Merge pull request #2919 from quan-nguyen-2110/fix-cracked-forum-false-positive

Fix Cracked Forum false positives

.github/workflows/validate_modified_targets.yml

@@ -20,6 +20,7 @@ jobs:
           # Checkout the base branch but fetch all history to avoid a second fetch call
           ref: ${{ github.base_ref }}
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Set up Python
         uses: actions/setup-python@v6
@@ -90,11 +91,11 @@ jobs:
       # --- The rest of the steps below are unchanged ---
 
       - name: Validate modified targets
-        if: steps.discover-modified.outputs.changed_targets != ''
-        continue-on-error: true
+        env:
+          CHANGED_TARGETS: ${{ steps.discover-modified.outputs.changed_targets }}
         run: |
           poetry run pytest -q --tb no -rA -m validate_targets -n 20 \
-            --chunked-sites "${{ steps.discover-modified.outputs.changed_targets }}" \
+            --chunked-sites "$CHANGED_TARGETS" \
             --junitxml=validation_results.xml
 
       - name: Prepare validation summary

pyproject.toml

@@ -8,7 +8,7 @@ source = "init"
 
 [tool.poetry]
 name = "sherlock-project"
-version = "0.16.0"
+version = "0.16.1"
 description = "Hunt down social media accounts by username across social networks"
 license = "MIT"
 authors = [

sherlock_project/resources/data.json

@@ -159,6 +159,7 @@
     "errorType": "status_code",
     "url": "https://www.artstation.com/{}",
     "urlMain": "https://www.artstation.com/",
+    "urlProbe": "https://www.artstation.com/users/{}.json",
     "username_claimed": "Blue"
   },
   "Asciinema": {
@@ -404,6 +405,13 @@
     "urlMain": "https://carbonmade.com/",
     "username_claimed": "jenny"
   },
+  "Carrd": {
+    "errorType": "status_code",
+    "regexCheck": "^[a-zA-Z0-9_-]{3,50}$",
+    "url": "https://{}.carrd.co/",
+    "urlMain": "https://carrd.co/",
+    "username_claimed": "blue"
+  },
   "Career.habr": {
     "errorMsg": "<h1>\u041e\u0448\u0438\u0431\u043a\u0430 404</h1>",
     "errorType": "message",
@@ -602,10 +610,9 @@
     "username_claimed": "blue"
   },
   "Cracked Forum": {
-    "errorMsg": "The member you specified is either invalid or doesn't exist",
-    "errorType": "message",
-    "url": "https://cracked.sh/{}",
-    "urlMain": "https://cracked.sh/",
+    "errorType": "status_code",
+    "url": "https://cracked.ax/{}",
+    "urlMain": "https://cracked.ax/",
     "username_claimed": "Blue"
   },
   "Credly": {
@@ -952,7 +959,8 @@
     "username_claimed": "blue"
   },
   "GeeksforGeeks": {
-    "errorType": "status_code",
+    "errorMsg": "false   | GeeksforGeeks Profile",
+    "errorType": "message",
     "url": "https://auth.geeksforgeeks.org/user/{}",
     "urlMain": "https://www.geeksforgeeks.org/",
     "username_claimed": "adam"
@@ -1526,7 +1534,8 @@
     "username_claimed": "lottiefiles"
   },
   "LushStories": {
-    "errorType": "status_code",
+    "errorType": "response_url",
+    "errorUrl": "https://www.lushstories.com/login",
     "isNSFW": true,
     "url": "https://www.lushstories.com/profile/{}",
     "urlMain": "https://www.lushstories.com/",
@@ -2279,6 +2288,13 @@
     "urlMain": "https://sourceforge.net/",
     "username_claimed": "blue"
   },
+  "SpaceHey": {
+    "errorType": "message",
+    "errorMsg": "Not Found (Error 404) | SpaceHey",
+    "url": "https://spacehey.com/{}",
+    "urlMain": "https://spacehey.com/",
+    "username_claimed": "blue"
+  },
   "SoylentNews": {
     "errorMsg": "The user you requested does not exist, no matter how much you wish this might be the case.",
     "errorType": "message",
@@ -2376,6 +2392,13 @@
     "urlMain": "https://www.strava.com/",
     "username_claimed": "blue"
   },
+  "Substack": {
+    "errorType": "status_code",
+    "regexCheck": "^[a-zA-Z0-9][a-zA-Z0-9_-]{1,60}$",
+    "url": "https://{}.substack.com/",
+    "urlMain": "https://substack.com/",
+    "username_claimed": "green"
+  },
   "SublimeForum": {
     "errorType": "status_code",
     "url": "https://forum.sublimetext.com/u/{}",
@@ -2827,8 +2850,10 @@
   },
   "akniga": {
     "errorType": "status_code",
+    "errorCode": 404,
+    "request_method": "GET",
     "url": "https://akniga.org/profile/{}",
-    "urlMain": "https://akniga.org/profile/blue/",
+    "urlMain": "https://akniga.org/",
     "username_claimed": "blue"
   },
   "authorSTREAM": {

