerprinthub': '--fingerprint {fingerprinthub}',
+            'arl': '--arl {arl}',
+        }
+    },
+}
+
+
 # ==================== 工具映射 ====================
 
 COMMAND_TEMPLATES = {
     'subdomain_discovery': SUBDOMAIN_DISCOVERY_COMMANDS,
     'port_scan': PORT_SCAN_COMMANDS,
     'site_scan': SITE_SCAN_COMMANDS,
+    'fingerprint_detect': FINGERPRINT_DETECT_COMMANDS,
     'directory_scan': DIRECTORY_SCAN_COMMANDS,
     'url_fetch': URL_FETCH_COMMANDS,
     'vuln_scan': VULN_SCAN_COMMANDS,
@@ -242,7 +265,7 @@ COMMAND_TEMPLATES = {
 EXECUTION_STAGES = [
     {
         'mode': 'sequential',
-        'flows': ['subdomain_discovery', 'port_scan', 'site_scan']
+        'flows': ['subdomain_discovery', 'port_scan', 'site_scan', 'fingerprint_detect']
     },
     {
         'mode': 'parallel',

backend/apps/scan/configs/engine_config_example.yaml

@@ -1,224 +1,169 @@
 # 引擎配置
 #
-# ==================== 参数命名规范 ====================
-# 所有参数统一用中划线，如 rate-limit, request-timeout, wordlist-name
-# - 贴近 CLI 参数风格，用户更直观
-# - 系统会自动转换为下划线供代码使用
-#
-# ==================== 必需参数 ====================
-# - enabled: 是否启用工具（true/false）
-# - timeout: 超时时间（秒），工具执行超过此时间会被强制终止
-#
-# 使用方式：
-# - 在前端创建扫描引擎时，将此配置保存到数据库
-# - 执行扫描时，从数据库读取配置并传递给 Flow
-# - 取消注释可选参数即可启用
+# 参数命名：统一用中划线（如 rate-limit），系统自动转换为下划线
+# 必需参数：enabled（是否启用）
+# 可选参数：timeout（超时秒数，默认 auto 自动计算）
 
 # ==================== 子域名发现 ====================
 # 
-# 流程说明：
-#   Stage 1: 被动收集（并行） - 必选，至少启用一个工具
-#   Stage 2: 字典爆破（可选） - 使用字典暴力枚举子域名
-#   Stage 3: 变异生成 + 验证（可选） - 基于已发现域名生成变异，流式验证存活
-#   Stage 4: DNS 存活验证（可选） - 验证所有候选域名是否能解析
-#
-# 灵活组合：可以关闭 2/3/4 中的任意阶段，最终结果会根据实际执行的阶段动态决定
+# Stage 1: 被动收集（并行） - 必选，至少启用一个工具
+# Stage 2: 字典爆破（可选） - 使用字典暴力枚举子域名
+# Stage 3: 变异生成 + 验证（可选） - 基于已发现域名生成变异，流式验证存活
+# Stage 4: DNS 存活验证（可选） - 验证所有候选域名是否能解析
 #
 subdomain_discovery:
   # === Stage 1: 被动收集工具（并行执行）===
   passive_tools:
     subfinder:
       enabled: true
-      timeout: 7200      # 2小时
-      # threads: 10     # 可选，并发 goroutine 数
+      timeout: 3600      # 1小时
+      # threads: 10      # 并发 goroutine 数
       
     amass_passive:
       enabled: true
-      timeout: 7200      # 2小时
+      timeout: 3600
       
     amass_active:
       enabled: true      # 主动枚举 + 爆破
-      timeout: 7200
+      timeout: 3600
       
     sublist3r:
       enabled: true
-      timeout: 7200
-      # threads: 50     # 可选，线程数
+      timeout: 3600
+      # threads: 50      # 线程数
     
     assetfinder:
       enabled: true
-      timeout: 7200
+      timeout: 3600
 
   # === Stage 2: 主动字典爆破（可选）===
   bruteforce:
-    enabled: false                       # 是否启用字典爆破
+    enabled: false
     subdomain_bruteforce:
-      timeout: auto                      # 自动根据字典行数计算（后续代码中按行数 * 3 秒实现）
-      wordlist-name: subdomains-top1million-110000.txt    # 字典名称，对应「字典管理」中的 Wordlist.name
+      # timeout: auto                    # 自动根据字典行数计算
+      wordlist-name: subdomains-top1million-110000.txt    # 对应「字典管理」中的 Wordlist.name
 
-  # === Stage 3: 变异生成 + 存活验证（可选，流式管道避免 OOM）===
+  # === Stage 3: 变异生成 + 存活验证（可选）===
   permutation:
-    enabled: true                        # 是否启用变异生成
+    enabled: true
     subdomain_permutation_resolve:
-      timeout: 7200                      # 2小时（变异量大时需要更长时间）
+      timeout: 7200
 
   # === Stage 4: DNS 存活验证（可选）===
   resolve:
-    enabled: true                        # 是否启用存活验证
+    enabled: true
     subdomain_resolve:
-      timeout: auto                      # 自动根据候选子域数量计算（在 Flow 中按行数 * 3 秒实现）
-      
+      timeout: auto    # 自动根据候选子域数量计算
 
