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     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/szoMrox2JEI/',
  18         'md5': '66c4a70e6bfc40dcb6be3eb1d74939eb',
  19         'info_dict': {
  20             'id': 'szoMrox2JEI',
  21             'ext': 'mp4',
  22             'title': 'Fuck bitches get money',
  23             'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25             'uploader': 'Victoria X Rave',
  26         },
  27     }, {
  28         'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
  29         'only_matching': True,
  30     }, {
  31         'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
  32         'only_matching': True,
  33     }]
  34
  35     def _real_extract(self, url):
  36         video_id = self._match_id(url)
  37
  38         webpage = self._download_webpage(
  39             'https://www.bitchute.com/video/%s' % video_id, video_id, headers={
  40                 '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',
  41             })
  42
  43         title = self._html_search_regex(
  44             (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'),
  45             webpage, 'title', default=None) or self._html_search_meta(
  46             'description', webpage, 'title',
  47             default=None) or self._og_search_description(webpage)
  48
  49         format_urls = []
  50         for mobj in re.finditer(
  51                 r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
  52             format_urls.append(mobj.group('url'))
  53         format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage))
  54
  55         formats = [
  56             {'url': format_url}
  57             for format_url in orderedSet(format_urls)]
  58
  59         if not formats:
  60             formats = self._parse_html5_media_entries(
  61                 url, webpage, video_id)[0]['formats']
  62
  63         self._check_formats(formats, video_id)
  64         self._sort_formats(formats)
  65
  66         description = self._html_search_regex(
  67             r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
  68             webpage, 'description', fatal=False)
  69         thumbnail = self._og_search_thumbnail(
  70             webpage, default=None) or self._html_search_meta(
  71             'twitter:image:src', webpage, 'thumbnail')
  72         uploader = self._html_search_regex(
  73             (r'(?s)<div class=["\']channel-banner.*?<p\b[^>]+\bclass=["\']name[^>]+>(.+?)</p>',
  74              r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'),
  75             webpage, 'uploader', fatal=False)
  76
  77         return {
  78             'id': video_id,
  79             'title': title,
  80             'description': description,
  81             'thumbnail': thumbnail,
  82             'uploader': uploader,
  83             'formats': formats,
  84         }
  85
  86
  87 class BitChuteChannelIE(InfoExtractor):
  88     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
  89     _TEST = {
  90         'url': 'https://www.bitchute.com/channel/victoriaxrave/',
  91         'playlist_mincount': 185,
  92         'info_dict': {
  93             'id': 'victoriaxrave',
  94         },
  95     }
  96
  97     _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
  98
  99     def _entries(self, channel_id):
 100         channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
 101         offset = 0
 102         for page_num in itertools.count(1):
 103             data = self._download_json(
 104                 '%sextend/' % channel_url, channel_id,
 105                 'Downloading channel page %d' % page_num,
 106                 data=urlencode_postdata({
 107                     'csrfmiddlewaretoken': self._TOKEN,
 108                     'name': '',
 109                     'offset': offset,
 110                 }), headers={
 111                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
 112                     'Referer': channel_url,
 113                     'X-Requested-With': 'XMLHttpRequest',
 114                     'Cookie': 'csrftoken=%s' % self._TOKEN,
 115                 })
 116             if data.get('success') is False:
 117                 break
 118             html = data.get('html')
 119             if not html:
 120                 break
 121             video_ids = re.findall(
 122                 r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
 123                 html)
 124             if not video_ids:
 125                 break
 126             offset += len(video_ids)
 127             for video_id in video_ids:
 128                 yield self.url_result(
 129                     'https://www.bitchute.com/video/%s' % video_id,
 130                     ie=BitChuteIE.ie_key(), video_id=video_id)
 131
 132     def _real_extract(self, url):
 133         channel_id = self._match_id(url)
 134         return self.playlist_result(
 135             self._entries(channel_id), playlist_id=channel_id)