youtube_dl/extractor/bitchute.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 ..utils import (
   9     orderedSet,
  10     unified_strdate,
  11     urlencode_postdata,
  12 )
  13
  14
  15 class BitChuteIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
  17     _TESTS = [{
  18         'url': 'https://www.bitchute.com/video/szoMrox2JEI/',
  19         'md5': '66c4a70e6bfc40dcb6be3eb1d74939eb',
  20         'info_dict': {
  21             'id': 'szoMrox2JEI',
  22             'ext': 'mp4',
  23             'title': 'Fuck bitches get money',
  24             'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26             'uploader': 'Victoria X Rave',
  27             'upload_date': '20170813',
  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             formats = self._parse_html5_media_entries(
  63                 url, webpage, video_id)[0]['formats']
  64
  65         self._check_formats(formats, video_id)
  66         self._sort_formats(formats)
  67
  68         description = self._html_search_regex(
  69             r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
  70             webpage, 'description', fatal=False)
  71         thumbnail = self._og_search_thumbnail(
  72             webpage, default=None) or self._html_search_meta(
  73             'twitter:image:src', webpage, 'thumbnail')
  74         uploader = self._html_search_regex(
  75             (r'(?s)<div class=["\']channel-banner.*?<p\b[^>]+\bclass=["\']name[^>]+>(.+?)</p>',
  76              r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'),
  77             webpage, 'uploader', fatal=False)
  78
  79         upload_date = unified_strdate(self._search_regex(
  80             r'class=["\']video-publish-date[^>]+>[^<]+ at \d+:\d+ UTC on (.+?)\.',
  81             webpage, 'upload date', fatal=False))
  82
  83         return {
  84             'id': video_id,
  85             'title': title,
  86             'description': description,
  87             'thumbnail': thumbnail,
  88             'uploader': uploader,
  89             'upload_date': upload_date,
  90             'formats': formats,
  91         }
  92
  93
  94 class BitChuteChannelIE(InfoExtractor):
  95     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
  96     _TEST = {
  97         'url': 'https://www.bitchute.com/channel/victoriaxrave/',
  98         'playlist_mincount': 185,
  99         'info_dict': {
 100             'id': 'victoriaxrave',
 101         },
 102     }
 103
 104     _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
 105
 106     def _entries(self, channel_id):
 107         channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
 108         offset = 0
 109         for page_num in itertools.count(1):
 110             data = self._download_json(
 111                 '%sextend/' % channel_url, channel_id,
 112                 'Downloading channel page %d' % page_num,
 113                 data=urlencode_postdata({
 114                     'csrfmiddlewaretoken': self._TOKEN,
 115                     'name': '',
 116                     'offset': offset,
 117                 }), headers={
 118                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
 119                     'Referer': channel_url,
 120                     'X-Requested-With': 'XMLHttpRequest',
 121                     'Cookie': 'csrftoken=%s' % self._TOKEN,
 122                 })
 123             if data.get('success') is False:
 124                 break
 125             html = data.get('html')
 126             if not html:
 127                 break
 128             video_ids = re.findall(
 129                 r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
 130                 html)
 131             if not video_ids:
 132                 break
 133             offset += len(video_ids)
 134             for video_id in video_ids:
 135                 yield self.url_result(
 136                     'https://www.bitchute.com/video/%s' % video_id,
 137                     ie=BitChuteIE.ie_key(), video_id=video_id)
 138
 139     def _real_extract(self, url):
 140         channel_id = self._match_id(url)
 141         return self.playlist_result(
 142             self._entries(channel_id), playlist_id=channel_id)