]>
jfr.im git - yt-dlp.git/blob - youtube_dlc/extractor/bitchute.py
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
17 class BitChuteIE(InfoExtractor
):
18 _VALID_URL
= r
'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
20 'url': 'https://www.bitchute.com/video/szoMrox2JEI/',
21 'md5': '66c4a70e6bfc40dcb6be3eb1d74939eb',
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',
32 'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
33 'only_matching': True,
35 'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
36 'only_matching': True,
39 def _real_extract(self
, url
):
40 video_id
= self
._match
_id
(url
)
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',
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)
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))
61 for format_url in orderedSet(format_urls)]
64 entries = self._parse_html5_media_entries(
65 url, webpage, video_id)
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
']
73 self._check_formats(formats, video_id)
74 self._sort_formats(formats)
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)
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))
94 'description': description,
95 'thumbnail': thumbnail,
97 'upload_date': upload_date,
102 class BitChuteChannelIE(InfoExtractor):
103 _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
105 'url': 'https://www.bitchute.com/channel/victoriaxrave/',
106 'playlist_mincount': 185,
108 'id': 'victoriaxrave',
112 _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
114 def _entries(self, channel_id):
115 channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
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,
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,
131 if data.get('success') is False:
133 html = data.get('html')
136 video_ids = re.findall(
137 r'class=["\']channel
-videos
-image
-container
[^
>]+>\s
*<a
\b[^
>]+\bhref
=["\']/video/([^"\'/]+)',
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)
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)