yt_dlp/extractor/rumble.py

   1 import itertools
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..networking.exceptions import HTTPError
   6 from ..utils import (
   7     ExtractorError,
   8     UnsupportedError,
   9     clean_html,
  10     determine_ext,
  11     extract_attributes,
  12     format_field,
  13     get_element_by_class,
  14     get_elements_html_by_class,
  15     int_or_none,
  16     join_nonempty,
  17     parse_count,
  18     parse_iso8601,
  19     traverse_obj,
  20     unescapeHTML,
  21     urljoin,
  22 )
  23
  24
  25 class RumbleEmbedIE(InfoExtractor):
  26     _VALID_URL = r'https?://(?:www\.)?rumble\.com/embed/(?:[0-9a-z]+\.)?(?P<id>[0-9a-z]+)'
  27     _EMBED_REGEX = [fr'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>{_VALID_URL})']
  28     _TESTS = [{
  29         'url': 'https://rumble.com/embed/v5pv5f',
  30         'md5': '36a18a049856720189f30977ccbb2c34',
  31         'info_dict': {
  32             'id': 'v5pv5f',
  33             'ext': 'mp4',
  34             'title': 'WMAR 2 News Latest Headlines | October 20, 6pm',
  35             'timestamp': 1571611968,
  36             'upload_date': '20191020',
  37             'channel_url': 'https://rumble.com/c/WMAR',
  38             'channel': 'WMAR',
  39             'thumbnail': 'https://sp.rmbl.ws/s8/1/5/M/z/1/5Mz1a.qR4e-small-WMAR-2-News-Latest-Headline.jpg',
  40             'duration': 234,
  41             'uploader': 'WMAR',
  42             'live_status': 'not_live',
  43         },
  44     }, {
  45         'url': 'https://rumble.com/embed/vslb7v',
  46         'md5': '7418035de1a30a178b8af34dc2b6a52b',
  47         'info_dict': {
  48             'id': 'vslb7v',
  49             'ext': 'mp4',
  50             'title': 'Defense Sec. says US Commitment to NATO Defense \'Ironclad\'',
  51             'timestamp': 1645142135,
  52             'upload_date': '20220217',
  53             'channel_url': 'https://rumble.com/c/CyberTechNews',
  54             'channel': 'CTNews',
  55             'thumbnail': 'https://sp.rmbl.ws/s8/6/7/i/9/h/7i9hd.OvCc.jpg',
  56             'duration': 901,
  57             'uploader': 'CTNews',
  58             'live_status': 'not_live',
  59         },
  60     }, {
  61         'url': 'https://rumble.com/embed/vunh1h',
  62         'info_dict': {
  63             'id': 'vunh1h',
  64             'ext': 'mp4',
  65             'title': '‘Gideon, op zoek naar de waarheid’ including ENG SUBS',
  66             'timestamp': 1647197663,
  67             'upload_date': '20220313',
  68             'channel_url': 'https://rumble.com/user/BLCKBX',
  69             'channel': 'BLCKBX',
  70             'thumbnail': r're:https://.+\.jpg',
  71             'duration': 5069,
  72             'uploader': 'BLCKBX',
  73             'live_status': 'not_live',
  74             'subtitles': {
  75                 'en': [
  76                     {
  77                         'url': r're:https://.+\.vtt',
  78                         'name': 'English',
  79                         'ext': 'vtt',
  80                     },
  81                 ],
  82             },
  83         },
  84         'params': {'skip_download': True},
  85     }, {
  86         'url': 'https://rumble.com/embed/v1essrt',
  87         'info_dict': {
  88             'id': 'v1essrt',
  89             'ext': 'mp4',
  90             'title': 'startswith:lofi hip hop radio 📚 - beats to relax/study to',
  91             'timestamp': 1661519399,
  92             'upload_date': '20220826',
  93             'channel_url': 'https://rumble.com/c/LofiGirl',
  94             'channel': 'Lofi Girl',
  95             'thumbnail': r're:https://.+\.jpg',
  96             'uploader': 'Lofi Girl',
  97             'live_status': 'is_live',
  98         },
  99         'params': {'skip_download': True},
 100     }, {
 101         'url': 'https://rumble.com/embed/v1amumr',
 102         'info_dict': {
 103             'id': 'v1amumr',
 104             'ext': 'mp4',
 105             'fps': 60,
 106             'title': 'Turning Point USA 2022 Student Action Summit DAY 1  - Rumble Exclusive Live',
 107             'timestamp': 1658518457,
 108             'upload_date': '20220722',
 109             'channel_url': 'https://rumble.com/c/RumbleEvents',
 110             'channel': 'Rumble Events',
 111             'thumbnail': r're:https://.+\.jpg',
