youtube_dlc/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     ExtractorError,
  10     GeoRestrictedError,
  11     orderedSet,
  12     unified_strdate,
  13     urlencode_postdata,
  14 )
  15
  16
  17 class BitChuteIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
  19     _TESTS = [{
  20         'url': 'https://www.bitchute.com/video/szoMrox2JEI/',
  21         'md5': '66c4a70e6bfc40dcb6be3eb1d74939eb',
  22         'info_dict': {
  23             'id': 'szoMrox2JEI',
  24             'ext': 'mp4',
  25             'title': 'Fuck bitches get money',
  26             'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a',
  27             'thumbnail': r're:^https?://.*\.jpg$',
  28             'uploader': 'Victoria X Rave',
  29             'upload_date': '20170813',
  30         },
  31     }, {
  32         'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
  33         'only_matching': True,
  34     }, {
  35         'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
  36         'only_matching': True,
  37     }]
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41
  42         webpage = self._download_webpage(
  43             'https://www.bitchute.com/video/%s' % video_id, video_id, headers={
  44                 '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',
  45             })
  46
  47         title = self._html_search_regex(
  48             (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'),
  49             webpage, 'title', default=None) or self._html_search_meta(
  50             'description', webpage, 'title',
  51             default=None) or self._og_search_description(webpage)
  52
  53         format_urls = []
  54         for mobj in re.finditer(
  55                 r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
  56             format_urls.append(mobj.group('url'))
  57         format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage))
  58
  59         formats = [
  60             {'url': format_url}
  61             for format_url in orderedSet(format_urls)]
  62
  63         if not formats:
  64             entries = self._parse_html5_media_entries(
  65                 url, webpage, video_id)
  66             if not entries:
  67                 error = self._html_search_regex(r'<h1 class="page-title">([^<]+)</h1>', webpage, 'error', default='Cannot find video')
  68                 if error == 'Video Unavailable':
  69                     raise GeoRestrictedError(error)
  70                 raise ExtractorError(error)
  71             formats = entries[0]['formats']
  72
  73         self._check_formats(formats, video_id)
  74         self._sort_formats(formats)
  75
  76         description = self._html_search_regex(
  77             r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
  78             webpage, 'description', fatal=False)
  79         thumbnail = self._og_search_thumbnail(
  80             webpage, default=None) or self._html_search_meta(
  81             'twitter:image:src', webpage, 'thumbnail')
  82         uploader = self._html_search_regex(
  83             (r'(?s)<div class=["\']channel-banner.*?<p\b[^>]+\bclass=["\']name[^>]+>(.+?)</p>',
  84              r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'),
  85             webpage, 'uploader', fatal=False)
  86
  87         upload_date = unified_strdate(self._search_regex(
  88             r'class=["\']video-publish-date[^>]+>[^<]+ at \d+:\d+ UTC on (.+?)\.',
  89             webpage, 'upload date', fatal=False))
  90
  91         return {
  92             'id': video_id,
  93             'title': title,
  94             'description': description,
  95             'thumbnail': thumbnail,
  96             'uploader': uploader,
  97             'upload_date': upload_date,
  98             'formats': formats,
  99         }
 100
 101
 102 class BitChuteChannelIE(InfoExtractor):
 103     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
 104     _TEST = {
 105         'url': 'https://www.bitchute.com/channel/victoriaxrave/',
 106         'playlist_mincount': 185,
 107         'info_dict': {
 108             'id': 'victoriaxrave',
 109         },
 110     }
 111
 112     _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
 113
 114     def _entries(self, channel_id):
 115         channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
 116         offset = 0
 117         for page_num in itertools.count(1):
 118             data = self._download_json(
 119                 '%sextend/' % channel_url, channel_id,
 120                 'Downloading channel page %d' % page_num,
 121                 data=urlencode_postdata({
 122                     'csrfmiddlewaretoken': self._TOKEN,
 123                     'name': '',
 124                     'offset': offset,
 125                 }), headers={
 126                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
 127                     'Referer': channel_url,
 128                     'X-Requested-With': 'XMLHttpRequest',
 129                     'Cookie': 'csrftoken=%s' % self._TOKEN,
 130                 })
 131             if data.get('success') is False:
 132                 break
 133             html = data.get('html')
 134             if not html:
 135                 break
 136             video_ids = re.findall(
 137                 r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
 138                 html)
 139             if not video_ids:
 140                 break
 141             offset += len(video_ids)
 142             for video_id in video_ids:
 143                 yield self.url_result(
 144                     'https://www.bitchute.com/video/%s' % video_id,
 145                     ie=BitChuteIE.ie_key(), video_id=video_id)
 146
 147     def _real_extract(self, url):
 148         channel_id = self._match_id(url)
 149         return self.playlist_result(
 150             self._entries(channel_id), playlist_id=channel_id)