 # ==================== 端口扫描 ====================
 port_scan:
   tools:
     naabu_active:
       enabled: true
-      timeout: auto     # 自动计算（根据：目标数 × 端口数 × 0.5秒）
-                        # 例如：100个域名 × 100个端口 × 0.5 = 5000秒
-                        #       10个域名 × 1000个端口 × 0.5 = 5000秒
-                        # 超时范围：60秒 ~ 2天（172800秒）
-                        # 或者手动指定：timeout: 3600
-      threads: 200        # 可选，并发连接数（默认 5）
-      # ports: 1-65535    # 可选，扫描端口范围（默认 1-65535）
-      top-ports: 100    # 可选，Scan for nmap top 100 ports（影响 timeout 计算）
-      rate: 10          # 可选，扫描速率（默认 10）
+      # timeout: auto    # 自动计算（目标数 × 端口数 × 0.5秒），范围 60秒 ~ 2天
+      threads: 200       # 并发连接数（默认 5）
+      # ports: 1-65535   # 扫描端口范围（默认 1-65535）
+      top-ports: 100     # 扫描 nmap top 100 端口
+      rate: 10           # 扫描速率（默认 10）
       
     naabu_passive:
       enabled: true
-      timeout: auto     # 自动计算（被动扫描通常较快，端口数默认为 100）
-      # 被动扫描，使用被动数据源，无需额外配置
+      # timeout: auto    # 被动扫描通常较快
 
 # ==================== 站点扫描 ====================
 site_scan:
   tools:
     httpx:
       enabled: true
-      timeout: auto         # 自动计算（根据URL数量，每个URL 1秒）
-                            # 或者手动指定：timeout: 3600
-      # threads: 50         # 可选，并发线程数（httpx 默认 50）
-      # rate-limit: 150     # 可选，每秒发送的请求数量（httpx 默认 150）
-      # request-timeout: 10  # 可选，单个请求的超时时间（httpx 默认 10）秒
-      # retries: 2          # 可选，请求失败重试次数
+      # timeout: auto        # 自动计算（每个 URL 约 1 秒）
+      # threads: 50          # 并发线程数（默认 50）
+      # rate-limit: 150      # 每秒请求数（默认 150）
+      # request-timeout: 10  # 单个请求超时秒数（默认 10）
+      # retries: 2           # 请求失败重试次数
+
+# ==================== 指纹识别 ====================
+# 在 site_scan 后串行执行，识别 WebSite 的技术栈
+fingerprint_detect:
+  tools:
+    xingfinger:
+      enabled: true
+      fingerprint-libs: [ehole, goby, wappalyzer, fingers, fingerprinthub, arl]  # 全部指纹库
 
 # ==================== 目录扫描 ====================
 directory_scan:
   tools:
     ffuf:
       enabled: true
-      timeout: auto                            # 自动计算超时时间（根据字典行数）
-                                               # 计算公式：字典行数 × 0.02秒/词
-                                               # 超时范围：60秒 ~ 7200秒（2小时）
-                                               # 也可以手动指定固定超时（如 300）
-      wordlist-name: dir_default.txt          # 字典名称（必需），对应「字典管理」中唯一的 Wordlist.name
-                                               # 安装时会自动初始化名为 dir_default.txt 的默认目录字典
-                                               # ffuf 会逐行读取字典文件，将每行作为 FUZZ 关键字的替换值
-      delay: 0.1-2.0                         # Seconds of delay between requests, or a range of random delay
-                                               # For example "0.1" or "0.1-2.0"
-      threads: 10                            # Number of concurrent threads (default: 40)
-      request-timeout: 10                    # HTTP request timeout in seconds (default: 10)
-      match-codes: 200,201,301,302,401,403   # Match HTTP status codes, comma separated
-      # rate: 0                                # Rate of requests per second (default: 0)
+      # timeout: auto                     # 自动计算（字典行数 × 0.02秒），范围 60秒 ~ 2小时
+      max-workers: 5                      # 并发扫描站点数（默认 5）
+      wordlist-name: dir_default.txt      # 对应「字典管理」中的 Wordlist.name
+      delay: 0.1-2.0                      # 请求间隔，支持范围随机（如 "0.1-2.0"）
+      threads: 10                         # 并发线程数（默认 40）
+      request-timeout: 10                 # HTTP 请求超时秒数（默认 10）
+      match-codes: 200,201,301,302,401,403  # 匹配的 HTTP 状态码
+      # rate: 0                           # 每秒请求数（默认 0 不限制）
 
 # ==================== URL 获取 ====================
 url_fetch:
   tools:
     waymore:
       enabled: true
-      timeout: 3600     # 工具级别总超时：固定 3600 秒（按域名 target_name 输入）
-                        # 如果目标较大或希望更快/更慢，可根据需要手动调整秒数
-                        # 输入类型：domain_name（域名级别，自动去重同域名站点）
+      timeout: 3600      # 固定 1 小时（按域名输入）
     
