chore: remote waf fingerprinting base

Add Docker build test to CI workflow (#2196)

.github/CODEOWNERS

@@ -1,5 +1,5 @@
 ### REPOSITORY
-/.github/CODEOWNERS @sdushantha
+/.github/CODEOWNERS @sdushantha @ppfeister
 /.github/FUNDING.yml @sdushantha
 /LICENSE @sdushantha
 

.github/workflows/exclusions.yml

@@ -45,9 +45,9 @@ jobs:
         run: |
           git fetch origin exclusions || true
 
-          if git show origin/exclusions:exclusions.txt >/dev/null 2>&1; then
+          if git show origin/exclusions:false_positive_exclusions.txt >/dev/null 2>&1; then
             # If the exclusions branch and file exist, compare
-            if git diff --quiet origin/exclusions -- exclusions.txt; then
+            if git diff --quiet origin/exclusions -- false_positive_exclusions.txt; then
               echo "exclusions_changed=false" >> "$GITHUB_OUTPUT"
             else
               echo "exclusions_changed=true" >> "$GITHUB_OUTPUT"
@@ -71,10 +71,19 @@ jobs:
           git config user.name "Paul Pfeister (automation)"
           git config user.email "code@pfeister.dev"
 
+          mv false_positive_exclusions.txt false_positive_exclusions.txt.tmp
+
+          git add -f false_positive_exclusions.txt.tmp # -f required to override .gitignore
+          git stash push -m "stash false positive exclusion list" -- false_positive_exclusions.txt.tmp
+
           git fetch origin exclusions || true # Allows creation of branch if deleted
           git checkout -B exclusions origin/exclusions || (git checkout --orphan exclusions && git rm -rf .)
 
-          git add false_positive_exclusions.txt
+          git stash pop || true
 
+          mv false_positive_exclusions.txt.tmp false_positive_exclusions.txt
+
+          git rm -f false_positive_exclusions.txt.tmp || true
+          git add false_positive_exclusions.txt
           git commit -m "auto: update exclusions list" || echo "No changes to commit"
           git push origin exclusions

.github/workflows/regression.yml

@@ -11,6 +11,7 @@ on:
       - '**/*.py'
       - '**/*.ini'
       - '**/*.toml'
+      - 'Dockerfile'
   push:
     branches:
       - master
@@ -21,11 +22,13 @@ on:
       - '**/*.py'
       - '**/*.ini'
       - '**/*.toml'
+      - 'Dockerfile'
 
 jobs:
   tox-lint:
-    # Linting is ran through tox to ensure that the same linter is used by local runners
     runs-on: ubuntu-latest
+    # Linting is ran through tox to ensure that the same linter
+    # is used by local runners
     steps:
       - uses: actions/checkout@v4
       - name: Set up linting environment
@@ -41,7 +44,8 @@ jobs:
   tox-matrix:
     runs-on: ${{ matrix.os }}
     strategy:
-      fail-fast: false # We want to know what specicic versions it fails on
+      # We want to know what specicic versions it fails on
+      fail-fast: false
       matrix:
         os: [
           ubuntu-latest,
@@ -67,3 +71,22 @@ jobs:
           pip install tox-gh-actions
       - name: Run tox
         run: tox
+  docker-build-test:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Get version from pyproject.toml
+        id: get-version
+        run: |
+          VERSION=$(grep -m1 'version = ' pyproject.toml | cut -d'"' -f2)
+          echo "version=$VERSION" >> $GITHUB_OUTPUT
+      - name: Build Docker image
+        run: |
+          docker build \
+            --build-arg VERSION_TAG=${{ steps.get-version.outputs.version }} \
+            -t sherlock-test:latest .
+      - name: Test Docker image runs
+        run: docker run --rm sherlock-test:latest --version

.github/workflows/validate_modified_targets.yml

@@ -0,0 +1,100 @@
+name: Modified Target Validation
+
+on:
+  pull_request_target:
+    branches:
+      - master
+    paths:
+      - "sherlock_project/resources/data.json"
+
+jobs:
+  validate-modified-targets:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v5
+        with:
+          ref: ${{ github.base_ref }}
+          fetch-depth: 1
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: '3.13'
+
+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v4
+        with:
+          poetry-version: 'latest'
+
+      - name: Install dependencies
+        run: |
+          poetry install --no-interaction --with dev
+
+      - name: Drop in place updated manifest from base
+        run: |
+          cp sherlock_project/resources/data.json data.json.base
+          git fetch origin pull/${{ github.event.pull_request.number }}/head:pr --depth=1
+          git show pr:sherlock_project/resources/data.json > sherlock_project/resources/data.json
+          cp sherlock_project/resources/data.json data.json.head
+
+      - name: Discover modified targets
+        id: discover-modified
+        run: |
+          CHANGED=$(
+            python - <<'EOF'
+          import json
+          with open("data.json.base") as f: base = json.load(f)
+          with open("data.json.head") as f: head = json.load(f)
+
+          changed = []
+          for k, v in head.items():
+              if k not in base or base[k] != v:
+                  changed.append(k)
+
+          print(",".join(sorted(changed)))
+          EOF
+          )
+
+          # Preserve changelist
+          echo -e ">>> Changed targets: \n$(echo $CHANGED | tr ',' '\n')"
+          echo "changed_targets=$CHANGED" >> "$GITHUB_OUTPUT"
+
+      - name: Validate modified targets
+        if: steps.discover-modified.outputs.changed_targets != ''
+        continue-on-error: true
+        run: |
+          poetry run pytest -q --tb no -rA -m validate_targets -n 20 \
+            --chunked-sites "${{ steps.discover-modified.outputs.changed_targets }}" \
+            --junitxml=validation_results.xml
+
+      - name: Prepare validation summary
+        if: steps.discover-modified.outputs.changed_targets != ''
+        id: prepare-summary
+        run: |
+          summary=$(
+            poetry run python devel/summarize_site_validation.py validation_results.xml || echo "Failed to generate summary of test results"
+          )
+          echo "$summary" > validation_summary.md
+
+      - name: Announce validation results
+        if: steps.discover-modified.outputs.changed_targets != ''
+        uses: actions/github-script@v8
+        with:
+          script: |
+            const fs = require('fs');
+            const body = fs.readFileSync('validation_summary.md', 'utf8');
+            await github.rest.issues.createComment({
+              issue_number: context.payload.pull_request.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: body,
+            });
+
+      - name: This step shows as ran when no modifications are found
+        if: steps.discover-modified.outputs.changed_targets == ''
+        run: |
+          echo "No modified targets found"