 112             'duration': 16427,
 113             'uploader': 'Rumble Events',
 114             'live_status': 'was_live',
 115         },
 116         'params': {'skip_download': True},
 117     }, {
 118         'url': 'https://rumble.com/embed/ufe9n.v5pv5f',
 119         'only_matching': True,
 120     }]
 121
 122     _WEBPAGE_TESTS = [
 123         {
 124             'note': 'Rumble JS embed',
 125             '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',
 126             'md5': '4701209ac99095592e73dbba21889690',
 127             'info_dict': {
 128                 'id': 'v15eqxl',
 129                 'ext': 'mp4',
 130                 'channel': 'Mr Producer Media',
 131                 'duration': 92,
 132                 'title': '911 Audio From The Man Who Wanted To Kill Supreme Court Justice Kavanaugh',
 133                 'channel_url': 'https://rumble.com/c/RichSementa',
 134                 'thumbnail': 'https://sp.rmbl.ws/s8/1/P/j/f/A/PjfAe.qR4e-small-911-Audio-From-The-Man-Who-.jpg',
 135                 'timestamp': 1654892716,
 136                 'uploader': 'Mr Producer Media',
 137                 'upload_date': '20220610',
 138                 'live_status': 'not_live',
 139             },
 140         },
 141     ]
 142
 143     @classmethod
 144     def _extract_embed_urls(cls, url, webpage):
 145         embeds = tuple(super()._extract_embed_urls(url, webpage))
 146         if embeds:
 147             return embeds
 148         return [f'https://rumble.com/embed/{mobj.group("id")}' for mobj in re.finditer(
 149             r'<script>[^<]*\bRumble\(\s*"play"\s*,\s*{[^}]*[\'"]?video[\'"]?\s*:\s*[\'"](?P<id>[0-9a-z]+)[\'"]', webpage)]
 150
 151     def _real_extract(self, url):
 152         video_id = self._match_id(url)
 153         video = self._download_json(
 154             'https://rumble.com/embedJS/u3/', video_id,
 155             query={'request': 'video', 'ver': 2, 'v': video_id})
 156
 157         sys_msg = traverse_obj(video, ('sys', 'msg'))
 158         if sys_msg:
 159             self.report_warning(sys_msg, video_id=video_id)
 160
 161         if video.get('live') == 0:
 162             live_status = 'not_live' if video.get('livestream_has_dvr') is None else 'was_live'
 163         elif video.get('live') == 1:
 164             live_status = 'is_upcoming' if video.get('livestream_has_dvr') else 'was_live'
 165         elif video.get('live') == 2:
 166             live_status = 'is_live'
 167         else:
 168             live_status = None
 169
 170         formats = []
 171         for ext, ext_info in (video.get('ua') or {}).items():
 172             if isinstance(ext_info, dict):
 173                 for height, video_info in ext_info.items():
 174                     if not traverse_obj(video_info, ('meta', 'h', {int_or_none})):
 175                         video_info.setdefault('meta', {})['h'] = height
 176                 ext_info = ext_info.values()
 177
 178             for video_info in ext_info:
 179                 meta = video_info.get('meta') or {}
 180                 if not video_info.get('url'):
 181                     continue
 182                 if ext == 'hls':
 183                     if meta.get('live') is True and video.get('live') == 1:
 184                         live_status = 'post_live'
 185                     formats.extend(self._extract_m3u8_formats(
 186                         video_info['url'], video_id,
 187                         ext='mp4', m3u8_id='hls', fatal=False, live=live_status == 'is_live'))
 188                     continue
 189                 timeline = ext == 'timeline'
 190                 if timeline:
 191                     ext = determine_ext(video_info['url'])
 192                 formats.append({
 193                     'ext': ext,
 194                     'acodec': 'none' if timeline else None,
 195                     'url': video_info['url'],
 196                     'format_id': join_nonempty(ext, format_field(meta, 'h', '%sp')),
 197                     'format_note': 'Timeline' if timeline else None,
 198                     'fps': None if timeline else video.get('fps'),
 199                     **traverse_obj(meta, {
 200                         'tbr': 'bitrate',
 201                         'filesize': 'size',
 202                         'width': 'w',
 203                         'height': 'h',
