yt_dlp/extractor/rumble.py

   1 import itertools
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_HTTPError
   6 from ..utils import (
   7     ExtractorError,
   8     UnsupportedError,
   9     clean_html,
  10     determine_ext,
  11     get_element_by_class,
  12     int_or_none,
  13     parse_count,
  14     parse_iso8601,
  15     traverse_obj,
  16     unescapeHTML,
  17 )
  18
  19
  20 class RumbleEmbedIE(InfoExtractor):
  21     _VALID_URL = r'https?://(?:www\.)?rumble\.com/embed/(?:[0-9a-z]+\.)?(?P<id>[0-9a-z]+)'
  22     _EMBED_REGEX = [fr'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>{_VALID_URL})']
  23     _TESTS = [{
  24         'url': 'https://rumble.com/embed/v5pv5f',
  25         'md5': '36a18a049856720189f30977ccbb2c34',
  26         'info_dict': {
  27             'id': 'v5pv5f',
  28             'ext': 'mp4',
  29             'title': 'WMAR 2 News Latest Headlines | October 20, 6pm',
  30             'timestamp': 1571611968,
  31             'upload_date': '20191020',
  32             'channel_url': 'https://rumble.com/c/WMAR',
  33             'channel': 'WMAR',
  34             'thumbnail': 'https://sp.rmbl.ws/s8/1/5/M/z/1/5Mz1a.OvCc-small-WMAR-2-News-Latest-Headline.jpg',
  35             'duration': 234,
  36             'uploader': 'WMAR',
  37             'live_status': 'not_live',
  38         }
  39     }, {
  40         'url': 'https://rumble.com/embed/vslb7v',
  41         'md5': '7418035de1a30a178b8af34dc2b6a52b',
  42         'info_dict': {
  43             'id': 'vslb7v',
  44             'ext': 'mp4',
  45             'title': 'Defense Sec. says US Commitment to NATO Defense \'Ironclad\'',
  46             'timestamp': 1645142135,
  47             'upload_date': '20220217',
  48             'channel_url': 'https://rumble.com/c/CyberTechNews',
  49             'channel': 'CTNews',
  50             'thumbnail': 'https://sp.rmbl.ws/s8/6/7/i/9/h/7i9hd.OvCc.jpg',
  51             'duration': 901,
  52             'uploader': 'CTNews',
  53             'live_status': 'not_live',
  54         }
  55     }, {
  56         'url': 'https://rumble.com/embed/vunh1h',
  57         'info_dict': {
  58             'id': 'vunh1h',
  59             'ext': 'mp4',
  60             'title': '‘Gideon, op zoek naar de waarheid’ including ENG SUBS',
  61             'timestamp': 1647197663,
  62             'upload_date': '20220313',
  63             'channel_url': 'https://rumble.com/user/BLCKBX',
  64             'channel': 'BLCKBX',
  65             'thumbnail': r're:https://.+\.jpg',
  66             'duration': 5069,
  67             'uploader': 'BLCKBX',
  68             'live_status': 'not_live',
  69             'subtitles': {
  70                 'en': [
  71                     {
  72                         'url': r're:https://.+\.vtt',
  73                         'name': 'English',
  74                         'ext': 'vtt'
  75                     }
  76                 ]
  77             },
  78         },
  79         'params': {'skip_download': True}
  80     }, {
  81         'url': 'https://rumble.com/embed/v1essrt',
  82         'info_dict': {
  83             'id': 'v1essrt',
  84             'ext': 'mp4',
  85             'title': 'startswith:lofi hip hop radio - beats to relax/study',
  86             'timestamp': 1661519399,
  87             'upload_date': '20220826',
  88             'channel_url': 'https://rumble.com/c/LofiGirl',
  89             'channel': 'Lofi Girl',
  90             'thumbnail': r're:https://.+\.jpg',
  91             'duration': None,
  92             'uploader': 'Lofi Girl',
  93             'live_status': 'is_live',
  94         },
  95         'params': {'skip_download': True}
  96     }, {
  97         'url': 'https://rumble.com/embed/v1amumr',
  98         'info_dict': {
  99             'id': 'v1amumr',
 100             'ext': 'webm',
 101             'fps': 60,
