[ie/youtube] Add web_embedded client for age-restricted videos (#13089)

Authored by: bashonly

.github/workflows/build.yml

@@ -192,7 +192,7 @@ jobs:
         with:
           path: ./repo
       - name: Virtualized Install, Prepare & Build
-        uses: yt-dlp/run-on-arch-action@v2
+        uses: yt-dlp/run-on-arch-action@v3
         with:
           # Ref: https://github.com/uraimo/run-on-arch-action/issues/55
           env: |
@@ -411,7 +411,7 @@ jobs:
         run: | # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py --include curl-cffi
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.11.1-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.13.0-py3-none-any.whl"
 
       - name: Prepare
         run: |
@@ -460,7 +460,7 @@ jobs:
         run: |
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.11.1-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.13.0-py3-none-any.whl"
 
       - name: Prepare
         run: |

README.md

@@ -1792,7 +1792,7 @@ The following extractors use this feature:
 #### youtube
 * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
 * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
-* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
+* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only works if the video is embeddable. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
 * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player), `initial_data` (skip initial data/next ep request). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause issues such as missing formats or metadata.  See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) and [#12826](https://github.com/yt-dlp/yt-dlp/issues/12826) for more details
 * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
 * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)

pyproject.toml

@@ -82,7 +82,7 @@ test = [
     "pytest-rerunfailures~=14.0",
 ]
 pyinstaller = [
-    "pyinstaller>=6.11.1",  # Windows temp cleanup fixed in 6.11.1
+    "pyinstaller>=6.13.0",  # Windows temp cleanup fixed in 6.13.0
 ]
 
 [project.urls]

yt_dlp/extractor/bitchute.py

@@ -1,30 +1,32 @@
 import functools
+import json
 import re
 
 from .common import InfoExtractor
 from ..networking import HEADRequest
+from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     OnDemandPagedList,
     clean_html,
-    extract_attributes,
+    determine_ext,
+    format_field,
     get_element_by_class,
-    get_element_by_id,
-    get_element_html_by_class,
     get_elements_html_by_class,
     int_or_none,
     orderedSet,
     parse_count,
     parse_duration,
-    traverse_obj,
-    unified_strdate,
+    parse_iso8601,
+    url_or_none,
     urlencode_postdata,
     urljoin,
 )
+from ..utils.traversal import traverse_obj
 
 
 class BitChuteIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?:video|embed|torrent/[^/?#]+)/(?P<id>[^/?#&]+)'
     _EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
     _TESTS = [{
         'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
@@ -34,12 +36,17 @@ class BitChuteIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'This is the first video on #BitChute !',
             'description': 'md5:a0337e7b1fe39e32336974af8173a034',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'thumbnail': r're:https?://.+/.+\.jpg$',
             'uploader': 'BitChute',
             'upload_date': '20170103',
             'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
             'channel': 'BitChute',
             'channel_url': 'https://www.bitchute.com/channel/bitchute/',
+            'uploader_id': 'I5NgtHZn9vPj',
+            'channel_id': '1VBwRfyNcKdX',
+            'view_count': int,
+            'duration': 16.0,
+            'timestamp': 1483425443,
         },
     }, {
         # test case: video with different channel and uploader
@@ -49,13 +56,18 @@ class BitChuteIE(InfoExtractor):
             'id': 'Yti_j9A-UZ4',
             'ext': 'mp4',
             'title': 'Israel at War | Full Measure',
-            'description': 'md5:38cf7bc6f42da1a877835539111c69ef',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'md5:e60198b89971966d6030d22b3268f08f',
+            'thumbnail': r're:https?://.+/.+\.jpg$',
             'uploader': 'sharylattkisson',
             'upload_date': '20231106',
             'uploader_url': 'https://www.bitchute.com/profile/9K0kUWA9zmd9/',
             'channel': 'Full Measure with Sharyl Attkisson',
             'channel_url': 'https://www.bitchute.com/channel/sharylattkisson/',
+            'uploader_id': '9K0kUWA9zmd9',
+            'channel_id': 'NpdxoCRv3ZLb',
+            'view_count': int,
+            'duration': 554.0,
+            'timestamp': 1699296106,
         },
     }, {
         # video not downloadable in browser, but we can recover it
@@ -66,25 +78,21 @@ class BitChuteIE(InfoExtractor):
             'ext': 'mp4',
             'filesize': 71537926,
             'title': 'STYXHEXENHAMMER666 - Election Fraud, Clinton 2020, EU Armies, and Gun Control',
-            'description': 'md5:228ee93bd840a24938f536aeac9cf749',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'md5:2029c7c212ccd4b040f52bb2d036ef4e',
+            'thumbnail': r're:https?://.+/.+\.jpg$',
             'uploader': 'BitChute',
             'upload_date': '20181113',
             'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
             'channel': 'BitChute',
             'channel_url': 'https://www.bitchute.com/channel/bitchute/',
+            'uploader_id': 'I5NgtHZn9vPj',
+            'channel_id': '1VBwRfyNcKdX',
+            'view_count': int,
+            'duration': 1701.0,
+            'tags': ['bitchute'],
+            'timestamp': 1542130287,
         },
         'params': {'check_formats': None},
-    }, {
-        # restricted video
-        'url': 'https://www.bitchute.com/video/WEnQU7XGcTdl/',
-        'info_dict': {
-            'id': 'WEnQU7XGcTdl',
-            'ext': 'mp4',
-            'title': 'Impartial Truth - Ein Letzter Appell an die Vernunft',
-        },
-        'params': {'skip_download': True},
-        'skip': 'Georestricted in DE',
     }, {
         'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
         'only_matching': True,
@@ -96,11 +104,8 @@ class BitChuteIE(InfoExtractor):
         'only_matching': True,
     }]
     _GEO_BYPASS = False
-
-    _HEADERS = {
-        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36',
-        'Referer': 'https://www.bitchute.com/',
-    }
+    _UPLOADER_URL_TMPL = 'https://www.bitchute.com/profile/%s/'
+    _CHANNEL_URL_TMPL = 'https://www.bitchute.com/channel/%s/'
 