Dockerfile

@@ -4,7 +4,7 @@
   # 3. Build image with BOTH latest and version tags
     # i.e. `docker build -t sherlock/sherlock:0.16.0 -t sherlock/sherlock:latest .`
 
-FROM python:3.12-slim-bullseye as build
+FROM python:3.12-slim-bullseye AS build
 WORKDIR /sherlock
 
 RUN pip3 install --no-cache-dir --upgrade pip

devel/summarize_site_validation.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python
+# This module summarizes the results of site validation tests queued by
+# workflow validate_modified_targets for presentation in Issue comments.
+
+from defusedxml import ElementTree as ET
+import sys
+from pathlib import Path
+
+def summarize_junit_xml(xml_path: Path) -> str:
+    tree = ET.parse(xml_path)
+    root = tree.getroot()
+    suite = root.find('testsuite')
+
+    pass_message: str = ":heavy_check_mark:   Pass"
+    fail_message: str = ":x:   Fail"
+
+    if suite is None:
+        raise ValueError("Invalid JUnit XML: No testsuite found")
+
+    summary_lines: list[str] = []
+    summary_lines.append("#### Automatic validation of changes\n")
+    summary_lines.append("| Target | F+ Check | F- Check |")
+    summary_lines.append("|---|---|---|")
+
+    failures = int(suite.get('failures', 0))
+    errors_detected: bool = False
+
+    results: dict[str, dict[str, str]] = {}
+
+    for testcase in suite.findall('testcase'):
+        test_name = testcase.get('name').split('[')[0]
+        site_name = testcase.get('name').split('[')[1].rstrip(']')
+        failure = testcase.find('failure')
+        error = testcase.find('error')
+
+        if site_name not in results:
+            results[site_name] = {}
+
+        if test_name == "test_false_neg":
+            results[site_name]['F- Check'] = pass_message if failure is None and error is None else fail_message
+        elif test_name == "test_false_pos":
+            results[site_name]['F+ Check'] = pass_message if failure is None and error is None else fail_message
+
+        if error is not None:
+            errors_detected = True
+
+    for result in results:
+        summary_lines.append(f"| {result} | {results[result].get('F+ Check', 'Error!')} | {results[result].get('F- Check', 'Error!')} |")
+
+    if failures > 0:
+        summary_lines.append("\n___\n" +
+            "\nFailures were detected on at least one updated target. Commits containing accuracy failures" +
+            " will often not be merged (unless a rationale is provided, such as false negatives due to regional differences).")
+
+    if errors_detected:
+        summary_lines.append("\n___\n" +
+            "\n**Errors were detected during validation. Please review the workflow logs.**")
+
+    return "\n".join(summary_lines)
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: summarize_site_validation.py <junit-xml-file>")
+        sys.exit(1)
+
+    xml_path: Path = Path(sys.argv[1])
+    if not xml_path.is_file():
+        print(f"Error: File '{xml_path}' does not exist.")
+        sys.exit(1)
+
+    summary: str = summarize_junit_xml(xml_path)
+    print(summary)

pyproject.toml

@@ -8,8 +8,7 @@ source = "init"
 
 [tool.poetry]
 name = "sherlock-project"
-# single source of truth for version is __init__.py
-version = "0"
+version = "0.16.0"
 description = "Hunt down social media accounts by username across social networks"
 license = "MIT"
 authors = [
@@ -47,12 +46,10 @@ PySocks = "^1.7.0"
 requests = "^2.22.0"
 requests-futures = "^1.0.0"
 stem = "^1.8.0"
-torrequest = "^0.1.0"
 pandas = "^2.2.1"
 openpyxl = "^3.0.10"
-
-[tool.poetry.extras]
-tor = ["torrequest"]
+tomli = "^2.2.1"
+pyyaml = "^6.0.3"
 
 [tool.poetry.group.dev.dependencies]
 jsonschema = "^4.0.0"
@@ -60,5 +57,9 @@ rstr = "^3.2.2"
 pytest = "^8.4.2"
 pytest-xdist = "^3.8.0"
 
+
+[tool.poetry.group.ci.dependencies]
+defusedxml = "^0.7.1"
+
 [tool.poetry.scripts]
 sherlock = 'sherlock_project.sherlock:main'

sherlock_project/__init__.py

@@ -5,11 +5,26 @@ networks.
 
 """
 
+from importlib.metadata import version as pkg_version, PackageNotFoundError
+import pathlib
+import tomli
+
+
+def get_version() -> str:
+    """Fetch the version number of the installed package."""
+    try:
+        return pkg_version("sherlock_project")
+    except PackageNotFoundError:
+        pyproject_path: pathlib.Path = pathlib.Path(__file__).resolve().parent.parent / "pyproject.toml"
+        with pyproject_path.open("rb") as f:
+            pyproject_data = tomli.load(f)
+        return pyproject_data["tool"]["poetry"]["version"]
+
 # This variable is only used to check for ImportErrors induced by users running as script rather than as module or package
 import_error_test_var = None
 