 102             'title': 'Turning Point USA 2022 Student Action Summit DAY 1  - Rumble Exclusive Live',
 103             'timestamp': 1658518457,
 104             'upload_date': '20220722',
 105             'channel_url': 'https://rumble.com/c/RumbleEvents',
 106             'channel': 'Rumble Events',
 107             'thumbnail': r're:https://.+\.jpg',
 108             'duration': 16427,
 109             'uploader': 'Rumble Events',
 110             'live_status': 'was_live',
 111         },
 112         'params': {'skip_download': True}
 113     }, {
 114         'url': 'https://rumble.com/embed/ufe9n.v5pv5f',
 115         'only_matching': True,
 116     }]
 117
 118     _WEBPAGE_TESTS = [
 119         {
 120             'note': 'Rumble JS embed',
 121             'url': 'https://therightscoop.com/what-does-9-plus-1-plus-1-equal-listen-to-this-audio-of-attempted-kavanaugh-assassins-call-and-youll-get-it',
 122             'md5': '4701209ac99095592e73dbba21889690',
 123             'info_dict': {
 124                 'id': 'v15eqxl',
 125                 'ext': 'mp4',
 126                 'channel': 'Mr Producer Media',
 127                 'duration': 92,
 128                 'title': '911 Audio From The Man Who Wanted To Kill Supreme Court Justice Kavanaugh',
 129                 'channel_url': 'https://rumble.com/c/RichSementa',
 130                 'thumbnail': 'https://sp.rmbl.ws/s8/1/P/j/f/A/PjfAe.OvCc-small-911-Audio-From-The-Man-Who-.jpg',
 131                 'timestamp': 1654892716,
 132                 'uploader': 'Mr Producer Media',
 133                 'upload_date': '20220610',
 134                 'live_status': 'not_live',
 135             }
 136         },
 137     ]
 138
 139     @classmethod
 140     def _extract_embed_urls(cls, url, webpage):
 141         embeds = tuple(super()._extract_embed_urls(url, webpage))
 142         if embeds:
 143             return embeds
 144         return [f'https://rumble.com/embed/{mobj.group("id")}' for mobj in re.finditer(
 145             r'<script>\s*Rumble\(\s*"play"\s*,\s*{\s*[\'"]video[\'"]\s*:\s*[\'"](?P<id>[0-9a-z]+)[\'"]', webpage)]
 146
 147     def _real_extract(self, url):
 148         video_id = self._match_id(url)
 149         video = self._download_json(
 150             'https://rumble.com/embedJS/u3/', video_id,
 151             query={'request': 'video', 'ver': 2, 'v': video_id})
 152
 153         sys_msg = traverse_obj(video, ('sys', 'msg'))
 154         if sys_msg:
 155             self.report_warning(sys_msg, video_id=video_id)
 156
 157         if video.get('live') == 0:
 158             live_status = 'not_live' if video.get('livestream_has_dvr') is None else 'was_live'
 159         elif video.get('live') == 1:
 160             live_status = 'is_upcoming' if video.get('livestream_has_dvr') else 'was_live'
 161         elif video.get('live') == 2:
 162             live_status = 'is_live'
 163         else:
 164             live_status = None
 165
 166         formats = []
 167         for ext, ext_info in (video.get('ua') or {}).items():
 168             for height, video_info in (ext_info or {}).items():
 169                 meta = video_info.get('meta') or {}
 170                 if not video_info.get('url'):
 171                     continue
 172                 if ext == 'hls':
 173                     if meta.get('live') is True and video.get('live') == 1:
 174                         live_status = 'post_live'
 175                     formats.extend(self._extract_m3u8_formats(
 176                         video_info['url'], video_id,
 177                         ext='mp4', m3u8_id='hls', fatal=False, live=live_status == 'is_live'))
 178                     continue
 179                 timeline = ext == 'timeline'
 180                 if timeline:
 181                     ext = determine_ext(video_info['url'])
 182                 formats.append({
