.actor/README.md

@@ -65,7 +65,7 @@ The Actor provides three types of outputs:
 | Field | Type | Required | Description |
 |-------|------|----------|-------------|
 | `username` | string | Yes | Username the search was conducted for |
-| `links` | array | Yes | Array with found links to the social media |
+| `links` | arrray | Yes | Array with found links to the social media |
 | `links[]`| string | No | URL to the account
 
 ### Example Dataset Item (JSON)

.github/CODEOWNERS

@@ -1,5 +1,5 @@
 ### REPOSITORY
-/.github/CODEOWNERS @sdushantha @ppfeister
+/.github/CODEOWNERS @sdushantha
 /.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:false_positive_exclusions.txt >/dev/null 2>&1; then
+          if git show origin/exclusions:exclusions.txt >/dev/null 2>&1; then
             # If the exclusions branch and file exist, compare
-            if git diff --quiet origin/exclusions -- false_positive_exclusions.txt; then
+            if git diff --quiet origin/exclusions -- exclusions.txt; then
               echo "exclusions_changed=false" >> "$GITHUB_OUTPUT"
             else
               echo "exclusions_changed=true" >> "$GITHUB_OUTPUT"
@@ -71,19 +71,10 @@ 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 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

@@ -11,7 +11,6 @@ on:
       - '**/*.py'
       - '**/*.ini'
       - '**/*.toml'
-      - 'Dockerfile'
   push:
     branches:
       - master
@@ -22,13 +21,11 @@ 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
@@ -44,8 +41,7 @@ jobs:
   tox-matrix:
     runs-on: ${{ matrix.os }}
     strategy:
-      # We want to know what specicic versions it fails on
-      fail-fast: false
+      fail-fast: false # We want to know what specicic versions it fails on
       matrix:
         os: [
           ubuntu-latest,
@@ -71,22 +67,3 @@ jobs:
           pip install tox-gh-actions
       - name: Run tox
         run: tox
-  docker-build-test:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Get version from pyproject.toml
-        id: get-version
-        run: |
-          VERSION=$(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

@@ -1,126 +0,0 @@
-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:
-          # Checkout the base branch but fetch all history to avoid a second fetch call
-          ref: ${{ github.base_ref }}
-          fetch-depth: 0
-
-      - name: Set up Python
-        uses: actions/setup-python@v6
-        with:
-          python-version: "3.13"
-
-      - name: Install Poetry
-        uses: abatilo/actions-poetry@v4
-        with:
-          poetry-version: "latest"
-
-      - name: Install dependencies
-        run: |
-          poetry install --no-interaction --with dev
-
-      - name: Prepare JSON versions for comparison
-        run: |
-          # Fetch only the PR's branch head (single network call in this step)
-          git fetch origin pull/${{ github.event.pull_request.number }}/head:pr
-
-          # Find the merge-base commit between the target branch and the PR branch
-          MERGE_BASE=$(git merge-base origin/${{ github.base_ref }} pr)
-          echo "Comparing PR head against merge-base commit: $MERGE_BASE"
-
-          # Safely extract the file from the PR's head and the merge-base commit
-          git show pr:sherlock_project/resources/data.json > data.json.head
-          git show $MERGE_BASE:sherlock_project/resources/data.json > data.json.base
-
-          # CRITICAL FIX: Overwrite the checked-out data.json with the one from the PR
-          # This ensures that pytest runs against the new, updated file.
-          cp data.json.head sherlock_project/resources/data.json
-
-      - name: Discover modified targets
-        id: discover-modified
-        run: |
-          CHANGED=$(
-            python - <<'EOF'
-          import json
-          import sys
-          try:
-              with open("data.json.base") as f: base = json.load(f)
-              with open("data.json.head") as f: head = json.load(f)
-          except FileNotFoundError as e:
-              print(f"Error: Could not find {e.filename}", file=sys.stderr)
-              sys.exit(1)
-          except json.JSONDecodeError as e:
-              print(f"Error: Could not decode JSON from a file - {e}", file=sys.stderr)
-              sys.exit(1)
-
-          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" >> "$GITHUB_OUTPUT"
-
-      - name: Validate remote manifest against local schema
-        if: steps.discover-modified.outputs.changed_targets != ''
-        run: |
-          poetry run pytest tests/test_manifest.py::test_validate_manifest_against_local_schema
-
-      # --- The rest of the steps below are unchanged ---
-
-      - name: Validate modified targets
-        if: steps.discover-modified.outputs.changed_targets != ''
-        continue-on-error: true
-        run: |
-          poetry run pytest -q --tb no -rA -m validate_targets -n 20 \
-            --chunked-sites "${{ 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/site-list.py