 204                     }, expected_type=lambda x: int(x) or None),
 205                 })
 206
 207         subtitles = {
 208             lang: [{
 209                 'url': sub_info['path'],
 210                 'name': sub_info.get('language') or '',
 211             }] for lang, sub_info in (video.get('cc') or {}).items() if sub_info.get('path')
 212         }
 213
 214         author = video.get('author') or {}
 215         thumbnails = traverse_obj(video, ('t', ..., {'url': 'i', 'width': 'w', 'height': 'h'}))
 216         if not thumbnails and video.get('i'):
 217             thumbnails = [{'url': video['i']}]
 218
 219         if live_status in {'is_live', 'post_live'}:
 220             duration = None
 221         else:
 222             duration = int_or_none(video.get('duration'))
 223
 224         return {
 225             'id': video_id,
 226             'title': unescapeHTML(video.get('title')),
 227             'formats': formats,
 228             'subtitles': subtitles,
 229             'thumbnails': thumbnails,
 230             'timestamp': parse_iso8601(video.get('pubDate')),
 231             'channel': author.get('name'),
 232             'channel_url': author.get('url'),
 233             'duration': duration,
 234             'uploader': author.get('name'),
 235             'live_status': live_status,
 236         }
 237
 238
 239 class RumbleIE(InfoExtractor):
 240     _VALID_URL = r'https?://(?:www\.)?rumble\.com/(?P<id>v(?!ideos)[\w.-]+)[^/]*$'
 241     _EMBED_REGEX = [
 242         r'<a class=video-item--a href=(?P<url>/v[\w.-]+\.html)>',
 243         r'<a[^>]+class="videostream__link link"[^>]+href=(?P<url>/v[\w.-]+\.html)[^>]*>']
 244     _TESTS = [{
 245         'add_ie': ['RumbleEmbed'],
 246         'url': 'https://rumble.com/vdmum1-moose-the-dog-helps-girls-dig-a-snow-fort.html',
 247         'md5': '53af34098a7f92c4e51cf0bd1c33f009',
 248         'info_dict': {
 249             'id': 'vb0ofn',
 250             'ext': 'mp4',
 251             'timestamp': 1612662578,
 252             'uploader': 'LovingMontana',
 253             'channel': 'LovingMontana',
 254             'upload_date': '20210207',
 255             'title': 'Winter-loving dog helps girls dig a snow fort ',
 256             'description': 'Moose the dog is more than happy to help with digging out this epic snow fort. Great job, Moose!',
 257             'channel_url': 'https://rumble.com/c/c-546523',
 258             'thumbnail': r're:https://.+\.jpg',
 259             'duration': 103,
 260             'like_count': int,
 261             'dislike_count': int,
 262             'view_count': int,
 263             'live_status': 'not_live',
 264         },
 265     }, {
 266         'url': 'http://www.rumble.com/vDMUM1?key=value',
 267         'only_matching': True,
 268     }, {
 269         'note': 'timeline format',
 270         'url': 'https://rumble.com/v2ea9qb-the-u.s.-cannot-hide-this-in-ukraine-anymore-redacted-with-natali-and-clayt.html',
 271         'md5': '40d61fec6c0945bca3d0e1dc1aa53d79',
 272         'params': {'format': 'wv'},
 273         'info_dict': {
 274             'id': 'v2bou5f',
 275             'ext': 'mp4',
 276             'uploader': 'Redacted News',
 277             'upload_date': '20230322',
 278             'timestamp': 1679445010,
 279             'title': 'The U.S. CANNOT hide this in Ukraine anymore | Redacted with Natali and Clayton Morris',
 280             'duration': 892,
 281             'channel': 'Redacted News',
 282             'description': 'md5:aaad0c5c3426d7a361c29bdaaced7c42',
 283             'channel_url': 'https://rumble.com/c/Redacted',
 284             'live_status': 'not_live',
 285             'thumbnail': 'https://sp.rmbl.ws/s8/1/d/x/2/O/dx2Oi.qR4e-small-The-U.S.-CANNOT-hide-this-i.jpg',
 286             'like_count': int,
 287             'dislike_count': int,
 288             'view_count': int,
 289         },
 290     }, {
 291         'url': 'https://rumble.com/v2e7fju-the-covid-twitter-files-drop-protecting-fauci-while-censoring-the-truth-wma.html',
 292         'info_dict': {
 293             'id': 'v2blzyy',
 294             'ext': 'mp4',
 295             'live_status': 'was_live',
 296             'release_timestamp': 1679446804,
 297             'description': 'md5:2ac4908ccfecfb921f8ffa4b30c1e636',
 298             'release_date': '20230322',
