]>
Commit | Line | Data |
---|---|---|
b65e3b06 S |
1 | import itertools |
2 | import re | |
3 | ||
4 | from .common import InfoExtractor | |
6b688b89 | 5 | from ..utils import ( |
37fb591c | 6 | ExtractorError, |
f72218c1 | 7 | HEADRequest, |
8 | clean_html, | |
9 | get_element_by_class, | |
10 | int_or_none, | |
6b688b89 | 11 | orderedSet, |
f72218c1 | 12 | traverse_obj, |
6ddd4bf6 | 13 | unified_strdate, |
6b688b89 S |
14 | urlencode_postdata, |
15 | ) | |
b65e3b06 S |
16 | |
17 | ||
18 | class BitChuteIE(InfoExtractor): | |
19 | _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)' | |
bfd973ec | 20 | _EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})'] |
b65e3b06 | 21 | _TESTS = [{ |
aca5774e | 22 | 'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/', |
23 | 'md5': '7e427d7ed7af5a75b5855705ec750e2b', | |
b65e3b06 | 24 | 'info_dict': { |
f72218c1 | 25 | 'id': 'UGlrF9o9b-Q', |
b65e3b06 | 26 | 'ext': 'mp4', |
aca5774e | 27 | 'title': 'This is the first video on #BitChute !', |
28 | 'description': 'md5:a0337e7b1fe39e32336974af8173a034', | |
b65e3b06 | 29 | 'thumbnail': r're:^https?://.*\.jpg$', |
aca5774e | 30 | 'uploader': 'BitChute', |
31 | 'upload_date': '20170103', | |
b65e3b06 | 32 | }, |
f72218c1 | 33 | }, { |
34 | # video not downloadable in browser, but we can recover it | |
35 | 'url': 'https://www.bitchute.com/video/2s6B3nZjAk7R/', | |
36 | 'md5': '05c12397d5354bf24494885b08d24ed1', | |
37 | 'info_dict': { | |
38 | 'id': '2s6B3nZjAk7R', | |
39 | 'ext': 'mp4', | |
40 | 'filesize': 71537926, | |
41 | 'title': 'STYXHEXENHAMMER666 - Election Fraud, Clinton 2020, EU Armies, and Gun Control', | |
42 | 'description': 'md5:228ee93bd840a24938f536aeac9cf749', | |
43 | 'thumbnail': r're:^https?://.*\.jpg$', | |
44 | 'uploader': 'BitChute', | |
45 | 'upload_date': '20181113', | |
46 | }, | |
47 | 'params': {'check_formats': None}, | |
b65e3b06 S |
48 | }, { |
49 | 'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/', | |
50 | 'only_matching': True, | |
51 | }, { | |
52 | 'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent', | |
53 | 'only_matching': True, | |
54 | }] | |
55 | ||
f72218c1 | 56 | _HEADERS = { |
57 | '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', | |
58 | 'Referer': 'https://www.bitchute.com/', | |
59 | } | |
60 | ||
61 | def _check_format(self, video_url, video_id): | |
62 | urls = orderedSet( | |
63 | re.sub(r'(^https?://)(seed\d+)(?=\.bitchute\.com)', fr'\g<1>{host}', video_url) | |
64 | for host in (r'\g<2>', 'seed150', 'seed151', 'seed152', 'seed153')) | |
65 | for url in urls: | |
66 | try: | |
67 | response = self._request_webpage( | |
68 | HEADRequest(url), video_id=video_id, note=f'Checking {url}', headers=self._HEADERS) | |
69 | except ExtractorError as e: | |
70 | self.to_screen(f'{video_id}: URL is invalid, skipping: {e.cause}') | |
71 | continue | |
72 | return { | |
73 | 'url': url, | |
74 | 'filesize': int_or_none(response.headers.get('Content-Length')) | |
75 | } | |
76 | ||
b65e3b06 S |
77 | def _real_extract(self, url): |
78 | video_id = self._match_id(url) | |
b65e3b06 | 79 | webpage = self._download_webpage( |
f72218c1 | 80 | f'https://www.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS) |
b65e3b06 | 81 | |