     katana:
       enabled: true
-      timeout: auto         # 工具级别总超时：自动计算（根据站点数量）
-                            # 或手动指定：timeout: 300
-      
-      # ========== 核心功能参数（已在命令中固定开启） ==========
-      # -jc: JavaScript 爬取 + 自动解析 .js 文件里的所有端点（最重要）
-      # -xhr: 从 JS 中提取 XHR/Fetch 请求的 API 路径（再多挖 10-20% 隐藏接口）
-      # -kf all: 自动 fuzz 所有已知敏感文件（.env、.git、backup、config 等 5000+ 条）
-      # -fs rdn: 智能过滤重复+噪声路径（分页、?id=1/2/3 全干掉，输出极干净）
-      
-      # ========== 可选参数（推荐配置） ==========
-      depth: 5              # 爬取最大深度（平衡深度与时间，默认 3，推荐 5）
-      threads: 10           # 全局并发数（极低并发最像真人，推荐 10）
-      rate-limit: 30        # 全局硬限速：每秒最多 30 个请求（WAF 几乎不报警）
-      random-delay: 1       # 每次请求之间随机延迟 0.5~1.5 秒（再加一层人性化）
-      retry: 2              # 失败请求自动重试 2 次（网络抖动不丢包）
-      request-timeout: 12   # 单请求超时 12 秒（防卡死，katana 参数名是 -timeout）
-      
-      # 输入类型：url（站点级别，每个站点单独爬取）
+      # timeout: auto    # 自动计算（根据站点数量）
+      depth: 5           # 爬取最大深度（默认 3）
+      threads: 10        # 全局并发数
+      rate-limit: 30     # 每秒最多请求数
+      random-delay: 1    # 请求间随机延迟秒数
+      retry: 2           # 失败重试次数
+      request-timeout: 12  # 单请求超时秒数
     
     uro:
       enabled: true
-      timeout: auto         # 自动计算（根据 URL 数量，每 100 个约 1 秒）
-                            # 范围：30 秒 ~ 300 秒
-                            # 或手动指定：timeout: 60
-      
-      # ========== 可选参数 ==========
-      # whitelist:          # 只保留指定扩展名的 URL（如：php,asp,jsp）
+      # timeout: auto    # 自动计算（每 100 个 URL 约 1 秒），范围 30 ~ 300 秒
+      # whitelist:       # 只保留指定扩展名
       #   - php
       #   - asp
-      # blacklist:            # 排除指定扩展名的 URL（静态资源）
+      # blacklist:       # 排除指定扩展名（静态资源）
       #   - jpg
-      #   - jpeg
       #   - png
-      #   - gif
-      #   - svg
-      #   - ico
       #   - css
-      #   - woff
-      #   - woff2
-      #   - ttf
-      #   - eot
-      #   - mp4
-      #   - mp3
-      #   - pdf
-      # filters:             # 额外的过滤规则，参考 uro 文档
-      #   - hasparams        # 只保留有参数的 URL
-      #   - hasext           # 只保留有扩展名的 URL
-      #   - vuln             # 只保留可能有漏洞的 URL
-      
-      # 用途：清理合并后的 URL 列表，去除冗余和无效 URL
-      # 输入类型：merged_file（合并后的 URL 文件）
-      # 输出：清理后的 URL 列表
+      # filters:         # 额外过滤规则
+      #   - hasparams    # 只保留有参数的 URL
+      #   - vuln         # 只保留可能有漏洞的 URL
     
     httpx:
       enabled: true
-      timeout: auto         # 自动计算（根据 URL 数量，每个 URL 1 秒）
-                            # 或手动指定：timeout: 600
-      # threads: 50         # 可选，并发线程数（httpx 默认 50）
-      # rate-limit: 150     # 可选，每秒发送的请求数量（httpx 默认 150）
-      # request-timeout: 10  # 可选，单个请求的超时时间（httpx 默认 10）秒
-      # retries: 2          # 可选，请求失败重试次数
-      
-      # 用途：判断 URL 存活，过滤无效 URL
-      # 输入类型：url_file（URL 列表文件）
-      # 输出：存活的 URL 及其响应信息（status, title, server, tech 等）
+      # timeout: auto        # 自动计算（每个 URL 约 1 秒）
+      # threads: 50          # 并发线程数（默认 50）
+      # rate-limit: 150      # 每秒请求数（默认 150）
+      # request-timeout: 10  # 单个请求超时秒数（默认 10）
+      # retries: 2           # 请求失败重试次数
 
 # ==================== 漏洞扫描 ====================
 vuln_scan:
   tools:
     dalfox_xss:
       enabled: true
-      timeout: auto          # 自动计算（根据 endpoints 行数 × 100 秒），或手动指定秒数如 timeout: 600
-      request-timeout: 10    # Dalfox 单个请求的超时时间，对应命令行 --timeout
+      # timeout: auto        # 自动计算（endpoints 行数 × 100 秒）
+      request-timeout: 10  # 单个请求超时秒数
       only-poc: r            # 只输出 POC 结果（r: 反射型）
-      ignore-return: "302,404,403"  # 忽略这些返回码
-      # blind-xss-server: xxx  # 可选：盲打 XSS 回连服务地址，需要时再开启
-      delay: 100             # Dalfox 扫描内部延迟参数
-      worker: 10             # Dalfox worker 数量
-      user-agent: "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"  # 默认 UA，可根据需要修改
+      ignore-return: "302,404,403"  # 忽略的返回码
+      delay: 50            # 请求间隔（毫秒）
+      worker: 30             # worker 数量
+      user-agent: "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
+      # blind-xss-server: xxx  # 盲打 XSS 回连服务地址
 