 __shortname__   = "Sherlock"
 __longname__    = "Sherlock: Find Usernames Across Social Networks"
-__version__     = "0.16.0"
+__version__     = get_version()
 
 forge_api_latest_release = "https://api.github.com/repos/sherlock-project/sherlock/releases/latest"

sherlock_project/resources/data.json

@@ -79,13 +79,13 @@
     "username_claimed": "pink"
   },
   "AllMyLinks": {
-    "errorMsg": "Not Found",
-    "errorType": "message",
-    "regexCheck": "^[a-z0-9][a-z0-9-]{2,32}$",
-    "url": "https://allmylinks.com/{}",
-    "urlMain": "https://allmylinks.com/",
-    "username_claimed": "blue"
-  },
+  "errorMsg": "Page not found",
+  "errorType": "message",
+  "regexCheck": "^[a-z0-9][a-z0-9-]{2,32}$",
+  "url": "https://allmylinks.com/{}",
+  "urlMain": "https://allmylinks.com/",
+  "username_claimed": "blue"
+},
   "AniWorld": {
     "errorMsg": "Dieses Profil ist nicht verf\u00fcgbar",
     "errorType": "message",
@@ -115,12 +115,20 @@
     "username_claimed": "lio24d"
   },
   "Apple Discussions": {
-    "errorMsg": "The page you tried was not found. You may have used an outdated link or may have typed the address (URL) incorrectly.",
+    "errorMsg": "Looking for something in Apple Support Communities?",
     "errorType": "message",
     "url": "https://discussions.apple.com/profile/{}",
     "urlMain": "https://discussions.apple.com",
     "username_claimed": "jason"
   },
+  "Aparat": {
+    "errorType": "status_code",
+    "request_method": "GET",
+    "url": "https://www.aparat.com/{}/",
+    "urlMain": "https://www.aparat.com/",
+    "urlProbe": "https://www.aparat.com/api/fa/v1/user/user/information/username/{}",
+    "username_claimed": "jadi"
+  },
   "Archive of Our Own": {
     "errorType": "status_code",
     "regexCheck": "^[^.]*?$",
@@ -564,8 +572,7 @@
     "username_claimed": "brown"
   },
   "CyberDefenders": {
-    "errorMsg": "<title>Blue Team Training for SOC analysts and DFIR - CyberDefenders</title>",
-    "errorType": "message",
+    "errorType": "status_code",
     "regexCheck": "^[^\\/:*?\"<>|@]{3,50}$",
     "request_method": "GET",
     "url": "https://cyberdefenders.org/p/{}",
@@ -592,6 +599,12 @@
     "urlMain": "https://www.dailymotion.com/",
     "username_claimed": "blue"
   },
+  "dcinside": {
+    "errorType": "status_code",
+    "url": "https://gallog.dcinside.com/{}",
+    "urlMain": "https://www.dcinside.com/",
+    "username_claimed": "anrbrb"
+  },
   "Dealabs": {
     "errorMsg": "La page que vous essayez",
     "errorType": "message",
@@ -600,13 +613,14 @@
     "urlMain": "https://www.dealabs.com/",
     "username_claimed": "blue"
   },
-  "DeviantART": {
-    "errorType": "status_code",
-    "regexCheck": "^[a-zA-Z][a-zA-Z0-9_-]*$",
-    "url": "https://{}.deviantart.com",
-    "urlMain": "https://deviantart.com",
-    "username_claimed": "blue"
-  },
+ "DeviantArt": {
+  "errorType": "message",
+  "errorMsg": "Llama Not Found",
+  "regexCheck": "^[a-zA-Z][a-zA-Z0-9_-]*$",
+  "url": "https://www.deviantart.com/{}",
+  "urlMain": "https://www.deviantart.com/",
+  "username_claimed": "blue"
+},
   "DigitalSpy": {
       "errorMsg": "The page you were looking for could not be found.",
       "errorType": "message",
@@ -807,14 +821,6 @@
     "urlMain": "https://framapiaf.org",
     "username_claimed": "pylapp"
   },
-  "Freelance.habr": {
-    "errorMsg": "<div class=\"icon_user_locked\"></div>",
-    "errorType": "message",
-    "regexCheck": "^((?!\\.).)*$",
-    "url": "https://freelance.habr.com/freelancers/{}",
-    "urlMain": "https://freelance.habr.com/",
-    "username_claimed": "adam"
-  },
   "Freelancer": {
     "errorMsg": "\"users\":{}",
     "errorType": "message",
@@ -1142,6 +1148,13 @@
     "urlProbe": "https://imginn.com/{}",
     "username_claimed": "instagram"
   },
+  "Instapaper": {
+    "errorType": "status_code",
+    "request_method": "GET",
+    "url": "https://www.instapaper.com/p/{}",
+    "urlMain": "https://www.instapaper.com/",
+    "username_claimed": "john"
+  },
   "Instructables": {
     "errorType": "status_code",
     "url": "https://www.instructables.com/member/{}",
@@ -1254,6 +1267,13 @@
     "urlMain": "https://linux.org.ru/",
     "username_claimed": "red"
   },
+  "Laracast": {
+    "errorType":"status_code",
+    "url": "https://laracasts.com/@{}",
+    "urlMain": "https://laracasts.com/",
+    "regexCheck": "^[a-zA-Z0-9_-]{3,}$",
+    "username_claimed": "user1"
+  },
   "Launchpad": {
     "errorType": "status_code",
     "url": "https://launchpad.net/~{}",
@@ -1426,12 +1446,12 @@
     "username_claimed": "blue"
   },
   "Mydramalist": {
-    "errorMsg": "Sign in - MyDramaList",
-    "errorType": "message",
-    "url": "https://www.mydramalist.com/profile/{}",
-    "urlMain": "https://mydramalist.com",
-    "username_claimed": "elhadidy12398"
-  },
+  "errorMsg": "The requested page was not found",
+  "errorType": "message",
+  "url": "https://www.mydramalist.com/profile/{}",
+  "urlMain": "https://mydramalist.com",
+  "username_claimed": "elhadidy12398"
+},
   "Myspace": {
     "errorType": "status_code",
     "url": "https://myspace.com/{}",
@@ -1445,6 +1465,13 @@
     "urlMain": "https://www.native-instruments.com/forum/",
     "username_claimed": "jambert"
   },
+  "namuwiki": {
+    "__comment__": "This is a Korean site and it's expected to return false negatives in certain other regions.",
+    "errorType": "status_code",
+    "url": "https://namu.wiki/w/%EC%82%AC%EC%9A%A9%EC%9E%90:{}",
+    "urlMain": "https://namu.wiki/",
+    "username_claimed": "namu"
+  },
   "NationStates Nation": {
     "errorMsg": "Was this your nation? It may have ceased to exist due to inactivity, but can rise again!",
     "errorType": "message",
@@ -1558,7 +1585,7 @@
     "url": "https://outgress.com/agents/{}",
     "urlMain": "https://outgress.com/",
     "username_claimed": "pylapp"
-  },  
+  },
   "PCGamer": {
     "errorMsg": "The specified member cannot be found. Please enter a member's entire name.",
     "errorType": "message",
@@ -1795,8 +1822,7 @@
     "username_claimed": "blue"
   },
   "Roblox": {
-    "errorMsg": "Page cannot be found or no longer exists",
-    "errorType": "message",
+    "errorType": "status_code",
     "url": "https://www.roblox.com/user.aspx?username={}",
     "urlMain": "https://www.roblox.com/",
     "username_claimed": "bluewolfekiller"
@@ -1904,7 +1930,7 @@
   },
   "SlideShare": {
     "errorType": "message",
-    "errorMsg": "<title>Username available</title>",
+    "errorMsg": "<title>Page no longer exists</title>",
     "url": "https://slideshare.net/{}",
     "urlMain": "https://slideshare.net/",
     "username_claimed": "blue"
@@ -1938,6 +1964,13 @@
     "urlMain": "https://www.snapchat.com",
     "username_claimed": "teamsnapchat"
   },
+  "SOOP": {
+    "errorType": "status_code",
+    "url": "https://www.sooplive.co.kr/station/{}",
+    "urlMain": "https://www.sooplive.co.kr/",
+    "urlProbe": "https://api-channel.sooplive.co.kr/v1.1/channel/{}/station",
+    "username_claimed": "udkn"
+  },
   "SoundCloud": {
     "errorType": "status_code",
     "url": "https://soundcloud.com/{}",
@@ -2105,6 +2138,12 @@
     "urlMain": "https://themeforest.net/",
     "username_claimed": "user"
   },
+  "tistory": {
+    "errorType": "status_code",
+    "url": "https://{}.tistory.com/",
+    "urlMain": "https://www.tistory.com/",
+    "username_claimed": "notice"
+  },
   "TnAFlix": {
     "errorType": "status_code",
     "isNSFW": true,
@@ -2779,7 +2818,7 @@
     "username_claimed": "green"
   },
   "threads": {
-    "errorMsg": "<title>Threads</title>",
+    "errorMsg": "<title>Threads • Log in</title>",
     "errorType": "message",
     "headers": {
       "Sec-Fetch-Mode": "navigate"