@@ -1,45 +1,39 @@
 #!/usr/bin/env python
 # This module generates the listing of supported sites which can be found in
-# sites.mdx. It also organizes all the sites in alphanumeric order
+# sites.md. It also organizes all the sites in alphanumeric order
 import json
 import os
 
+
 DATA_REL_URI: str = "sherlock_project/resources/data.json"
 
-DEFAULT_ENCODING = "utf-8"
-
 # Read the data.json file
-with open(DATA_REL_URI, "r", encoding=DEFAULT_ENCODING) as data_file:
+with open(DATA_REL_URI, "r", encoding="utf-8") as data_file:
     data: dict = json.load(data_file)
 
 # Removes schema-specific keywords for proper processing
-social_networks = data.copy()
+social_networks: dict = dict(data)
 social_networks.pop('$schema', None)
 
 # Sort the social networks in alphanumeric order
-social_networks = sorted(social_networks.items())
+social_networks: list = sorted(social_networks.items())
 
 # Make output dir where the site list will be written
 os.mkdir("output")
 
-# Write the list of supported sites to sites.mdx
-with open("output/sites.mdx", "w", encoding=DEFAULT_ENCODING) as site_file:
-    site_file.write("---\n")
-    site_file.write("title: 'List of supported sites'\n")
-    site_file.write("sidebarTitle: 'Supported sites'\n")
-    site_file.write("icon: 'globe'\n")
-    site_file.write("description: 'Sherlock currently supports **400+** sites'\n")
-    site_file.write("---\n\n")
-
+# Write the list of supported sites to sites.md
+with open("output/sites.mdx", "w") as site_file:
+    site_file.write("---\ntitle: 'List of supported sites'\nsidebarTitle: 'Supported sites'\nicon: 'globe'\ndescription: 'Sherlock currently supports **400+** sites'\n---\n\n")
     for social_network, info in social_networks:
         url_main = info["urlMain"]
         is_nsfw = "**(NSFW)**" if info.get("isNSFW") else ""
         site_file.write(f"1. [{social_network}]({url_main}) {is_nsfw}\n")
 
 # Overwrite the data.json file with sorted data
-with open(DATA_REL_URI, "w", encoding=DEFAULT_ENCODING) as data_file:
+with open(DATA_REL_URI, "w") as data_file:
     sorted_data = json.dumps(data, indent=2, sort_keys=True)
     data_file.write(sorted_data)
-    data_file.write("\n")  # Keep the newline after writing data
+    data_file.write("\n")
 
 print("Finished updating supported site listing!")
+

devel/summarize_site_validation.py

@@ -1,72 +0,0 @@
-#!/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)

docs/README.md

@@ -124,7 +124,7 @@ Thank you to everyone who has contributed to Sherlock! ❤️
   <img src="https://contrib.rocks/image?&columns=25&max=10000&&repo=sherlock-project/sherlock" alt="contributors"/>
 </a>
 
-## Star History
+## Star history
 
 <picture>
   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=sherlock-project/sherlock&type=Date&theme=dark" />

pyproject.toml

@@ -8,7 +8,8 @@ source = "init"
 
 [tool.poetry]
 name = "sherlock-project"
-version = "0.16.0"
+# single source of truth for version is __init__.py
+version = "0"
 description = "Hunt down social media accounts by username across social networks"
 license = "MIT"
 authors = [
@@ -29,10 +30,6 @@ classifiers = [
     "Natural Language :: English",
     "Operating System :: OS Independent",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Programming Language :: Python :: 3.13",
     "Topic :: Security"
 ]
 homepage = "https://sherlockproject.xyz/"
@@ -50,9 +47,12 @@ 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"
-tomli = "^2.2.1"
+
+[tool.poetry.extras]
+tor = ["torrequest"]
 
 [tool.poetry.group.dev.dependencies]
 jsonschema = "^4.0.0"
@@ -60,9 +60,5 @@ 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

@@ -5,26 +5,11 @@ 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__     = get_version()
+__version__     = "0.16.0"
 
 forge_api_latest_release = "https://api.github.com/repos/sherlock-project/sherlock/releases/latest"

