yt_dlp/extractor/rumble.py

   1 import itertools
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str, compat_HTTPError
   6 from ..utils import (
   7     determine_ext,
   8     int_or_none,
   9     parse_iso8601,
  10     try_get,
  11     unescapeHTML,
  12     ExtractorError,
  13 )
  14
  15
  16 class RumbleEmbedIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?rumble\.com/embed/(?:[0-9a-z]+\.)?(?P<id>[0-9a-z]+)'
  18     _TESTS = [{
  19         'url': 'https://rumble.com/embed/v5pv5f',
  20         'md5': '36a18a049856720189f30977ccbb2c34',
  21         'info_dict': {
  22             'id': 'v5pv5f',
  23             'ext': 'mp4',
  24             'title': 'WMAR 2 News Latest Headlines | October 20, 6pm',
  25             'timestamp': 1571611968,
  26             'upload_date': '20191020',
  27             'channel_url': 'https://rumble.com/c/WMAR',
  28             'channel': 'WMAR',
  29             'thumbnail': 'https://sp.rmbl.ws/s8/1/5/M/z/1/5Mz1a.OvCc-small-WMAR-2-News-Latest-Headline.jpg',
  30             'duration': 234,
  31             'uploader': 'WMAR',
  32         }
  33     }, {
  34         'url': 'https://rumble.com/embed/vslb7v',
  35         'md5': '7418035de1a30a178b8af34dc2b6a52b',
  36         'info_dict': {
  37             'id': 'vslb7v',
  38             'ext': 'mp4',
  39             'title': 'Defense Sec. says US Commitment to NATO Defense \'Ironclad\'',
  40             'timestamp': 1645142135,
  41             'upload_date': '20220217',
  42             'channel_url': 'https://rumble.com/c/CyberTechNews',
  43             'channel': 'CTNews',
  44             'thumbnail': 'https://sp.rmbl.ws/s8/6/7/i/9/h/7i9hd.OvCc.jpg',
  45             'duration': 901,
  46             'uploader': 'CTNews',
  47         }
  48     }, {
  49         'url': 'https://rumble.com/embed/ufe9n.v5pv5f',
  50         'only_matching': True,
  51     }]
  52
  53     @staticmethod
  54     def _extract_urls(webpage):
  55         return [
  56             mobj.group('url')
  57             for mobj in re.finditer(
  58                 r'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>%s)' % RumbleEmbedIE._VALID_URL,
  59                 webpage)]
  60
  61     def _real_extract(self, url):
  62         video_id = self._match_id(url)
  63         video = self._download_json(
  64             'https://rumble.com/embedJS/', video_id,
  65             query={'request': 'video', 'v': video_id})
  66         title = unescapeHTML(video['title'])
  67
  68         formats = []
  69         for height, ua in (video.get('ua') or {}).items():
  70             for i in range(2):
  71                 f_url = try_get(ua, lambda x: x[i], compat_str)
  72                 if f_url:
  73                     ext = determine_ext(f_url)
  74                     f = {
  75                         'ext': ext,
  76                         'format_id': '%s-%sp' % (ext, height),
  77                         'height': int_or_none(height),
  78                         'url': f_url,
  79                     }
  80                     bitrate = try_get(ua, lambda x: x[i + 2]['bitrate'])
  81                     if bitrate:
  82                         f['tbr'] = int_or_none(bitrate)
  83                     formats.append(f)
  84         self._sort_formats(formats)
  85
  86         subtitles = {
  87             lang: [{
  88                 'url': sub_info['path'],
  89                 'name': sub_info.get('language') or '',
  90             }] for lang, sub_info in (video.get('cc') or {}).items() if sub_info.get('path')
  91         }
  92
  93         author = video.get('author') or {}
  94
  95         return {
  96             'id': video_id,
  97             'title': title,
  98             'formats': formats,
  99             'subtitles': subtitles,
 100             'thumbnail': video.get('i'),
 101             'timestamp': parse_iso8601(video.get('pubDate')),
 102             'channel': author.get('name'),
 103             'channel_url': author.get('url'),
 104             'duration': int_or_none(video.get('duration')),
 105             'uploader': author.get('name'),
 106         }
 107
 108
 109 class RumbleChannelIE(InfoExtractor):
 110     _VALID_URL = r'(?P<url>https?://(?:www\.)?rumble\.com/(?:c|user)/(?P<id>[^&?#$/]+))'
 111
 112     _TESTS = [{
 113         'url': 'https://rumble.com/c/Styxhexenhammer666',
 114         'playlist_mincount': 1160,
 115         'info_dict': {
 116             'id': 'Styxhexenhammer666',
 117         },
 118     }, {
 119         'url': 'https://rumble.com/user/goldenpoodleharleyeuna',
 120         'playlist_count': 4,
 121         'info_dict': {
 122             'id': 'goldenpoodleharleyeuna',
 123         },
 124     }]
 125
 126     def entries(self, url, playlist_id):
 127         for page in itertools.count(1):
 128             try:
 129                 webpage = self._download_webpage(f'{url}?page={page}', playlist_id, note='Downloading page %d' % page)
 130             except ExtractorError as e:
 131                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
 132                     break
 133                 raise
 134             for video_url in re.findall(r'class=video-item--a\s?href=([^>]+\.html)', webpage):
 135                 yield self.url_result('https://rumble.com' + video_url)
 136
 137     def _real_extract(self, url):
 138         url, playlist_id = self._match_valid_url(url).groups()
 139         return self.playlist_result(self.entries(url, playlist_id), playlist_id=playlist_id)