[bitchute] Fix extraction (closes #18567)
[youtube-dl] / 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._sort_formats(formats)
59
60         description = self._html_search_regex(
61             r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
62             webpage, 'description', fatal=False)
63         thumbnail = self._og_search_thumbnail(
64             webpage, default=None) or self._html_search_meta(
65             'twitter:image:src', webpage, 'thumbnail')
66         uploader = self._html_search_regex(
67             r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>', webpage,
68             'uploader', fatal=False)
69
70         return {
71             'id': video_id,
72             'title': title,
73             'description': description,
74             'thumbnail': thumbnail,
75             'uploader': uploader,
76             'formats': formats,
77         }
78
79
80 class BitChuteChannelIE(InfoExtractor):
81     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
82     _TEST = {
83         'url': 'https://www.bitchute.com/channel/victoriaxrave/',
84         'playlist_mincount': 185,
85         'info_dict': {
86             'id': 'victoriaxrave',
87         },
88     }
89
90     _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
91
92     def _entries(self, channel_id):
93         channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
94         offset = 0
95         for page_num in itertools.count(1):
96             data = self._download_json(
97                 '%sextend/' % channel_url, channel_id,
98                 'Downloading channel page %d' % page_num,
99                 data=urlencode_postdata({
100                     'csrfmiddlewaretoken': self._TOKEN,
101                     'name': '',
102                     'offset': offset,
103                 }), headers={
104                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
105                     'Referer': channel_url,
106                     'X-Requested-With': 'XMLHttpRequest',
107                     'Cookie': 'csrftoken=%s' % self._TOKEN,
108                 })
109             if data.get('success') is False:
110                 break
111             html = data.get('html')
112             if not html:
113                 break
114             video_ids = re.findall(
115                 r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
116                 html)
117             if not video_ids:
118                 break
119             offset += len(video_ids)
120             for video_id in video_ids:
121                 yield self.url_result(
122                     'https://www.bitchute.com/video/%s' % video_id,
123                     ie=BitChuteIE.ie_key(), video_id=video_id)
124
125     def _real_extract(self, url):
126         channel_id = self._match_id(url)
127         return self.playlist_result(
128             self._entries(channel_id), playlist_id=channel_id)