 299             'timestamp': 1679445692,
 300             'duration': 4435,
 301             'upload_date': '20230322',
 302             'title': 'The Covid Twitter Files Drop: Protecting Fauci While Censoring The Truth w/Matt Taibbi',
 303             'uploader': 'Kim Iversen',
 304             'channel_url': 'https://rumble.com/c/KimIversen',
 305             'channel': 'Kim Iversen',
 306             'thumbnail': 'https://sp.rmbl.ws/s8/1/6/b/w/O/6bwOi.qR4e-small-The-Covid-Twitter-Files-Dro.jpg',
 307             'like_count': int,
 308             'dislike_count': int,
 309             'view_count': int,
 310         },
 311     }]
 312
 313     _WEBPAGE_TESTS = [{
 314         'url': 'https://rumble.com/videos?page=2',
 315         'playlist_mincount': 24,
 316         'info_dict': {
 317             'id': 'videos?page=2',
 318             'title': 'All videos',
 319             'description': 'Browse videos uploaded to Rumble.com',
 320             'age_limit': 0,
 321         },
 322     }, {
 323         'url': 'https://rumble.com/browse/live',
 324         'playlist_mincount': 25,
 325         'info_dict': {
 326             'id': 'live',
 327             'title': 'Browse',
 328             'age_limit': 0,
 329         },
 330     }, {
 331         'url': 'https://rumble.com/search/video?q=rumble&sort=views',
 332         'playlist_mincount': 24,
 333         'info_dict': {
 334             'id': 'video?q=rumble&sort=views',
 335             'title': 'Search results for: rumble',
 336             'age_limit': 0,
 337         },
 338     }]
 339
 340     def _real_extract(self, url):
 341         page_id = self._match_id(url)
 342         webpage = self._download_webpage(url, page_id)
 343         url_info = next(RumbleEmbedIE.extract_from_webpage(self._downloader, url, webpage), None)
 344         if not url_info:
 345             raise UnsupportedError(url)
 346
 347         return {
 348             '_type': 'url_transparent',
 349             'ie_key': url_info['ie_key'],
 350             'url': url_info['url'],
 351             'release_timestamp': parse_iso8601(self._search_regex(
 352                 r'(?:Livestream begins|Streamed on):\s+<time datetime="([^"]+)', webpage, 'release date', default=None)),
 353             'view_count': int_or_none(self._search_regex(
 354                 r'"userInteractionCount"\s*:\s*(\d+)', webpage, 'view count', default=None)),
 355             'like_count': parse_count(self._search_regex(
 356                 r'<span data-js="rumbles_up_votes">\s*([\d,.KM]+)', webpage, 'like count', default=None)),
 357             'dislike_count': parse_count(self._search_regex(
 358                 r'<span data-js="rumbles_down_votes">\s*([\d,.KM]+)', webpage, 'dislike count', default=None)),
 359             'description': clean_html(get_element_by_class('media-description', webpage)),
 360         }
 361
 362
 363 class RumbleChannelIE(InfoExtractor):
 364     _VALID_URL = r'(?P<url>https?://(?:www\.)?rumble\.com/(?:c|user)/(?P<id>[^&?#$/]+))'
 365
 366     _TESTS = [{
 367         'url': 'https://rumble.com/c/Styxhexenhammer666',
 368         'playlist_mincount': 1160,
 369         'info_dict': {
 370             'id': 'Styxhexenhammer666',
 371         },
 372     }, {
 373         'url': 'https://rumble.com/user/goldenpoodleharleyeuna',
 374         'playlist_mincount': 4,
 375         'info_dict': {
 376             'id': 'goldenpoodleharleyeuna',
 377         },
 378     }]
 379
 380     def entries(self, url, playlist_id):
 381         for page in itertools.count(1):
 382             try:
 383                 webpage = self._download_webpage(f'{url}?page={page}', playlist_id, note=f'Downloading page {page}')
 384             except ExtractorError as e:
 385                 if isinstance(e.cause, HTTPError) and e.cause.status == 404:
 386                     break
 387                 raise
 388             for video_url in traverse_obj(
 389                 get_elements_html_by_class('videostream__link', webpage), (..., {extract_attributes}, 'href'),
 390             ):
 391                 yield self.url_result(urljoin('https://rumble.com', video_url))
 392
 393     def _real_extract(self, url):
 394         url, playlist_id = self._match_valid_url(url).groups()
 395         return self.playlist_result(self.entries(url, playlist_id), playlist_id=playlist_id)