 183                     'ext': ext,
 184                     'acodec': 'none' if timeline else None,
 185                     'url': video_info['url'],
 186                     'format_id': '%s-%sp' % (ext, height),
 187                     'format_note': 'Timeline' if timeline else None,
 188                     'fps': None if timeline else video.get('fps'),
 189                     **traverse_obj(meta, {
 190                         'tbr': 'bitrate',
 191                         'filesize': 'size',
 192                         'width': 'w',
 193                         'height': 'h',
 194                     }, expected_type=lambda x: int(x) or None)
 195                 })
 196
 197         subtitles = {
 198             lang: [{
 199                 'url': sub_info['path'],
 200                 'name': sub_info.get('language') or '',
 201             }] for lang, sub_info in (video.get('cc') or {}).items() if sub_info.get('path')
 202         }
 203
 204         author = video.get('author') or {}
 205         thumbnails = traverse_obj(video, ('t', ..., {'url': 'i', 'width': 'w', 'height': 'h'}))
 206         if not thumbnails and video.get('i'):
 207             thumbnails = [{'url': video['i']}]
 208
 209         if live_status in {'is_live', 'post_live'}:
 210             duration = None
 211         else:
 212             duration = int_or_none(video.get('duration'))
 213
 214         return {
 215             'id': video_id,
 216             'title': unescapeHTML(video.get('title')),
 217             'formats': formats,
 218             'subtitles': subtitles,
 219             'thumbnails': thumbnails,
 220             'timestamp': parse_iso8601(video.get('pubDate')),
 221             'channel': author.get('name'),
 222             'channel_url': author.get('url'),
 223             'duration': duration,
 224             'uploader': author.get('name'),
 225             'live_status': live_status,
 226         }
 227
 228
 229 class RumbleIE(InfoExtractor):
 230     _VALID_URL = r'https?://(?:www\.)?rumble\.com/(?P<id>v(?!ideos)[\w.-]+)[^/]*$'
 231     _EMBED_REGEX = [r'<a class=video-item--a href=(?P<url>/v[\w.-]+\.html)>']
 232     _TESTS = [{
 233         'add_ie': ['RumbleEmbed'],
 234         'url': 'https://rumble.com/vdmum1-moose-the-dog-helps-girls-dig-a-snow-fort.html',
 235         'md5': '53af34098a7f92c4e51cf0bd1c33f009',
 236         'info_dict': {
 237             'id': 'vb0ofn',
 238             'ext': 'mp4',
 239             'timestamp': 1612662578,
 240             'uploader': 'LovingMontana',
 241             'channel': 'LovingMontana',
 242             'upload_date': '20210207',
 243             'title': 'Winter-loving dog helps girls dig a snow fort ',
 244             'description': 'Moose the dog is more than happy to help with digging out this epic snow fort. Great job, Moose!',
 245             'channel_url': 'https://rumble.com/c/c-546523',
 246             'thumbnail': r're:https://.+\.jpg',
 247             'duration': 103,
 248             'like_count': int,
 249             'view_count': int,
 250             'live_status': 'not_live',
 251         }
 252     }, {
 253         'url': 'http://www.rumble.com/vDMUM1?key=value',
 254         'only_matching': True,
 255     }, {
 256         'note': 'timeline format',
 257         'url': 'https://rumble.com/v2ea9qb-the-u.s.-cannot-hide-this-in-ukraine-anymore-redacted-with-natali-and-clayt.html',
 258         'md5': '40d61fec6c0945bca3d0e1dc1aa53d79',
 259         'params': {'format': 'wv'},
 260         'info_dict': {
 261             'id': 'v2bou5f',
 262             'ext': 'mp4',
 263             'uploader': 'Redacted News',
 264             'upload_date': '20230322',
 265             'timestamp': 1679445010,
 266             'title': 'The U.S. CANNOT hide this in Ukraine anymore | Redacted with Natali and Clayton Morris',
 267             'duration': 892,