sherlock_project/resources/data.schema.json

@@ -1,80 +1,149 @@
 {
-    "$schema": "https://json-schema.org/draft/2020-12/schema",
-    "title": "Sherlock Target Manifest",
-    "description": "Social media targets to probe for the existence of known usernames",
-    "type": "object",
-    "properties": {
-        "$schema": { "type": "string" }
-    },
-    "patternProperties": {
-        "^(?!\\$).*?$": {
-            "type": "object",
-            "description": "Target name and associated information (key should be human readable name)",
-            "required": [ "url", "urlMain", "errorType", "username_claimed" ],
-            "properties": {
-                "url": { "type": "string" },
-                "urlMain": { "type": "string" },
-                "urlProbe": { "type": "string" },
-                "username_claimed": { "type": "string" },
-                "regexCheck": { "type": "string" },
-                "isNSFW": { "type": "boolean" },
-                "headers": { "type": "object" },
-                "request_payload": { "type": "object" },
-                "__comment__": {
-                    "type": "string",
-                    "description": "Used to clarify important target information if (and only if) a commit message would not suffice.\nThis key should not be parsed anywhere within Sherlock."
-                },
-                "tags": {
-                    "oneOf": [
-                        { "$ref": "#/$defs/tag" },
-                        { "type": "array", "items": { "$ref": "#/$defs/tag" } }
-                    ]
-                },
-                "request_method": {
-                    "type": "string",
-                    "enum": [ "GET", "POST", "HEAD", "PUT" ]
-                },
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "title": "Sherlock Target Manifest",
+  "description": "Social media targets to probe for the existence of known usernames",
+  "type": "object",
+  "properties": {
+    "$schema": { "type": "string" }
+  },
+  "patternProperties": {
+    "^(?!\\$).*?$": {
+      "type": "object",
+      "description": "Target name and associated information (key should be human readable name)",
+      "required": ["url", "urlMain", "errorType", "username_claimed"],
+      "properties": {
+        "url": { "type": "string" },
+        "urlMain": { "type": "string" },
+        "urlProbe": { "type": "string" },
+        "username_claimed": { "type": "string" },
+        "regexCheck": { "type": "string" },
+        "isNSFW": { "type": "boolean" },
+        "headers": { "type": "object" },
+        "request_payload": { "type": "object" },
+        "__comment__": {
+          "type": "string",
+          "description": "Used to clarify important target information if (and only if) a commit message would not suffice.\nThis key should not be parsed anywhere within Sherlock."
+        },
+        "tags": {
+          "oneOf": [
+            { "$ref": "#/$defs/tag" },
+            { "type": "array", "items": { "$ref": "#/$defs/tag" } }
+          ]
+        },
+        "request_method": {
+          "type": "string",
+          "enum": ["GET", "POST", "HEAD", "PUT"]
+        },
+        "errorType": {
+          "oneOf": [
+            {
+              "type": "string",
+              "enum": ["message", "response_url", "status_code"]
+            },
+            {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": ["message", "response_url", "status_code"]
+              }
+            }
+          ]
+        },
+        "errorMsg": {
+          "oneOf": [
+            { "type": "string" },
+            { "type": "array", "items": { "type": "string" } }
+          ]
+        },
+        "errorCode": {
+          "oneOf": [
+            { "type": "integer" },
+            { "type": "array", "items": { "type": "integer" } }
+          ]
+        },
+        "errorUrl": { "type": "string" },
+        "response_url": { "type": "string" }
+      },
+      "dependencies": {
+        "errorMsg": {
+          "oneOf": [
+            { "properties": { "errorType": { "const": "message" } } },
+            {
+              "properties": {
                 "errorType": {
-                    "type": "string",
-                    "enum": [ "message", "response_url", "status_code" ]
-                },
-                "errorMsg": {
-                    "oneOf": [
-                        { "type": "string" },
-                        { "type": "array", "items": { "type": "string" } }
-                    ]
-                },
-                "errorCode": {
-                    "oneOf": [
-                        { "type": "integer" },
-                        { "type": "array", "items": { "type": "integer" } }
-                    ]
-                },
-                "errorUrl": { "type": "string" },
-                "response_url": { "type": "string" }
-            },
-            "dependencies": {
-                "errorMsg": {
-                    "properties" : { "errorType": { "const": "message" } }
-                },
-                "errorUrl": {
-                    "properties": { "errorType": { "const": "response_url" } }
-                },
-                "errorCode": {
-                    "properties": { "errorType": { "const": "status_code" } }
+                  "type": "array",
+                  "contains": { "const": "message" }
                 }
-            },
-            "if": { "properties": { "errorType": { "const": "message" } } },
-            "then": { "required": [ "errorMsg" ] },
-            "else": {
-                "if": { "properties": { "errorType": { "const": "response_url" } } },
-                "then": { "required": [ "errorUrl" ] }
-            },
-            "additionalProperties": false
+              }
+            }
+          ]
+        },
+        "errorUrl": {
+          "oneOf": [
+            { "properties": { "errorType": { "const": "response_url" } } },
+            {
+              "properties": {
+                "errorType": {
+                  "type": "array",
+                  "contains": { "const": "response_url" }
+                }
+              }
+            }
+          ]
+        },
+        "errorCode": {
+          "oneOf": [
+            { "properties": { "errorType": { "const": "status_code" } } },
+            {
+              "properties": {
+                "errorType": {
+                  "type": "array",
+                  "contains": { "const": "status_code" }
+                }
+              }
+            }
+          ]
         }
-    },
-    "additionalProperties": false,
-    "$defs": {
-        "tag": { "type": "string", "enum": [ "adult", "gaming" ] }
+      },
+      "allOf": [
+        {
+          "if": {
+            "anyOf": [
+              { "properties": { "errorType": { "const": "message" } } },
+              {
+                "properties": {
+                  "errorType": {
+                    "type": "array",
+                    "contains": { "const": "message" }
+                  }
+                }
+              }
+            ]
+          },
+          "then": { "required": ["errorMsg"] }
+        },
+        {
+          "if": {
+            "anyOf": [
+              { "properties": { "errorType": { "const": "response_url" } } },
+              {
+                "properties": {
+                  "errorType": {
+                    "type": "array",
+                    "contains": { "const": "response_url" }
+                  }
+                }
+              }
+            ]
+          },
+          "then": { "required": ["errorUrl"] }
+        }
+      ],
+      "additionalProperties": false
     }
+  },
+  "additionalProperties": false,
+  "$defs": {
+    "tag": { "type": "string", "enum": ["adult", "gaming"] }
+  }
 }

