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     _TESTS = [{
  17         'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
  18         'md5': '7e427d7ed7af5a75b5855705ec750e2b',
  19         'info_dict': {
  20             'id': 'szoMrox2JEI',
  21             'ext': 'mp4',
  22             'title': 'This is the first video on #BitChute !',
  23             'description': 'md5:a0337e7b1fe39e32336974af8173a034',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25             'uploader': 'BitChute',
  26             'upload_date': '20170103',
  27         },
  28     }, {
  29         'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
  30         'only_matching': True,
  31     }, {
  32         'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
  33         'only_matching': True,
  34     }]
  35
  36     @staticmethod
  37     def _extract_urls(webpage):
  38         return [
  39             mobj.group('url')
  40             for mobj in re.finditer(
  41                 r'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>%s)' % BitChuteIE._VALID_URL,
  42                 webpage)]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46
  47         webpage = self._download_webpage(
  48             'https://www.bitchute.com/video/%s' % video_id, video_id, headers={
  49                 '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',
  50             })
  51
  52         title = self._html_search_regex(
  53             (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'),
  54             webpage, 'title', default=None) or self._html_search_meta(
  55             'description', webpage, 'title',
  56             default=None) or self._og_search_description(webpage)
  57
  58         format_urls = []
  59         for mobj in re.finditer(
  60                 r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
  61             format_urls.append(mobj.group('url'))
  62         format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage))
  63
  64         formats = [
  65             {'url': format_url}
  66             for format_url in orderedSet(format_urls)]
  67
  68         if not formats:
  69             entries = self._parse_html5_media_entries(
  70                 url, webpage, video_id)
  71             if not entries:
  72                 error = self._html_search_regex(r'<h1 class="page-title">([^<]+)</h1>', webpage, 'error', default='Cannot find video')
  73                 if error == 'Video Unavailable':
  74                     raise GeoRestrictedError(error)
  75                 raise ExtractorError(error)
  76             formats = entries[0]['formats']
  77
  78         self._check_formats(formats, video_id)
  79         self._sort_formats(formats)
  80
  81         description = self._html_search_regex(
  82             r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
  83             webpage, 'description', fatal=False)
  84         thumbnail = self._og_search_thumbnail(
  85             webpage, default=None) or self._html_search_meta(
  86             'twitter:image:src', webpage, 'thumbnail')
  87         uploader = self._html_search_regex(
  88             (r'(?s)<div class=["\']channel-banner.*?<p\b[^>]+\bclass=["\']name[^>]+>(.+?)</p>',
  89              r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'),
  90             webpage, 'uploader', fatal=False)
  91
  92         upload_date = unified_strdate(self._search_regex(
  93             r'class=["\']video-publish-date[^>]+>[^<]+ at \d+:\d+ UTC on (.+?)\.',
  94             webpage, 'upload date', fatal=False))
  95
  96         return {
  97             'id': video_id,
  98             'title': title,
  99             'description': description,
 100             'thumbnail': thumbnail,
 101             'uploader': uploader,
 102             'upload_date': upload_date,
 103             'formats': formats,
 104         }
 105
 106
 107 class BitChuteChannelIE(InfoExtractor):
 108     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
 109     _TEST = {
 110         'url': 'https://www.bitchute.com/channel/victoriaxrave/',
 111         'playlist_mincount': 185,
 112         'info_dict': {
 113             'id': 'victoriaxrave',
 114         },
 115     }
 116
 117     _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
 118
 119     def _entries(self, channel_id):
 120         channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
 121         offset = 0
 122         for page_num in itertools.count(1):
 123             data = self._download_json(
 124                 '%sextend/' % channel_url, channel_id,
 125                 'Downloading channel page %d' % page_num,
 126                 data=urlencode_postdata({
 127                     'csrfmiddlewaretoken': self._TOKEN,
 128                     'name': '',
 129                     'offset': offset,
 130                 }), headers={
 131                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
 132                     'Referer': channel_url,
 133                     'X-Requested-With': 'XMLHttpRequest',
 134                     'Cookie': 'csrftoken=%s' % self._TOKEN,
 135                 })
 136             if data.get('success') is False:
 137                 break
 138             html = data.get('html')
 139             if not html:
 140                 break
 141             video_ids = re.findall(
 142                 r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
 143                 html)
 144             if not video_ids:
 145                 break
 146             offset += len(video_ids)
 147             for video_id in video_ids:
 148                 yield self.url_result(
 149                     'https://www.bitchute.com/video/%s' % video_id,
 150                     ie=BitChuteIE.ie_key(), video_id=video_id)
 151
 152     def _real_extract(self, url):
 153         channel_id = self._match_id(url)
 154         return self.playlist_result(
 155             self._entries(channel_id), playlist_id=channel_id)