_ Git - youtube-dl/blob - 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         self._check_formats(formats, video_id)
  59         self._sort_formats(formats)
  60
  61         description = self._html_search_regex(
  62             r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
  63             webpage, 'description', fatal=False)
  64         thumbnail = self._og_search_thumbnail(
  65             webpage, default=None) or self._html_search_meta(
  66             'twitter:image:src', webpage, 'thumbnail')
  67         uploader = self._html_search_regex(
  68             (r'(?s)<div class=["\']channel-banner.*?<p\b[^>]+\bclass=["\']name[^>]+>(.+?)</p>',
  69              r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'),
  70             webpage, 'uploader', fatal=False)
  71
  72         return {
  73             'id': video_id,
  74             'title': title,
  75             'description': description,
  76             'thumbnail': thumbnail,
  77             'uploader': uploader,
  78             'formats': formats,
  79         }
  80
  81
  82 class BitChuteChannelIE(InfoExtractor):
  83     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
  84     _TEST = {
  85         'url': 'https://www.bitchute.com/channel/victoriaxrave/',
  86         'playlist_mincount': 185,
  87         'info_dict': {
  88             'id': 'victoriaxrave',
  89         },
  90     }
  91
  92     _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
  93
  94     def _entries(self, channel_id):
  95         channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
  96         offset = 0
  97         for page_num in itertools.count(1):
  98             data = self._download_json(
  99                 '%sextend/' % channel_url, channel_id,
 100                 'Downloading channel page %d' % page_num,
 101                 data=urlencode_postdata({
 102                     'csrfmiddlewaretoken': self._TOKEN,
 103                     'name': '',
 104                     'offset': offset,
 105                 }), headers={
 106                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
 107                     'Referer': channel_url,
 108                     'X-Requested-With': 'XMLHttpRequest',
 109                     'Cookie': 'csrftoken=%s' % self._TOKEN,
 110                 })
 111             if data.get('success') is False:
 112                 break
 113             html = data.get('html')
 114             if not html:
 115                 break
 116             video_ids = re.findall(
 117                 r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
 118                 html)
 119             if not video_ids:
 120                 break
 121             offset += len(video_ids)
 122             for video_id in video_ids:
 123                 yield self.url_result(
 124                     'https://www.bitchute.com/video/%s' % video_id,
 125                     ie=BitChuteIE.ie_key(), video_id=video_id)
 126
 127     def _real_extract(self, url):
 128         channel_id = self._match_id(url)
 129         return self.playlist_result(
 130             self._entries(channel_id), playlist_id=channel_id)