sherlock_project/sherlock.py

@@ -171,8 +171,6 @@ def sherlock(
     username: str,
     site_data: dict[str, dict[str, str]],
     query_notify: QueryNotify,
-    tor: bool = False,
-    unique_tor: bool = False,
     dump_response: bool = False,
     proxy: Optional[str] = None,
     timeout: int = 60,
@@ -188,8 +186,6 @@ def sherlock(
     query_notify           -- Object with base type of QueryNotify().
                               This will be used to notify the caller about
                               query results.
-    tor                    -- Boolean indicating whether to use a tor circuit for the requests.
-    unique_tor             -- Boolean indicating whether to use a new tor circuit for each request.
     proxy                  -- String indicating the proxy URL
     timeout                -- Time in seconds to wait before timing out request.
                               Default is 60 seconds.
@@ -210,32 +206,9 @@ def sherlock(
 
     # Notify caller that we are starting the query.
     query_notify.start(username)
-    # Create session based on request methodology
-    if tor or unique_tor:
-        try:
-            from torrequest import TorRequest  # noqa: E402
-        except ImportError:
-            print("Important!")
-            print("> --tor and --unique-tor are now DEPRECATED, and may be removed in a future release of Sherlock.")
-            print("> If you've installed Sherlock via pip, you can include the optional dependency via `pip install 'sherlock-project[tor]'`.")
-            print("> Other packages should refer to their documentation, or install it separately with `pip install torrequest`.\n")
-            sys.exit(query_notify.finish())
 
-        print("Important!")
-        print("> --tor and --unique-tor are now DEPRECATED, and may be removed in a future release of Sherlock.")
-
-        # Requests using Tor obfuscation
-        try:
-            underlying_request = TorRequest()
-        except OSError:
-            print("Tor not found in system path. Unable to continue.\n")
-            sys.exit(query_notify.finish())
-
-        underlying_session = underlying_request.session
-    else:
-        # Normal requests
-        underlying_session = requests.session()
-        underlying_request = requests.Request()
+    # Normal requests
+    underlying_session = requests.session()
 
     # Limit number of workers to 20.
     # This is probably vastly overkill.
@@ -359,15 +332,10 @@ def sherlock(
             # Store future in data for access later
             net_info["request_future"] = future
 
-            # Reset identify for tor (if needed)
-            if unique_tor:
-                underlying_request.reset_identity()
-
         # Add this site's results into final dictionary with all the other results.
         results_total[social_network] = results_site
 
     # Open the file containing account links
-    # Core logic: If tor requests, make them here. If multi-threaded requests, wait for responses
     for social_network, net_info in site_data.items():
         # Retrieve results again
         results_site = results_total.get(social_network)
@@ -381,6 +349,8 @@ def sherlock(
 
         # Get the expected error type
         error_type = net_info["errorType"]
+        if isinstance(error_type, str):
+            error_type: list[str] = [error_type]
 
         # Retrieve future and ensure it has finished
         future = net_info["request_future"]
@@ -425,58 +395,60 @@ def sherlock(
         elif any(hitMsg in r.text for hitMsg in WAFHitMsgs):
             query_status = QueryStatus.WAF
 
