yt_dlp/extractor/rumble.py

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