f72218c1 | 82 | publish_date = clean_html(get_element_by_class('video-publish-date', webpage)) |
83 | entries = self._parse_html5_media_entries(url, webpage, video_id) | |
b65e3b06 | 84 | |
f72218c1 | 85 | formats = [] |
86 | for format_ in traverse_obj(entries, (0, 'formats', ...)): | |
87 | if self.get_param('check_formats') is not False: | |
88 | format_.update(self._check_format(format_.pop('url'), video_id) or {}) | |
89 | if 'url' not in format_: | |
90 | continue | |
91 | formats.append(format_) | |
4c78c3d7 S |
92 | |
93 | if not formats: | |
f72218c1 | 94 | self.raise_no_formats( |
95 | 'Video is unavailable. Please make sure this video is playable in the browser ' | |
96 | 'before reporting this issue.', expected=True, video_id=video_id) | |
b65e3b06 S |
97 | self._sort_formats(formats) |
98 | ||
b65e3b06 S |
99 | return { |
100 | 'id': video_id, | |
f72218c1 | 101 | 'title': self._html_extract_title(webpage) or self._og_search_title(webpage), |
102 | 'description': self._og_search_description(webpage, default=None), | |
103 | 'thumbnail': self._og_search_thumbnail(webpage), | |
104 | 'uploader': clean_html(get_element_by_class('owner', webpage)), | |
105 | 'upload_date': unified_strdate(self._search_regex( | |
106 | r'at \d+:\d+ UTC on (.+?)\.', publish_date, 'upload date', fatal=False)), | |
b65e3b06 S |
107 | 'formats': formats, |
108 | } | |
109 | ||
110 | ||
111 | class BitChuteChannelIE(InfoExtractor): | |
112 | _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)' | |
113 | _TEST = { | |
114 | 'url': 'https://www.bitchute.com/channel/victoriaxrave/', | |
115 | 'playlist_mincount': 185, | |
116 | 'info_dict': { | |
117 | 'id': 'victoriaxrave', | |
118 | }, | |
119 | } | |
120 | ||
121 | _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7' | |
122 | ||
123 | def _entries(self, channel_id): | |
124 | channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id | |
de4c41b4 S |
125 | offset = 0 |
126 | for page_num in itertools.count(1): | |
b65e3b06 S |
127 | data = self._download_json( |
128 | '%sextend/' % channel_url, channel_id, | |
de4c41b4 | 129 | 'Downloading channel page %d' % page_num, |
b65e3b06 S |
130 | data=urlencode_postdata({ |
131 | 'csrfmiddlewaretoken': self._TOKEN, | |
132 | 'name': '', | |
de4c41b4 | 133 | 'offset': offset, |
b65e3b06 S |
134 | }), headers={ |
135 | 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', | |
136 | 'Referer': channel_url, | |
137 | 'X-Requested-With': 'XMLHttpRequest', | |
138 | 'Cookie': 'csrftoken=%s' % self._TOKEN, | |
139 | }) | |
140 | if data.get('success') is False: | |
141 | break | |
142 | html = data.get('html') | |
143 | if not html: | |
144 | break | |
145 | video_ids = re.findall( | |
146 | r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)', | |
147 | html) | |
148 | if not video_ids: | |
149 | break | |
de4c41b4 | 150 | offset += len(video_ids) |
b65e3b06 S |
151 | for video_id in video_ids: |
152 | yield self.url_result( | |
153 | 'https://www.bitchute.com/video/%s' % video_id, | |
154 | ie=BitChuteIE.ie_key(), video_id=video_id) | |
155 | ||
156 | def _real_extract(self, url): | |
157 | channel_id = self._match_id(url) | |
158 | return self.playlist_result( | |
159 | self._entries(channel_id), playlist_id=channel_id) |