-        elif error_type == "message":
-            # error_flag True denotes no error found in the HTML
-            # error_flag False denotes error found in the HTML
-            error_flag = True
-            errors = net_info.get("errorMsg")
-            # errors will hold the error message
-            # it can be string or list
-            # by isinstance method we can detect that
-            # and handle the case for strings as normal procedure
-            # and if its list we can iterate the errors
-            if isinstance(errors, str):
-                # Checks if the error message is in the HTML
-                # if error is present we will set flag to False
-                if errors in r.text:
-                    error_flag = False
-            else:
-                # If it's list, it will iterate all the error message
-                for error in errors:
-                    if error in r.text:
-                        error_flag = False
-                        break
-            if error_flag:
-                query_status = QueryStatus.CLAIMED
-            else:
-                query_status = QueryStatus.AVAILABLE
-        elif error_type == "status_code":
-            error_codes = net_info.get("errorCode")
-            query_status = QueryStatus.CLAIMED
-
-            # Type consistency, allowing for both singlets and lists in manifest
-            if isinstance(error_codes, int):
-                error_codes = [error_codes]
-
-            if error_codes is not None and r.status_code in error_codes:
-                query_status = QueryStatus.AVAILABLE
-            elif r.status_code >= 300 or r.status_code < 200:
-                query_status = QueryStatus.AVAILABLE
-        elif error_type == "response_url":
-            # For this detection method, we have turned off the redirect.
-            # So, there is no need to check the response URL: it will always
-            # match the request.  Instead, we will ensure that the response
-            # code indicates that the request was successful (i.e. no 404, or
-            # forward to some odd redirect).
-            if 200 <= r.status_code < 300:
-                query_status = QueryStatus.CLAIMED
-            else:
-                query_status = QueryStatus.AVAILABLE
         else:
-            # It should be impossible to ever get here...
-            raise ValueError(
-                f"Unknown Error Type '{error_type}' for " f"site '{social_network}'"
-            )
+            if any(errtype not in ["message", "status_code", "response_url"] for errtype in error_type):
+                error_context = f"Unknown error type '{error_type}' for {social_network}"
+                query_status = QueryStatus.UNKNOWN
+            else:
+                if "message" in error_type:
+                    # error_flag True denotes no error found in the HTML
+                    # error_flag False denotes error found in the HTML
+                    error_flag = True
+                    errors = net_info.get("errorMsg")
+                    # errors will hold the error message
+                    # it can be string or list
+                    # by isinstance method we can detect that
+                    # and handle the case for strings as normal procedure
+                    # and if its list we can iterate the errors
+                    if isinstance(errors, str):
+                        # Checks if the error message is in the HTML
+                        # if error is present we will set flag to False
+                        if errors in r.text:
+                            error_flag = False
+                    else:
+                        # If it's list, it will iterate all the error message
+                        for error in errors:
+                            if error in r.text:
+                                error_flag = False
+                                break
+                    if error_flag:
+                        query_status = QueryStatus.CLAIMED
+                    else:
+                        query_status = QueryStatus.AVAILABLE
+
+                if "status_code" in error_type and query_status is not QueryStatus.AVAILABLE:
+                    error_codes = net_info.get("errorCode")
+                    query_status = QueryStatus.CLAIMED
+
+                    # Type consistency, allowing for both singlets and lists in manifest
+                    if isinstance(error_codes, int):
+                        error_codes = [error_codes]
+
+                    if error_codes is not None and r.status_code in error_codes:
+                        query_status = QueryStatus.AVAILABLE
+                    elif r.status_code >= 300 or r.status_code < 200:
+                        query_status = QueryStatus.AVAILABLE
+
+                if "response_url" in error_type and query_status is not QueryStatus.AVAILABLE:
+                    # For this detection method, we have turned off the redirect.
+                    # So, there is no need to check the response URL: it will always
+                    # match the request.  Instead, we will ensure that the response
+                    # code indicates that the request was successful (i.e. no 404, or
+                    # forward to some odd redirect).
+                    if 200 <= r.status_code < 300:
+                        query_status = QueryStatus.CLAIMED
+                    else:
+                        query_status = QueryStatus.AVAILABLE
 
         if dump_response:
             print("+++++++++++++++++++++")
@@ -596,22 +568,6 @@ def main():
         dest="output",
         help="If using single username, the output of the result will be saved to this file.",
     )
-    parser.add_argument(
-        "--tor",
-        "-t",
-        action="store_true",
-        dest="tor",
-        default=False,
-        help="Make requests over Tor; increases runtime; requires Tor to be installed and in system path.",
-    )
-    parser.add_argument(
-        "--unique-tor",
-        "-u",
-        action="store_true",
-        dest="unique_tor",
-        default=False,
-        help="Make requests over Tor with new Tor circuit after each request; increases runtime; requires Tor to be installed and in system path.",
-    )
     parser.add_argument(
         "--csv",
         action="store_true",
@@ -719,12 +675,22 @@ def main():
         help="Include checking of NSFW sites from default list.",
     )
 
+    # TODO deprecated in favor of --txt, retained for workflow compatibility, to be removed
+    # in future release
     parser.add_argument(
         "--no-txt",
         action="store_true",
         dest="no_txt",
         default=False,
-        help="Disable creation of a txt file",
+        help="Disable creation of a txt file - WILL BE DEPRECATED",
+    )
+
+    parser.add_argument(
+        "--txt",
+        action="store_true",
+        dest="output_txt",
+        default=False,
+        help="Enable creation of a txt file",
     )
 
     parser.add_argument(
@@ -742,7 +708,7 @@ def main():
 
     # Check for newer version of Sherlock. If it exists, let the user know about it
     try:
-        latest_release_raw = requests.get(forge_api_latest_release).text
+        latest_release_raw = requests.get(forge_api_latest_release, timeout=10).text
         latest_release_json = json_loads(latest_release_raw)
         latest_remote_tag = latest_release_json["tag_name"]
 
@@ -755,22 +721,10 @@ def main():
     except Exception as error:
         print(f"A problem occurred while checking for an update: {error}")
 