sherlock_project/sherlock.py

@@ -136,6 +136,9 @@ def get_response(request_future, error_type, social_network):
     except requests.exceptions.RequestException as err:
         error_context = "Unknown Error"
         exception_text = str(err)
+    except UnicodeError as err:
+        error_context = "Encoding Error"
+        exception_text = str(err)
 
     return response, error_context, exception_text
 

tests/test_unicode.py

@@ -0,0 +1,47 @@
+"""Tests for handling usernames with special/unicode characters."""
+
+from concurrent.futures import Future
+
+from sherlock_project.sherlock import get_response
+
+
+def _make_future_with_exception(exc):
+    """Create a Future that raises the given exception."""
+    future = Future()
+    future.set_exception(exc)
+    return future
+
+
+def test_get_response_handles_unicode_decode_error():
+    """Regression test for issue #2730.
+
+    Usernames with special characters (e.g. 'Émile') can trigger a
+    UnicodeDecodeError inside the requests library during redirect
+    handling. This must not crash the program.
+    """
+    future = _make_future_with_exception(
+        UnicodeDecodeError("utf-8", b"\xe9", 0, 1, "invalid continuation byte")
+    )
+    response, error_context, exception_text = get_response(
+        request_future=future,
+        error_type=["status_code"],
+        social_network="TestSite",
+    )
+    assert response is None
+    assert error_context == "Encoding Error"
+    assert "utf-8" in exception_text
+
+
+def test_get_response_handles_unicode_encode_error():
+    """UnicodeEncodeError should also be caught (subclass of UnicodeError)."""
+    future = _make_future_with_exception(
+        UnicodeEncodeError("ascii", "É", 0, 1, "ordinal not in range(128)")
+    )
+    response, error_context, exception_text = get_response(
+        request_future=future,
+        error_type=["status_code"],
+        social_network="TestSite",
+    )
+    assert response is None
+    assert error_context == "Encoding Error"
+    assert "ascii" in exception_text

tests/test_ux.py

@@ -4,7 +4,7 @@ from sherlock_interactives import Interactives
 from sherlock_interactives import InteractivesSubprocessError
 
 def test_remove_nsfw(sites_obj):
-    nsfw_target: str = 'Pornhub'
+    nsfw_target: str = 'Xvideos'
     assert nsfw_target in {site.name: site.information for site in sites_obj}
     sites_obj.remove_nsfw_sites()
     assert nsfw_target not in {site.name: site.information for site in sites_obj}
@@ -12,8 +12,8 @@ def test_remove_nsfw(sites_obj):
 
 # Parametrized sites should *not* include Motherless, which is acting as the control
 @pytest.mark.parametrize('nsfwsites', [
-    ['Pornhub'],
-    ['Pornhub', 'Xvideos'],
+    ['Xvideos'],
+    ['Xvideos', 'Erome'],
 ])
 def test_nsfw_explicit_selection(sites_obj, nsfwsites):
     for site in nsfwsites: