[ie/unsupported] Update unsupported sites (#17085)

Closes #10045
Closes #10368
Closes #16117

Authored by: bashonly

yt_dlp/extractor/_extractors.py

@@ -691,7 +691,6 @@ from .gmanetwork import GMANetworkVideoIE
 from .go import GoIE
 from .godresource import GodResourceIE
 from .godtube import GodTubeIE
-from .gofile import GofileIE
 from .golem import GolemIE
 from .goodgame import GoodGameIE
 from .googledrive import (
@@ -2120,6 +2119,7 @@ from .unitednations import UnitedNationsWebTvIE
 from .unity import UnityIE
 from .unsupported import (
     KnownDRMIE,
+    KnownLiabilityIE,
     KnownPiracyIE,
 )
 from .uol import UOLIE

yt_dlp/extractor/gofile.py

@@ -1,104 +0,0 @@
-import hashlib
-
-from .common import InfoExtractor
-from ..utils import ExtractorError, try_get
-
-
-class GofileIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?gofile\.io/d/(?P<id>[^/]+)'
-    _TESTS = [{
-        'url': 'https://gofile.io/d/AMZyDw',
-        'info_dict': {
-            'id': 'AMZyDw',
-        },
-        'playlist_mincount': 2,
-        'playlist': [{
-            'info_dict': {
-                'id': 'de571ac1-5edc-42e2-8ec2-bdac83ad4a31',
-                'filesize': 928116,
-                'ext': 'mp4',
-                'title': 'nuuh',
-                'release_timestamp': 1638338704,
-                'release_date': '20211201',
-            },
-        }],
-    }, {
-        'url': 'https://gofile.io/d/is8lKr',
-        'info_dict': {
-            'id': 'TMjXd9',
-            'ext': 'mp4',
-        },
-        'playlist_count': 0,
-        'skip': 'No video/audio found at provided URL.',
-    }, {
-        'url': 'https://gofile.io/d/TMjXd9',
-        'info_dict': {
-            'id': 'TMjXd9',
-        },
-        'playlist_count': 1,
-    }, {
-        'url': 'https://gofile.io/d/gqOtRf',
-        'info_dict': {
-            'id': 'gqOtRf',
-        },
-        'playlist_mincount': 1,
-        'params': {
-            'videopassword': 'password',
-        },
-    }]
-    _STATIC_TOKEN = '4fd6sg89d7s6'  # From https://gofile.io/dist/js/config.js
-    _TOKEN = None
-
-    def _real_initialize(self):
-        token = self._get_cookies('https://gofile.io/').get('accountToken')
-        if token:
-            self._TOKEN = token.value
-            return
-
-        account_data = self._download_json(
-            'https://api.gofile.io/accounts', None, 'Getting a new guest account', data=b'{}')
-        self._TOKEN = account_data['data']['token']
-        self._set_cookie('.gofile.io', 'accountToken', self._TOKEN)
-
-    def _entries(self, file_id):
-        query_params = {}
-        if password := self.get_param('videopassword'):
-            query_params['password'] = hashlib.sha256(password.encode()).hexdigest()
-
-        files = self._download_json(
-            f'https://api.gofile.io/contents/{file_id}', file_id, 'Getting filelist',
-            query=query_params, headers={
-                'Authorization': f'Bearer {self._TOKEN}',
-                'X-Website-Token': self._STATIC_TOKEN,
-            })
-
-        status = files['status']
-        if status == 'error-passwordRequired':
-            raise ExtractorError(
-                'This video is protected by a password, use the --video-password option', expected=True)
-        elif status != 'ok':
-            raise ExtractorError(f'{self.IE_NAME} said: status {status}', expected=True)
-
-        found_files = False
-        for file in (try_get(files, lambda x: x['data']['children'], dict) or {}).values():
-            file_type, file_format = file.get('mimetype').split('/', 1)
-            if file_type not in ('video', 'audio') and file_format != 'vnd.mts':
-                continue
-
-            found_files = True
-            file_url = file.get('link')
-            if file_url:
-                yield {
-                    'id': file['id'],
-                    'title': file['name'].rsplit('.', 1)[0],
-                    'url': file_url,
-                    'filesize': file.get('size'),
-                    'release_timestamp': file.get('createTime'),
-                }
-
-        if not found_files:
-            raise ExtractorError('No video/audio found at provided URL.', expected=True)
-
-    def _real_extract(self, url):
-        file_id = self._match_id(url)
-        return self.playlist_result(self._entries(file_id), playlist_id=file_id)

yt_dlp/extractor/unsupported.py

@@ -303,6 +303,7 @@ class KnownPiracyIE(UnsupportedInfoExtractor):
         r'xanimu\.com',
         r'musicdex\.org',
         r'duboku\.io',
+        r'gofile\.io',
     )
 
     _TESTS = [{
@@ -311,9 +312,42 @@ class KnownPiracyIE(UnsupportedInfoExtractor):
     }, {
         'url': 'https://thisav.com/en/terms',
         'only_matching': True,
+    }, {
+        'url': 'https://gofile.io/d/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         raise ExtractorError(
             f'This website is no longer supported since it has been determined to be primarily used for piracy.{LF}'
             f'{self._downloader._format_err("DO NOT", self._downloader.Styles.ERROR)} open issues for it', expected=True)
+
+
+class KnownLiabilityIE(UnsupportedInfoExtractor):
+    """Sites that would be a liability to the project if supported
+
+    In order for this to not end up being a catalog of sketchy sites,
+    only sites that were once supported should be added to this list
+    """
+
+    URLS = (
+        r'motherless\.com',
+        r'suno\.com',
+        r'udio\.com',
+    )
+
+    _TESTS = [{
+        'url': 'https://motherless.com/',
+        'only_matching': True,
+    }, {
+        'url': 'https://suno.com/song/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.udio.com/songs/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        raise ExtractorError(
+            f'This website is not supported and will not be supported.{LF}'
+            f'{self._downloader._format_err("DO NOT", self._downloader.Styles.ERROR)} open issues for it', expected=True)