     nuclei:
       enabled: true
-      timeout: auto                        # 自动计算（根据 endpoints 行数），或手动指定秒数
-      template-repo-names:                 # 模板仓库列表（必填，数组写法），对应「Nuclei 模板」中的仓库名
-        - nuclei-templates                 # Worker 会自动同步到与 Server 一致的 commit 版本
-        # - nuclei-custom                  # 可追加自定义仓库，按顺序依次 -t 传入
-      concurrency: 25                      # 并发数（默认 25）
-      rate-limit: 150                      # 每秒请求数限制（默认 150）
-      request-timeout: 5                   # 单个请求超时秒数（默认 5）
-      severity: medium,high,critical       # 只扫描中高危，降低噪音（逗号分隔）
-      # tags: cve,rce                      # 可选：只使用指定标签的模板
+      # timeout: auto        # 自动计算（根据 endpoints 行数）
+      template-repo-names:   # 模板仓库列表，对应「Nuclei 模板」中的仓库名
+        - nuclei-templates
+        # - nuclei-custom    # 可追加自定义仓库
+      concurrency: 25        # 并发数（默认 25）
+      rate-limit: 150        # 每秒请求数限制（默认 150）
+      request-timeout: 5     # 单个请求超时秒数（默认 5）
+      severity: medium,high,critical  # 只扫描中高危
+      # tags: cve,rce        # 只使用指定标签的模板

backend/apps/scan/flows/__init__.py

@@ -5,8 +5,10 @@
 
 from .initiate_scan_flow import initiate_scan_flow
 from .subdomain_discovery_flow import subdomain_discovery_flow
+from .fingerprint_detect_flow import fingerprint_detect_flow
 
 __all__ = [
     'initiate_scan_flow',
     'subdomain_discovery_flow',
+    'fingerprint_detect_flow',
 ]

backend/apps/scan/flows/directory_scan_flow.py

@@ -5,7 +5,7 @@
 
 架构：
 - Flow 负责编排多个原子 Task
-- 支持串行执行扫描工具（流式处理）
+- 支持并发执行扫描工具（使用 ThreadPoolTaskRunner）
 - 每个 Task 可独立重试
 - 配置由 YAML 解析
 """
@@ -14,11 +14,15 @@
 from apps.common.prefect_django_setup import setup_django_for_prefect
 
 from prefect import flow
+from prefect.task_runners import ThreadPoolTaskRunner
 
+import hashlib
 import logging
 import os
 import subprocess
+from datetime import datetime
 from pathlib import Path
+from typing import List, Tuple
 
 from apps.scan.tasks.directory_scan import (
     export_sites_task,
@@ -33,6 +37,9 @@ from apps.scan.utils import config_parser, build_scan_command, ensure_wordlist_l
 
 logger = logging.getLogger(__name__)
 
+# 默认最大并发数
+DEFAULT_MAX_WORKERS = 5
+
 
 def calculate_directory_scan_timeout(
     tool_config: dict,
@@ -112,36 +119,37 @@ def calculate_directory_scan_timeout(
         return min_timeout
 
 
-def _setup_directory_scan_directory(scan_workspace_dir: str) -> Path:
+def _get_max_workers(tool_config: dict, default: int = DEFAULT_MAX_WORKERS) -> int:
     """
-    创建并验证目录扫描工作目录
+    从单个工具配置中获取 max_workers 参数
     
     Args:
-        scan_workspace_dir: 扫描工作空间目录
+        tool_config: 单个工具的配置字典，如 {'max_workers': 10, 'threads': 5, ...}
+        default: 默认值，默认为 5
         
     Returns:
-        Path: 目录扫描目录路径
-        
-    Raises:
-        RuntimeError: 目录创建或验证失败
+        int: max_workers 值
     """
-    directory_scan_dir = Path(scan_workspace_dir) / 'directory_scan'
-    directory_scan_dir.mkdir(parents=True, exist_ok=True)
+    if not isinstance(tool_config, dict):
+        return default
     
-    if not directory_scan_dir.is_dir():
-        raise RuntimeError(f"目录扫描目录创建失败: {directory_scan_dir}")
-    if not os.access(directory_scan_dir, os.W_OK):
-        raise RuntimeError(f"目录扫描目录不可写: {directory_scan_dir}")
-    
-    return directory_scan_dir
+    # 支持 max_workers 和 max-workers（YAML 中划线会被转换）
+    max_workers = tool_config.get('max_workers') or tool_config.get('max-workers')
+    if max_workers is not None and isinstance(max_workers, int) and max_workers > 0:
+        return max_workers
+    return default
 
 
-def _export_site_urls(target_id: int, directory_scan_dir: Path) -> tuple[str, int]:
+
+
+
+def _export_site_urls(target_id: int, target_name: str, directory_scan_dir: Path) -> tuple[str, int]:
     """
-    导出目标下的所有站点 URL 到文件
+    导出目标下的所有站点 URL 到文件（支持懒加载）
     
     Args:
         target_id: 目标 ID
+        target_name: 目标名称（用于懒加载创建默认站点）
         directory_scan_dir: 目录扫描目录
         
     Returns:
@@ -185,7 +193,7 @@ def _run_scans_sequentially(
     target_name: str
 ) -> tuple[int, int, list]:
     """
-    串行执行目录扫描任务（支持多工具）
+    串行执行目录扫描任务（支持多工具）- 已废弃，保留用于兼容
     
     Args:
         enabled_tools: 启用的工具配置字典
@@ -333,6 +341,198 @@ def _run_scans_sequentially(
     return total_directories, processed_count, failed_sites
 
