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