yt_dlp/extractor/bitchute.py

   1 import itertools
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     GeoRestrictedError,
   8     orderedSet,
   9     unified_strdate,
  10     urlencode_postdata,
  11 )
  12
  13
  14 class BitChuteIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
  16     _EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
  17     _TESTS = [{
  18         'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
  19         'md5': '7e427d7ed7af5a75b5855705ec750e2b',
  20         'info_dict': {
  21             'id': 'szoMrox2JEI',
  22             'ext': 'mp4',
  23             'title': 'This is the first video on #BitChute !',
  24             'description': 'md5:a0337e7b1fe39e32336974af8173a034',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26             'uploader': 'BitChute',
  27             'upload_date': '20170103',
  28         },
  29     }, {
  30         'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
  31         'only_matching': True,
  32     }, {
  33         'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
  34         'only_matching': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39
  40         webpage = self._download_webpage(
  41             'https://www.bitchute.com/video/%s' % video_id, video_id, headers={
  42                 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36',
  43             })
  44
  45         title = self._html_search_regex(
  46             (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'),
  47             webpage, 'title', default=None) or self._html_search_meta(
  48             'description', webpage, 'title',
  49             default=None) or self._og_search_description(webpage)
  50
  51         format_urls = []
  52         for mobj in re.finditer(
  53                 r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
  54             format_urls.append(mobj.group('url'))
  55         format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage))
  56
  57         formats = [
  58             {'url': format_url}
  59             for format_url in orderedSet(format_urls)]
  60
  61         if not formats:
  62             entries = self._parse_html5_media_entries(
  63                 url, webpage, video_id)
  64             if not entries:
  65                 error = self._html_search_regex(r'<h1 class="page-title">([^<]+)</h1>', webpage, 'error', default='Cannot find video')
  66                 if error == 'Video Unavailable':
  67                     raise GeoRestrictedError(error)
  68                 raise ExtractorError(error)
  69             formats = entries[0]['formats']
  70
  71         self._check_formats(formats, video_id)
  72         self._sort_formats(formats)
  73
  74         description = self._html_search_regex(
  75             r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
  76             webpage, 'description', fatal=False)
  77         thumbnail = self._og_search_thumbnail(
  78             webpage, default=None) or self._html_search_meta(
  79             'twitter:image:src', webpage, 'thumbnail')
  80         uploader = self._html_search_regex(
  81             (r'(?s)<div class=["\']channel-banner.*?<p\b[^>]+\bclass=["\']name[^>]+>(.+?)</p>',
  82              r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'),
  83             webpage, 'uploader', fatal=False)
  84
  85         upload_date = unified_strdate(self._search_regex(
  86             r'class=["\']video-publish-date[^>]+>[^<]+ at \d+:\d+ UTC on (.+?)\.',
  87             webpage, 'upload date', fatal=False))
  88
  89         return {
  90             'id': video_id,
  91             'title': title,
  92             'description': description,
  93             'thumbnail': thumbnail,
  94             'uploader': uploader,
  95             'upload_date': upload_date,
  96             'formats': formats,
  97         }
  98
  99
 100 class BitChuteChannelIE(InfoExtractor):
 101     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
 102     _TEST = {
 103         'url': 'https://www.bitchute.com/channel/victoriaxrave/',
 104         'playlist_mincount': 185,
 105         'info_dict': {
 106             'id': 'victoriaxrave',
 107         },
 108     }
 109
 110     _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
 111
 112     def _entries(self, channel_id):
 113         channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
 114         offset = 0
 115         for page_num in itertools.count(1):
 116             data = self._download_json(
 117                 '%sextend/' % channel_url, channel_id,
 118                 'Downloading channel page %d' % page_num,
 119                 data=urlencode_postdata({
 120                     'csrfmiddlewaretoken': self._TOKEN,
 121                     'name': '',
 122                     'offset': offset,
 123                 }), headers={
 124                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
 125                     'Referer': channel_url,
 126                     'X-Requested-With': 'XMLHttpRequest',
 127                     'Cookie': 'csrftoken=%s' % self._TOKEN,
 128                 })
 129             if data.get('success') is False:
 130                 break
 131             html = data.get('html')
 132             if not html:
 133                 break
 134             video_ids = re.findall(
 135                 r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
 136                 html)
 137             if not video_ids:
 138                 break
 139             offset += len(video_ids)
 140             for video_id in video_ids:
 141                 yield self.url_result(
 142                     'https://www.bitchute.com/video/%s' % video_id,
 143                     ie=BitChuteIE.ie_key(), video_id=video_id)
 144
 145     def _real_extract(self, url):
 146         channel_id = self._match_id(url)
 147         return self.playlist_result(
 148             self._entries(channel_id), playlist_id=channel_id)