 
+def _generate_log_filename(tool_name: str, site_url: str, directory_scan_dir: Path) -> Path:
+    """
+    生成唯一的日志文件名
+    
+    使用 URL 的 hash 确保并发时不会冲突
+    
+    Args:
+        tool_name: 工具名称
+        site_url: 站点 URL
+        directory_scan_dir: 目录扫描目录
+        
+    Returns:
+        Path: 日志文件路径
+    """
+    url_hash = hashlib.md5(site_url.encode()).hexdigest()[:8]
+    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S_%f')
+    return directory_scan_dir / f"{tool_name}_{url_hash}_{timestamp}.log"
+
+
+def _run_scans_concurrently(
+    enabled_tools: dict,
+    sites_file: str,
+    directory_scan_dir: Path,
+    scan_id: int,
+    target_id: int,
+    site_count: int,
+    target_name: str
+) -> Tuple[int, int, List[str]]:
+    """
+    并发执行目录扫描任务（使用 ThreadPoolTaskRunner）
+    
+    Args:
+        enabled_tools: 启用的工具配置字典
+        sites_file: 站点文件路径
+        directory_scan_dir: 目录扫描目录
+        scan_id: 扫描任务 ID
+        target_id: 目标 ID
+        site_count: 站点数量
+        target_name: 目标名称（用于错误日志）
+        
+    Returns:
+        tuple: (total_directories, processed_sites, failed_sites)
+    """
+    # 读取站点列表
+    sites: List[str] = []
+    with open(sites_file, 'r', encoding='utf-8') as f:
+        for line in f:
+            site_url = line.strip()
+            if site_url:
+                sites.append(site_url)
+    
+    if not sites:
+        logger.warning("站点列表为空")
+        return 0, 0, []
+    
+    logger.info(
+        "准备并发扫描 %d 个站点，使用工具: %s",
+        len(sites), ', '.join(enabled_tools.keys())
+    )
+    
+    total_directories = 0
+    processed_sites_count = 0
+    failed_sites: List[str] = []
+    
+    # 遍历每个工具
+    for tool_name, tool_config in enabled_tools.items():
+        # 每个工具独立获取 max_workers 配置
+        max_workers = _get_max_workers(tool_config)
+        
+        logger.info("="*60)
+        logger.info("使用工具: %s (并发模式, max_workers=%d)", tool_name, max_workers)
+        logger.info("="*60)
+
+        # 如果配置了 wordlist_name，则先确保本地存在对应的字典文件（含 hash 校验）
+        wordlist_name = tool_config.get('wordlist_name')
+        if wordlist_name:
+            try:
+                local_wordlist_path = ensure_wordlist_local(wordlist_name)
+                tool_config['wordlist'] = local_wordlist_path
+            except Exception as exc:
+                logger.error("为工具 %s 准备字典失败: %s", tool_name, exc)
+                # 当前工具无法执行，将所有站点视为失败，继续下一个工具
+                failed_sites.extend(sites)
+                continue
+        
+        # 计算超时时间（所有站点共用）
+        site_timeout = tool_config.get('timeout', 300)
+        if site_timeout == 'auto':
+            site_timeout = calculate_directory_scan_timeout(tool_config)
+            logger.info(f"✓ 工具 {tool_name} 动态计算 timeout: {site_timeout}秒")
+        
+        # 准备所有站点的扫描参数
+        scan_params_list = []
+        for idx, site_url in enumerate(sites, 1):
+            try:
+                command = build_scan_command(
+                    tool_name=tool_name,
+                    scan_type='directory_scan',
+                    command_params={'url': site_url},
+                    tool_config=tool_config
+                )
+                log_file = _generate_log_filename(tool_name, site_url, directory_scan_dir)
+                scan_params_list.append({
+                    'idx': idx,
+                    'site_url': site_url,
+                    'command': command,
+                    'log_file': str(log_file),
+                    'timeout': site_timeout
+                })
+            except Exception as e:
+                logger.error(
+                    "✗ [%d/%d] 构建 %s 命令失败: %s - 站点: %s",
+                    idx, len(sites), tool_name, e, site_url
+                )
+                failed_sites.append(site_url)
+        
+        if not scan_params_list:
+            logger.warning("没有有效的扫描任务")
+            continue
+        
+        # ============================================================
+        # 分批执行策略：控制实际并发的 ffuf 进程数
+        # ============================================================
+        total_tasks = len(scan_params_list)
+        logger.info("开始分批执行 %d 个扫描任务（每批 %d 个）...", total_tasks, max_workers)
+        
+        batch_num = 0
+        for batch_start in range(0, total_tasks, max_workers):
+            batch_end = min(batch_start + max_workers, total_tasks)
+            batch_params = scan_params_list[batch_start:batch_end]
+            batch_num += 1
+            
+            logger.info("执行第 %d 批任务（%d-%d/%d）...", batch_num, batch_start + 1, batch_end, total_tasks)
+            
+            # 提交当前批次的任务（非阻塞，立即返回 future）
+            futures = []
+            for params in batch_params:
+                future = run_and_stream_save_directories_task.submit(
+                    cmd=params['command'],
+                    tool_name=tool_name,
+                    scan_id=scan_id,
+                    target_id=target_id,
+                    site_url=params['site_url'],
+                    cwd=str(directory_scan_dir),
+                    shell=True,
+                    batch_size=1000,
+                    timeout=params['timeout'],
+                    log_file=params['log_file']
+                )
+                futures.append((params['idx'], params['site_url'], future))
+            
+            # 等待当前批次所有任务完成（阻塞，确保本批完成后再启动下一批）
+            for idx, site_url, future in futures:
+                try:
+                    result = future.result()  # 阻塞等待单个任务完成
+                    directories_found = result.get('created_directories', 0)
+                    total_directories += directories_found
+                    processed_sites_count += 1
+                    
+                    logger.info(
+                        "✓ [%d/%d] 站点扫描完成: %s - 发现 %d 个目录",
+                        idx, len(sites), site_url, directories_found
+                    )
+                    
+                except Exception as exc:
+                    failed_sites.append(site_url)
+                    if 'timeout' in str(exc).lower() or isinstance(exc, subprocess.TimeoutExpired):
+                        logger.warning(
+                            "⚠️ [%d/%d] 站点扫描超时: %s - 错误: %s",
+                            idx, len(sites), site_url, exc
+                        )
+                    else:
+                        logger.error(
+                            "✗ [%d/%d] 站点扫描失败: %s - 错误: %s",
+                            idx, len(sites), site_url, exc
+                        )
+    
+    # 输出汇总信息
+    if failed_sites:
+        logger.warning(
+            "部分站点扫描失败: %d/%d",
+            len(failed_sites), len(sites)
+        )
+    
+    logger.info(
+        "✓ 并发目录扫描执行完成 - 成功: %d/%d, 失败: %d, 总目录数: %d",
+        processed_sites_count, len(sites), len(failed_sites), total_directories
+    )
+    
+    return total_directories, processed_sites_count, failed_sites
+
+
 @flow(
     name="directory_scan", 
     log_prints=True,
@@ -359,7 +559,7 @@ def directory_scan_flow(
         Step 0: 创建工作目录
         Step 1: 导出站点 URL 列表到文件（供扫描工具使用）
         Step 2: 验证工具配置
-        Step 3: 串行执行扫描工具并实时保存结果
+        Step 3: 并发执行扫描工具并实时保存结果（使用 ThreadPoolTaskRunner）
     