 268             'channel': 'Redacted News',
 269             'description': 'md5:aaad0c5c3426d7a361c29bdaaced7c42',
 270             'channel_url': 'https://rumble.com/c/Redacted',
 271             'live_status': 'not_live',
 272             'thumbnail': 'https://sp.rmbl.ws/s8/1/d/x/2/O/dx2Oi.qR4e-small-The-U.S.-CANNOT-hide-this-i.jpg',
 273         },
 274     }]
 275
 276     _WEBPAGE_TESTS = [{
 277         'url': 'https://rumble.com/videos?page=2',
 278         'playlist_count': 25,
 279         'info_dict': {
 280             'id': 'videos?page=2',
 281             'title': 'All videos',
 282             'description': 'Browse videos uploaded to Rumble.com',
 283             'age_limit': 0,
 284         },
 285     }, {
 286         'url': 'https://rumble.com/live-videos',
 287         'playlist_mincount': 19,
 288         'info_dict': {
 289             'id': 'live-videos',
 290             'title': 'Live Videos',
 291             'description': 'Live videos on Rumble.com',
 292             'age_limit': 0,
 293         },
 294     }, {
 295         'url': 'https://rumble.com/search/video?q=rumble&sort=views',
 296         'playlist_count': 24,
 297         'info_dict': {
 298             'id': 'video?q=rumble&sort=views',
 299             'title': 'Search results for: rumble',
 300             'age_limit': 0,
 301         },
 302     }]
 303
 304     def _real_extract(self, url):
 305         page_id = self._match_id(url)
 306         webpage = self._download_webpage(url, page_id)
 307         url_info = next(RumbleEmbedIE.extract_from_webpage(self._downloader, url, webpage), None)
 308         if not url_info:
 309             raise UnsupportedError(url)
 310
 311         release_ts_str = self._search_regex(
 312             r'(?:Livestream begins|Streamed on):\s+<time datetime="([^"]+)',
 313             webpage, 'release date', fatal=False, default=None)
 314         view_count_str = self._search_regex(r'<span class="media-heading-info">([\d,]+) Views',
 315                                             webpage, 'view count', fatal=False, default=None)
 316
 317         return self.url_result(
 318             url_info['url'], ie_key=url_info['ie_key'], url_transparent=True,
 319             view_count=parse_count(view_count_str),
 320             release_timestamp=parse_iso8601(release_ts_str),
 321             like_count=parse_count(get_element_by_class('rumbles-count', webpage)),
 322             description=clean_html(get_element_by_class('media-description', webpage)),
 323         )
 324
 325
 326 class RumbleChannelIE(InfoExtractor):
 327     _VALID_URL = r'(?P<url>https?://(?:www\.)?rumble\.com/(?:c|user)/(?P<id>[^&?#$/]+))'
 328
 329     _TESTS = [{
 330         'url': 'https://rumble.com/c/Styxhexenhammer666',
 331         'playlist_mincount': 1160,
 332         'info_dict': {
 333             'id': 'Styxhexenhammer666',
 334         },
 335     }, {
 336         'url': 'https://rumble.com/user/goldenpoodleharleyeuna',
 337         'playlist_mincount': 4,
 338         'info_dict': {
 339             'id': 'goldenpoodleharleyeuna',
 340         },
 341     }]
 342
 343     def entries(self, url, playlist_id):
 344         for page in itertools.count(1):
 345             try:
 346                 webpage = self._download_webpage(f'{url}?page={page}', playlist_id, note='Downloading page %d' % page)
 347             except ExtractorError as e:
 348                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
 349                     break
 350                 raise
 351             for video_url in re.findall(r'class=video-item--a\s?href=([^>]+\.html)', webpage):
 352                 yield self.url_result('https://rumble.com' + video_url)
 353
 354     def _real_extract(self, url):
 355         url, playlist_id = self._match_valid_url(url).groups()
 356         return self.playlist_result(self.entries(url, playlist_id), playlist_id=playlist_id)