     def _check_format(self, video_url, video_id):
         urls = orderedSet(
@@ -112,7 +117,7 @@ class BitChuteIE(InfoExtractor):
         for url in urls:
             try:
                 response = self._request_webpage(
-                    HEADRequest(url), video_id=video_id, note=f'Checking {url}', headers=self._HEADERS)
+                    HEADRequest(url), video_id=video_id, note=f'Checking {url}')
             except ExtractorError as e:
                 self.to_screen(f'{video_id}: URL is invalid, skipping: {e.cause}')
                 continue
@@ -121,54 +126,79 @@ class BitChuteIE(InfoExtractor):
                 'filesize': int_or_none(response.headers.get('Content-Length')),
             }
 
-    def _raise_if_restricted(self, webpage):
-        page_title = clean_html(get_element_by_class('page-title', webpage)) or ''
-        if re.fullmatch(r'(?:Channel|Video) Restricted', page_title):
-            reason = clean_html(get_element_by_id('page-detail', webpage)) or page_title
-            self.raise_geo_restricted(reason)
-
-    @staticmethod
-    def _make_url(html):
-        path = extract_attributes(get_element_html_by_class('spa', html) or '').get('href')
-        return urljoin('https://www.bitchute.com', path)
+    def _call_api(self, endpoint, data, display_id, fatal=True):
+        note = endpoint.rpartition('/')[2]
+        try:
+            return self._download_json(
+                f'https://api.bitchute.com/api/beta/{endpoint}', display_id,
+                f'Downloading {note} API JSON', f'Unable to download {note} API JSON',
+                data=json.dumps(data).encode(),
+                headers={
+                    'Accept': 'application/json',
+                    'Content-Type': 'application/json',
+                })
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 403:
+                errors = '. '.join(traverse_obj(e.cause.response.read().decode(), (
+                    {json.loads}, 'errors', lambda _, v: v['context'] == 'reason', 'message', {str})))
+                if errors and 'location' in errors:
+                    # Can always be fatal since the video/media call will reach this code first
+                    self.raise_geo_restricted(errors)
+            if fatal:
+                raise
+            self.report_warning(e.msg)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(
-            f'https://old.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
-
-        self._raise_if_restricted(webpage)
-        publish_date = clean_html(get_element_by_class('video-publish-date', webpage))
-        entries = self._parse_html5_media_entries(url, webpage, video_id)
+        data = {'video_id': video_id}
+        media_url = self._call_api('video/media', data, video_id)['media_url']
 
         formats = []
-        for format_ in traverse_obj(entries, (0, 'formats', ...)):
+        if determine_ext(media_url) == 'm3u8':
+            formats.extend(
+                self._extract_m3u8_formats(media_url, video_id, 'mp4', m3u8_id='hls', live=True))
+        else:
             if self.get_param('check_formats') is not False:
-                format_.update(self._check_format(format_.pop('url'), video_id) or {})
-                if 'url' not in format_:
-                    continue
-            formats.append(format_)
+                if fmt := self._check_format(media_url, video_id):
+                    formats.append(fmt)
+            else:
+                formats.append({'url': media_url})
 
         if not formats:
             self.raise_no_formats(
                 'Video is unavailable. Please make sure this video is playable in the browser '
                 'before reporting this issue.', expected=True, video_id=video_id)
 