     ffuf 输出字段：
         - url: 发现的目录/文件 URL
@@ -418,10 +618,11 @@ def directory_scan_flow(
             raise ValueError("enabled_tools 不能为空")
         
         # Step 0: 创建工作目录
-        directory_scan_dir = _setup_directory_scan_directory(scan_workspace_dir)
+        from apps.scan.utils import setup_scan_directory
+        directory_scan_dir = setup_scan_directory(scan_workspace_dir, 'directory_scan')
         
-        # Step 1: 导出站点 URL
-        sites_file, site_count = _export_site_urls(target_id, directory_scan_dir)
+        # Step 1: 导出站点 URL（支持懒加载）
+        sites_file, site_count = _export_site_urls(target_id, target_name, directory_scan_dir)
         
         if site_count == 0:
             logger.warning("目标下没有站点，跳过目录扫描")
@@ -440,14 +641,15 @@ def directory_scan_flow(
         
         # Step 2: 工具配置信息
         logger.info("Step 2: 工具配置信息")
-        logger.info(
-            "✓ 启用工具: %s",
-            ', '.join(enabled_tools.keys())
-        )
+        tool_info = []
+        for tool_name, tool_config in enabled_tools.items():
+            mw = _get_max_workers(tool_config)
+            tool_info.append(f"{tool_name}(max_workers={mw})")
+        logger.info("✓ 启用工具: %s", ', '.join(tool_info))
         
-        # Step 3: 串行执行扫描工具并实时保存结果
-        logger.info("Step 3: 串行执行扫描工具并实时保存结果")
-        total_directories, processed_sites, failed_sites = _run_scans_sequentially(
+        # Step 3: 并发执行扫描工具并实时保存结果
+        logger.info("Step 3: 并发执行扫描工具并实时保存结果")
+        total_directories, processed_sites, failed_sites = _run_scans_concurrently(
             enabled_tools=enabled_tools,
             sites_file=sites_file,
             directory_scan_dir=directory_scan_dir,