sherlock_project/resources/data.schema.json

@@ -1,149 +1,80 @@
 {
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "title": "Sherlock Target Manifest",
-  "description": "Social media targets to probe for the existence of known usernames",
-  "type": "object",
-  "properties": {
-    "$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": "#/$defs/tag" } }
-          ]
-        },
-        "request_method": {
-          "type": "string",
-          "enum": ["GET", "POST", "HEAD", "PUT"]
-        },
-        "errorType": {
-          "oneOf": [
-            {
-              "type": "string",
-              "enum": ["message", "response_url", "status_code"]
+    "$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": {
+                    "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" }
             },
-            {
-              "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": "array",
-                  "contains": { "const": "message" }
+            "dependencies": {
+                "errorMsg": {
+                    "properties" : { "errorType": { "const": "message" } }
+                },
+                "errorUrl": {
+                    "properties": { "errorType": { "const": "response_url" } }
+                },
+                "errorCode": {
+                    "properties": { "errorType": { "const": "status_code" } }
                 }
-              }
-            }
-          ]
-        },
-        "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" }
-                }
-              }
-            }
-          ]
+            },
+            "if": { "properties": { "errorType": { "const": "message" } } },
+            "then": { "required": [ "errorMsg" ] },
+            "else": {
+                "if": { "properties": { "errorType": { "const": "response_url" } } },
+                "then": { "required": [ "errorUrl" ] }
+            },
+            "additionalProperties": false
         }
-      },
-      "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" ] }
     }
-  },
-  "additionalProperties": false,
-  "$defs": {
-    "tag": { "type": "string", "enum": ["adult", "gaming"] }
-  }
 }

sherlock_project/sherlock.py

@@ -171,6 +171,8 @@ 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,
@@ -186,6 +188,8 @@ 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.
@@ -206,9 +210,32 @@ 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())
 
-    # Normal requests
-    underlying_session = requests.session()
+        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()
 
     # Limit number of workers to 20.
     # This is probably vastly overkill.
@@ -332,10 +359,15 @@ 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)
@@ -349,8 +381,6 @@ 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"]
@@ -395,60 +425,58 @@ def sherlock(
         elif any(hitMsg in r.text for hitMsg in WAFHitMsgs):
             query_status = QueryStatus.WAF
 
-        else:
-            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
+        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 "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 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
 
-                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]
 
-                    # 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 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 dump_response:
             print("+++++++++++++++++++++")
@@ -568,6 +596,22 @@ 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",
@@ -675,22 +719,12 @@ 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 - WILL BE DEPRECATED",
-    )
-
-    parser.add_argument(
-        "--txt",
-        action="store_true",
-        dest="output_txt",
-        default=False,
-        help="Enable creation of a txt file",
+        help="Disable creation of a txt file",
     )
 
     parser.add_argument(
@@ -708,7 +742,7 @@ 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, timeout=10).text
+        latest_release_raw = requests.get(forge_api_latest_release).text
         latest_release_json = json_loads(latest_release_raw)
         latest_remote_tag = latest_release_json["tag_name"]
 
@@ -721,10 +755,22 @@ 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)
@@ -756,7 +802,7 @@ 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, timeout=10).text
+                    pull_request_raw = requests.get(pull_url).text
                     pull_request_json = json_loads(pull_request_raw)
 
                     # Check if it's a valid pull request
@@ -825,6 +871,8 @@ 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,
@@ -840,7 +888,7 @@ def main():
         else:
             result_file = f"{username}.txt"
 
-        if args.output_txt:
+        if not args.no_txt:
             with open(result_file, "w", encoding="utf-8") as file:
                 exists_counter = 0
                 for website_name in results:
@@ -925,8 +973,8 @@ def main():
                 {
                     "username": usernames,
                     "name": names,
-                    "url_main": [f'=HYPERLINK(\"{u}\")' for u in url_main],
-                    "url_user": [f'=HYPERLINK(\"{u}\")' for u in url_user],
+                    "url_main": url_main,
+                    "url_user": url_user,
                     "exists": exists,
                     "http_status": http_status,
                     "response_time_s": response_time_s,

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, timeout=30)
+                response = requests.get(url=data_file_path)
             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, timeout=10)
+                response = requests.get(url=EXCLUSIONS_URL)
                 if response.status_code == 200:
                     exclusions = response.text.splitlines()
                     exclusions = [exclusion.strip() for exclusion in exclusions]

tests/conftest.py

@@ -4,9 +4,9 @@ import urllib
 import pytest
 from sherlock_project.sites import SitesInformation
 
-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}
+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}
     return sites_iterable
 
 @pytest.fixture()
@@ -25,27 +25,9 @@ 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(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
-            }
-
+        sites_info = fetch_local_manifest()
         params = [{name: data} for name, data in sites_info.items()]
         ids = list(sites_info.keys())
         metafunc.parametrize("chunked_sites", params, ids=ids)

tests/test_validate_targets.py

@@ -16,7 +16,6 @@ def set_pattern_upper_bound(pattern: str, upper_bound: int = FALSE_POSITIVE_QUAN
     """Set upper bound for regex patterns that use quantifiers such as `+` `*` or `{n,}`."""
     def replace_upper_bound(match: re.Match) -> str: # type: ignore
         lower_bound: int = int(match.group(1)) if match.group(1) else 0 # type: ignore
-        nonlocal upper_bound
         upper_bound = upper_bound if lower_bound < upper_bound else lower_bound # type: ignore  # noqa: F823
         return f'{{{lower_bound},{upper_bound}}}'