-        details = get_element_by_class('details', webpage) or ''
-        uploader_html = get_element_html_by_class('creator', details) or ''
-        channel_html = get_element_html_by_class('name', details) or ''
+        video = self._call_api('video', data, video_id, fatal=False)
+        channel = None
+        if channel_id := traverse_obj(video, ('channel', 'channel_id', {str})):
+            channel = self._call_api('channel', {'channel_id': channel_id}, video_id, fatal=False)
 
         return {
+            **traverse_obj(video, {
+                'title': ('video_name', {str}),
+                'description': ('description', {str}),
+                'thumbnail': ('thumbnail_url', {url_or_none}),
+                'channel': ('channel', 'channel_name', {str}),
+                'channel_id': ('channel', 'channel_id', {str}),
+                'channel_url': ('channel', 'channel_url', {urljoin('https://www.bitchute.com/')}),
+                'uploader_id': ('profile_id', {str}),
+                'uploader_url': ('profile_id', {format_field(template=self._UPLOADER_URL_TMPL)}, filter),
+                'timestamp': ('date_published', {parse_iso8601}),
+                'duration': ('duration', {parse_duration}),
+                'tags': ('hashtags', ..., {str}, filter, all, filter),
+                'view_count': ('view_count', {int_or_none}),
+                'is_live': ('state_id', {lambda x: x == 'live'}),
+            }),
+            **traverse_obj(channel, {
+                'channel': ('channel_name', {str}),
+                'channel_id': ('channel_id', {str}),
+                'channel_url': ('url_slug', {format_field(template=self._CHANNEL_URL_TMPL)}, filter),
+                'uploader': ('profile_name', {str}),
+                'uploader_id': ('profile_id', {str}),
+                'uploader_url': ('profile_id', {format_field(template=self._UPLOADER_URL_TMPL)}, filter),
+            }),
             'id': video_id,
-            'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
-            'description': self._og_search_description(webpage, default=None),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader': clean_html(uploader_html),
-            'uploader_url': self._make_url(uploader_html),
-            'channel': clean_html(channel_html),
-            'channel_url': self._make_url(channel_html),
-            'upload_date': unified_strdate(self._search_regex(
-                r'at \d+:\d+ UTC on (.+?)\.', publish_date, 'upload date', fatal=False)),
             'formats': formats,
         }
 
@@ -190,7 +220,7 @@ class BitChuteChannelIE(InfoExtractor):
                     'ext': 'mp4',
                     'title': 'This is the first video on #BitChute !',
                     'description': 'md5:a0337e7b1fe39e32336974af8173a034',
-                    'thumbnail': r're:^https?://.*\.jpg$',
+                    'thumbnail': r're:https?://.+/.+\.jpg$',
                     'uploader': 'BitChute',
                     'upload_date': '20170103',
                     'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
@@ -198,6 +228,9 @@ class BitChuteChannelIE(InfoExtractor):
                     'channel_url': 'https://www.bitchute.com/channel/bitchute/',
                     'duration': 16,
                     'view_count': int,
+                    'uploader_id': 'I5NgtHZn9vPj',
+                    'channel_id': '1VBwRfyNcKdX',
+                    'timestamp': 1483425443,
                 },
             },
         ],
@@ -213,6 +246,7 @@ class BitChuteChannelIE(InfoExtractor):
             'title': 'Bruce MacDonald and "The Light of Darkness"',
             'description': 'md5:747724ef404eebdfc04277714f81863e',
         },
+        'skip': '404 Not Found',
     }, {
         'url': 'https://old.bitchute.com/playlist/wV9Imujxasw9/',
         'only_matching': True,

yt_dlp/extractor/youtube/_video.py

@@ -3115,9 +3115,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 else:
                     prs.append(pr)
 
+            # web_embedded can work around age-gate and age-verification for some embeddable videos
+            if self._is_agegated(pr) and variant != 'web_embedded':
+                append_client(f'web_embedded.{base_client}')
+            # Unauthenticated users will only get web_embedded client formats if age-gated
+            if self._is_agegated(pr) and not self.is_authenticated:
+                self.to_screen(
+                    f'{video_id}: This video is age-restricted; some formats may be missing '
+                    f'without authentication. {self._youtube_login_hint}', only_once=True)
+
             # EU countries require age-verification for accounts to access age-restricted videos
             # If account is not age-verified, _is_agegated() will be truthy for non-embedded clients
-            if self.is_authenticated and self._is_agegated(pr):
+            embedding_is_disabled = variant == 'web_embedded' and self._is_unplayable(pr)
+            if self.is_authenticated and (self._is_agegated(pr) or embedding_is_disabled):
                 self.to_screen(
                     f'{video_id}: This video is age-restricted and YouTube is requiring '
                     'account age-verification; some formats may be missing', only_once=True)