backend/apps/scan/flows/fingerprint_detect_flow.py

@@ -0,0 +1,376 @@
+"""
+指纹识别 Flow
+
+负责编排指纹识别的完整流程
+
+架构：
+- Flow 负责编排多个原子 Task
+- 在 site_scan 后串行执行
+- 使用 xingfinger 工具识别技术栈
+- 流式处理输出，批量更新数据库
+"""
+
+# Django 环境初始化（导入即生效）
+from apps.common.prefect_django_setup import setup_django_for_prefect
+
+import logging
+import os
+from datetime import datetime
+from pathlib import Path
+
+from prefect import flow
+
+from apps.scan.handlers.scan_flow_handlers import (
+    on_scan_flow_running,
+    on_scan_flow_completed,
+    on_scan_flow_failed,
+)
+from apps.scan.tasks.fingerprint_detect import (
+    export_urls_for_fingerprint_task,
+    run_xingfinger_and_stream_update_tech_task,
+)
+from apps.scan.utils import build_scan_command
+from apps.scan.utils.fingerprint_helpers import get_fingerprint_paths
+
+logger = logging.getLogger(__name__)
+
+
+def calculate_fingerprint_detect_timeout(
+    url_count: int,
+    base_per_url: float = 5.0,
+    min_timeout: int = 300
+) -> int:
+    """
+    根据 URL 数量计算超时时间
+    
+    公式：超时时间 = URL 数量 × 每 URL 基础时间
+    最小值：300秒
+    无上限
+    
+    Args:
+        url_count: URL 数量
+        base_per_url: 每 URL 基础时间（秒），默认 5秒
+        min_timeout: 最小超时时间（秒），默认 300秒
+        
+    Returns:
+        int: 计算出的超时时间（秒）
+        
+    """
+    timeout = int(url_count * base_per_url)
+    return max(min_timeout, timeout)
+
+
+
+
+
+def _export_urls(
+    target_id: int,
+    fingerprint_dir: Path,
+    source: str = 'website'
+) -> tuple[str, int]:
+    """
+    导出 URL 到文件
+    
+    Args:
+        target_id: 目标 ID
+        fingerprint_dir: 指纹识别目录
+        source: 数据源类型
+        
+    Returns:
+        tuple: (urls_file, total_count)
+    """
+    logger.info("Step 1: 导出 URL 列表 (source=%s)", source)
+    
+    urls_file = str(fingerprint_dir / 'urls.txt')
+    export_result = export_urls_for_fingerprint_task(
+        target_id=target_id,
+        output_file=urls_file,
+        source=source,
+        batch_size=1000
+    )
+    
+    total_count = export_result['total_count']
+    
+    logger.info(
+        "✓ URL 导出完成 - 文件: %s, 数量: %d",
+        export_result['output_file'],
+        total_count
+    )
+    
+    return export_result['output_file'], total_count
+
+
+def _run_fingerprint_detect(
+    enabled_tools: dict,
+    urls_file: str,
+    url_count: int,
+    fingerprint_dir: Path,
+    scan_id: int,
+    target_id: int,
+    source: str
+) -> tuple[dict, list]:
+    """
+    执行指纹识别任务
+    
+    Args:
+        enabled_tools: 已启用的工具配置字典
+        urls_file: URL 文件路径
+        url_count: URL 总数
+        fingerprint_dir: 指纹识别目录
+        scan_id: 扫描任务 ID
+        target_id: 目标 ID
+        source: 数据源类型
+        
+    Returns:
+        tuple: (tool_stats, failed_tools)
+    """
+    tool_stats = {}
+    failed_tools = []
+    
+    for tool_name, tool_config in enabled_tools.items():
+        # 1. 获取指纹库路径
+        lib_names = tool_config.get('fingerprint_libs', ['ehole'])
+        fingerprint_paths = get_fingerprint_paths(lib_names)
+        
+        if not fingerprint_paths:
+            reason = f"没有可用的指纹库: {lib_names}"
+            logger.warning(reason)
+            failed_tools.append({'tool': tool_name, 'reason': reason})
+            continue
+        
+        # 2. 将指纹库路径合并到 tool_config（用于命令构建）
+        tool_config_with_paths = {**tool_config, **fingerprint_paths}
+        
+        # 3. 构建命令
+        try:
+            command = build_scan_command(
+                tool_name=tool_name,
+                scan_type='fingerprint_detect',
+                command_params={
+                    'urls_file': urls_file
+                },
+                tool_config=tool_config_with_paths
+            )
+        except Exception as e:
+            reason = f"命令构建失败: {str(e)}"
+            logger.error("构建 %s 命令失败: %s", tool_name, e)
+            failed_tools.append({'tool': tool_name, 'reason': reason})
+            continue
+        
+        # 4. 计算超时时间
+        timeout = calculate_fingerprint_detect_timeout(url_count)
+        
+        # 5. 生成日志文件路径
+        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+        log_file = fingerprint_dir / f"{tool_name}_{timestamp}.log"
+        
+        logger.info(
+            "开始执行 %s 指纹识别 - URL数: %d, 超时: %ds, 指纹库: %s",
+            tool_name, url_count, timeout, list(fingerprint_paths.keys())
+        )
+        
+        # 6. 执行扫描任务
+        try:
+            result = run_xingfinger_and_stream_update_tech_task(
+                cmd=command,
+                tool_name=tool_name,
+                scan_id=scan_id,
+                target_id=target_id,
+                source=source,
+                cwd=str(fingerprint_dir),
+                timeout=timeout,
+                log_file=str(log_file),
+                batch_size=100
+            )
+            
+            tool_stats[tool_name] = {
+                'command': command,
+                'result': result,
+                'timeout': timeout,
+                'fingerprint_libs': list(fingerprint_paths.keys())
+            }
+            
+            logger.info(
+                "✓ 工具 %s 执行完成 - 处理记录: %d, 更新: %d, 未找到: %d",
+                tool_name,
+                result.get('processed_records', 0),
+                result.get('updated_count', 0),
+                result.get('not_found_count', 0)
+            )
+            
+        except Exception as exc:
+            failed_tools.append({'tool': tool_name, 'reason': str(exc)})
+            logger.error("工具 %s 执行失败: %s", tool_name, exc, exc_info=True)
+    
+    if failed_tools:
