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