-    # Argument check
-    # TODO regex check on args.proxy
-    if args.tor and (args.proxy is not None):
-        raise Exception("Tor and Proxy cannot be set at the same time.")
-
     # Make prompts
     if args.proxy is not None:
         print("Using the proxy: " + args.proxy)
 
-    if args.tor or args.unique_tor:
-        print("Using Tor to make requests")
-
-        print(
-            "Warning: some websites might refuse connecting over Tor, so note that using this option might increase connection errors."
-        )
-
     if args.no_color:
         # Disable color output.
         init(strip=True, convert=False)
@@ -802,7 +756,7 @@ def main():
                 if args.json_file.isnumeric():
                     pull_number = args.json_file
                     pull_url = f"https://api.github.com/repos/sherlock-project/sherlock/pulls/{pull_number}"
-                    pull_request_raw = requests.get(pull_url).text
+                    pull_request_raw = requests.get(pull_url, timeout=10).text
                     pull_request_json = json_loads(pull_request_raw)
 
                     # Check if it's a valid pull request
@@ -871,8 +825,6 @@ def main():
             username,
             site_data,
             query_notify,
-            tor=args.tor,
-            unique_tor=args.unique_tor,
             dump_response=args.dump_response,
             proxy=args.proxy,
             timeout=args.timeout,
@@ -888,7 +840,7 @@ def main():
         else:
             result_file = f"{username}.txt"
 
-        if not args.no_txt:
+        if args.output_txt:
             with open(result_file, "w", encoding="utf-8") as file:
                 exists_counter = 0
                 for website_name in results:

sherlock_project/sites.py

@@ -129,7 +129,7 @@ class SitesInformation:
         if data_file_path.lower().startswith("http"):
             # Reference is to a URL.
             try:
-                response = requests.get(url=data_file_path)
+                response = requests.get(url=data_file_path, timeout=30)
             except Exception as error:
                 raise FileNotFoundError(
                     f"Problem while attempting to access data file URL '{data_file_path}':  {error}"
@@ -166,7 +166,7 @@ class SitesInformation:
 
         if honor_exclusions:
             try:
-                response = requests.get(url=EXCLUSIONS_URL)
+                response = requests.get(url=EXCLUSIONS_URL, timeout=10)
                 if response.status_code == 200:
                     exclusions = response.text.splitlines()
                     exclusions = [exclusion.strip() for exclusion in exclusions]

sherlock_project/waf_check.py

@@ -0,0 +1,84 @@
+import requests
+import yaml
+
+
+NUCLEI_FINGERPRINT_URL: str = "https://raw.githubusercontent.com/projectdiscovery/nuclei-templates/refs/heads/main/http/global-matchers/global-waf-detect.yaml"
+
+def _check_nuclei_regex(matcher: dict[str,str|list[str]], response: requests.Response) -> bool:
+    import re
+
+    and_cond: bool = matcher.get('condition', '') == 'and'
+
+    target_text: str
+    if matcher['part'] == 'body':
+        target_text = response.text
+    elif matcher['part'] == 'header':
+        target_text = str(response.headers)
+    else:
+        target_text = response.text + str(response.headers)
+
+    for regex in matcher['regex']:
+        if re.search(regex, target_text):
+            if not and_cond:
+                return True
+        else:
+            break
+    else:
+        # `and` conditions will cycle, resulting in this default return True
+        # unless an early failed detection breaks the loop (resulting in False)
+        return True
+    return False
+
+def _check_nuclei_words(matcher: dict[str,str|list[str]], response: requests.Response) -> bool:
+    and_cond: bool = matcher.get('condition', '') == 'and'
+
+    target_text: str
+    if matcher['part'] == 'body':
+        target_text = response.text
+    elif matcher['part'] == 'header':
+        target_text = str(response.headers)
+    else:
+        target_text = response.text + str(response.headers)
+
+    for word in matcher['words']:
+        if word in target_text:
+            if not and_cond:
+                return True
+        else:
+            break
+    else:
+        # `and` conditions will cycle, resulting in this default return True
+        # unless an early failed detection breaks the loop (resulting in False)
+        return True
+    return False
+
+def fetch_nuclei_fingerprints() -> list[dict[str,str|list[str]]] | None:
+    """Fetch the latest Nuclei WAF fingerprints from the official repository."""
+    try:
+        response = requests.get(NUCLEI_FINGERPRINT_URL, timeout=10)
+        response.raise_for_status()
+        raw = yaml.safe_load(response.text)
+        fingerprints: list[dict[str,str|list[str]]] = raw['http'][0]['matchers']
+        return fingerprints
+    except requests.RequestException as e:
+        print(f"Error fetching Nuclei fingerprints: {e}")
+        return None
+    except yaml.YAMLError as e:
+        print(f"Error parsing YAML data: {e}")
+        return None
+
+def nuclei_check(response: requests.Response, fingerprints: list[dict[str,str|list[str]]]) -> bool:
+    """Check if the response matches any of the WAF fingerprints.
+
+    Keyword arguments:
+    response -- The HTTP response to check.
+    fingerprints -- The list of Nuclei WAF fingerprints to check against.
+
+    Returns True if a WAF is detected, False otherwise.
+    """
+    for matcher in fingerprints:
+        if matcher['type'] == 'word':
+            return _check_nuclei_words(matcher, response)
+        elif matcher['type'] == 'regex':
+            return _check_nuclei_regex(matcher, response)
+    return False

tests/conftest.py

@@ -4,9 +4,9 @@ import urllib
 import pytest
 from sherlock_project.sites import SitesInformation
 
-def fetch_local_manifest() -> dict[str, dict[str, str]]:
-    sites_obj = SitesInformation(data_file_path=os.path.join(os.path.dirname(__file__), "../sherlock_project/resources/data.json"))
-    sites_iterable = {site.name: site.information for site in sites_obj}
+def fetch_local_manifest(honor_exclusions: bool = True) -> dict[str, dict[str, str]]:
+    sites_obj = SitesInformation(data_file_path=os.path.join(os.path.dirname(__file__), "../sherlock_project/resources/data.json"), honor_exclusions=honor_exclusions)
+    sites_iterable: dict[str, dict[str, str]] = {site.name: site.information for site in sites_obj}
     return sites_iterable
 