+        logger.warning(
+            "以下指纹识别工具执行失败: %s",
+            ', '.join([f['tool'] for f in failed_tools])
+        )
+    
+    return tool_stats, failed_tools
+
+
+@flow(
+    name="fingerprint_detect",
+    log_prints=True,
+    on_running=[on_scan_flow_running],
+    on_completion=[on_scan_flow_completed],
+    on_failure=[on_scan_flow_failed],
+)
+def fingerprint_detect_flow(
+    scan_id: int,
+    target_name: str,
+    target_id: int,
+    scan_workspace_dir: str,
+    enabled_tools: dict
+) -> dict:
+    """
+    指纹识别 Flow
+    
+    主要功能：
+        1. 从数据库导出目标下所有 WebSite URL 到文件
+        2. 使用 xingfinger 进行技术栈识别
+        3. 解析结果并更新 WebSite.tech 字段（合并去重）
+    
+    工作流程：
+        Step 0: 创建工作目录
+        Step 1: 导出 URL 列表
+        Step 2: 解析配置，获取启用的工具
+        Step 3: 执行 xingfinger 并解析结果
+    
+    Args:
+        scan_id: 扫描任务 ID
+        target_name: 目标名称
+        target_id: 目标 ID
+        scan_workspace_dir: 扫描工作空间目录
+        enabled_tools: 启用的工具配置（xingfinger）
+        
+    Returns:
+        dict: {
+            'success': bool,
+            'scan_id': int,
+            'target': str,
+            'scan_workspace_dir': str,
+            'urls_file': str,
+            'url_count': int,
+            'processed_records': int,
+            'updated_count': int,
+            'not_found_count': int,
+            'executed_tasks': list,
+            'tool_stats': dict
+        }
+    """
+    try:
+        logger.info(
+            "="*60 + "\n" +
+            "开始指纹识别\n" +
+            f"  Scan ID: {scan_id}\n" +
+            f"  Target: {target_name}\n" +
+            f"  Workspace: {scan_workspace_dir}\n" +
+            "="*60
+        )
+        
+        # 参数验证
+        if scan_id is None:
+            raise ValueError("scan_id 不能为空")
+        if not target_name:
+            raise ValueError("target_name 不能为空")
+        if target_id is None:
+            raise ValueError("target_id 不能为空")
+        if not scan_workspace_dir:
+            raise ValueError("scan_workspace_dir 不能为空")
+        
+        # 数据源类型（当前只支持 website）
+        source = 'website'
+        
+        # Step 0: 创建工作目录
+        from apps.scan.utils import setup_scan_directory
+        fingerprint_dir = setup_scan_directory(scan_workspace_dir, 'fingerprint_detect')
+        
+        # Step 1: 导出 URL（支持懒加载）
+        urls_file, url_count = _export_urls(target_id, fingerprint_dir, source)
+        
+        if url_count == 0:
+            logger.warning("目标下没有可用的 URL，跳过指纹识别")
+            return {
+                'success': True,
+                'scan_id': scan_id,
+                'target': target_name,
+                'scan_workspace_dir': scan_workspace_dir,
+                'urls_file': urls_file,
+                'url_count': 0,
+                'processed_records': 0,
+                'updated_count': 0,
+                'created_count': 0,
+                'executed_tasks': ['export_urls_for_fingerprint'],
+                'tool_stats': {
+                    'total': 0,
+                    'successful': 0,
+                    'failed': 0,
+                    'successful_tools': [],
+                    'failed_tools': [],
+                    'details': {}
+                }
+            }
+        
+        # Step 2: 工具配置信息
+        logger.info("Step 2: 工具配置信息")
+        logger.info("✓ 启用工具: %s", ', '.join(enabled_tools.keys()))
+        
+        # Step 3: 执行指纹识别
+        logger.info("Step 3: 执行指纹识别")
+        tool_stats, failed_tools = _run_fingerprint_detect(
+            enabled_tools=enabled_tools,
+            urls_file=urls_file,
+            url_count=url_count,
+            fingerprint_dir=fingerprint_dir,
+            scan_id=scan_id,
+            target_id=target_id,
+            source=source
+        )
+        
+        logger.info("="*60 + "\n✓ 指纹识别完成\n" + "="*60)
+        
+        # 动态生成已执行的任务列表
+        executed_tasks = ['export_urls_for_fingerprint']
+        executed_tasks.extend([f'run_xingfinger ({tool})' for tool in tool_stats.keys()])
+        
+        # 汇总所有工具的结果
+        total_processed = sum(stats['result'].get('processed_records', 0) for stats in tool_stats.values())
+        total_updated = sum(stats['result'].get('updated_count', 0) for stats in tool_stats.values())
+        total_created = sum(stats['result'].get('created_count', 0) for stats in tool_stats.values())
+        
+        successful_tools = [name for name in enabled_tools.keys() 
+                           if name not in [f['tool'] for f in failed_tools]]
+        
+        return {
+            'success': True,
+            'scan_id': scan_id,
+            'target': target_name,
+            'scan_workspace_dir': scan_workspace_dir,
+            'urls_file': urls_file,
+            'url_count': url_count,
+            'processed_records': total_processed,
+            'updated_count': total_updated,
+            'created_count': total_created,
+            'executed_tasks': executed_tasks,
+            'tool_stats': {
+                'total': len(enabled_tools),
+                'successful': len(successful_tools),
+                'failed': len(failed_tools),
+                'successful_tools': successful_tools,
+                'failed_tools': failed_tools,
+                'details': tool_stats
+            }
+        }
+        
+    except ValueError as e:
+        logger.error("配置错误: %s", e)
+        raise
+    except RuntimeError as e:
+        logger.error("运行时错误: %s", e)
+        raise
+    except Exception as e:
+        logger.exception("指纹识别失败: %s", e)
+        raise