 @pytest.fixture()
@@ -25,9 +25,27 @@ def remote_schema():
         schemadat = json.load(remoteschema)
     yield schemadat
 
+def pytest_addoption(parser):
+    parser.addoption(
+        "--chunked-sites",
+        action="store",
+        default=None,
+        help="For tests utilizing chunked sites, include only the (comma-separated) site(s) specified.",
+    )
+
 def pytest_generate_tests(metafunc):
     if "chunked_sites" in metafunc.fixturenames:
-        sites_info = fetch_local_manifest()
+        sites_info = fetch_local_manifest(honor_exclusions=False)
+
+        # Ingest and apply site selections
+        site_filter: str | None = metafunc.config.getoption("--chunked-sites")
+        if site_filter:
+            selected_sites: list[str] = [site.strip() for site in site_filter.split(",")]
+            sites_info = {
+                site: data for site, data in sites_info.items()
+                if site in selected_sites
+            }
+
         params = [{name: data} for name, data in sites_info.items()]
         ids = list(sites_info.keys())
         metafunc.parametrize("chunked_sites", params, ids=ids)

tests/mocks/global_waf_detect.yaml

@@ -0,0 +1,26 @@
+id: global-waf-detect
+http:
+  - global-matchers: true
+    matchers-condition: or
+    matchers:
+      - type: regex
+        name: regexSite
+        regex:
+          - '(?i)access.to.this.page.has.been.denied'
+          - '(?i)http(s)?://(www.)?anotheroneblocked.\w+.whywasiblocked'
+        condition: or
+        part: response
+
+      - type: word
+        name: wordSiteBody
+        part: body
+        words:
+          - "bad_text_in_body"
+
+      - type: word
+        name: wordSiteHead
+        part: header
+        condition: or
+        words:
+          - "text_in_head"
+          - "other_in_head"

tests/test_waf_check.py

@@ -0,0 +1,107 @@
+import os
+import unittest
+from unittest.mock import patch, Mock
+import requests
+from requests.structures import CaseInsensitiveDict
+import yaml
+
+from sherlock_project import waf_check
+
+
+TEMPLATE_BODY_PATH: str = os.path.join(os.path.dirname(__file__), 'mocks', 'global_waf_detect.yaml')
+
+def side_effect(url, **kwargs) -> Mock:
+    if url == waf_check.NUCLEI_FINGERPRINT_URL:
+        with open(TEMPLATE_BODY_PATH, 'r', encoding='utf-8') as file:
+            template_body: str = file.read()
+        mock_response: Mock = Mock()
+        mock_response.status_code = 200
+        mock_response.text = template_body
+        return mock_response
+    raise RuntimeError("Unexpected URL")
+
+class TestWafCheck(unittest.TestCase):
+
+    @patch('sherlock_project.waf_check.requests.get')
+    def test_fetch_nuclei_fingerprints(self, mock_requests_get): # type: ignore
+        mock_requests_get.side_effect = side_effect
+
+        result = waf_check.fetch_nuclei_fingerprints()
+
+        with open(TEMPLATE_BODY_PATH, 'r', encoding='utf-8') as file:
+            template_body: str = file.read()
+
+        expected: list[dict[str, str | list[str]]] = yaml.safe_load(template_body)['http'][0]['matchers']
+        self.assertEqual(result, expected)
+
+    def test_nuclei_regex_check(self):
+        mock_res: requests.Response = requests.Response()
+        mock_res.status_code = 200
+        mock_res._content = b"This is a test response with Test-Regex in the body."
+        mock_res.headers = CaseInsensitiveDict({
+            'Content-Type': 'text/html',
+            'Server': 'TestServer'
+        })
+        matcher: dict[str, str | list[str]] = {
+            'type': 'regex',
+            'name': 'test-regex',
+            'part': 'body',
+            'regex': [r'(?i)not-present'],
+            'condition': 'or'
+        }
+        self.assertFalse(waf_check._check_nuclei_regex(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['regex'] = [r'(?i)TeSt-REgEx']
+        self.assertTrue(waf_check._check_nuclei_regex(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['regex'] = [r'(?i)TeSt-REgEx', r'(?i)Not-Present']
+        self.assertTrue(waf_check._check_nuclei_regex(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['condition'] = 'and'
+        self.assertFalse(waf_check._check_nuclei_regex(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['part'] = 'header'
+        matcher['regex'] = [r'(?i)testserver']
+        self.assertTrue(waf_check._check_nuclei_regex(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['part'] = 'response'
+        self.assertTrue(waf_check._check_nuclei_regex(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['regex'] = [r'(?i)not-present']
+        self.assertFalse(waf_check._check_nuclei_regex(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+    def test_nuclei_words_check(self):
+        mock_res: requests.Response = requests.Response()
+        mock_res.status_code = 200
+        mock_res._content = b"This is a test response with test-words in the body."
+        mock_res.headers = CaseInsensitiveDict({
+            'Content-Type': 'text/html',
+            'Server': 'TestServer'
+        })
+        matcher: dict[str, str | list[str]] = {
+            'type': 'word',
+            'name': 'test-word',
+            'part': 'body',
+            'words': ['not-present'],
+            'condition': 'or'
+        }
+        self.assertFalse(waf_check._check_nuclei_words(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['words'] = ['test-word']
+        self.assertTrue(waf_check._check_nuclei_words(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['words'] = ['test-word', 'Not-Present']
+        self.assertTrue(waf_check._check_nuclei_words(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['condition'] = 'and'
+        self.assertFalse(waf_check._check_nuclei_words(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['part'] = 'header'
+        matcher['words'] = ['testserver']
+        self.assertFalse(waf_check._check_nuclei_words(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['words'] = ['TestServer']
+        self.assertTrue(waf_check._check_nuclei_words(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]
+
+        matcher['part'] = 'response'
+        self.assertTrue(waf_check._check_nuclei_words(matcher, mock_res)) # pyright: ignore[reportPrivateUsage]