-import itertools
+import functools
import re
from .common import InfoExtractor
+from ..networking import HEADRequest
from ..utils import (
ExtractorError,
- GeoRestrictedError,
+ OnDemandPagedList,
+ clean_html,
+ extract_attributes,
+ get_element_by_class,
+ get_element_by_id,
+ get_element_html_by_class,
+ get_elements_html_by_class,
+ int_or_none,
orderedSet,
+ parse_count,
+ parse_duration,
+ traverse_obj,
unified_strdate,
urlencode_postdata,
+ urljoin,
)
'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
'md5': '7e427d7ed7af5a75b5855705ec750e2b',
'info_dict': {
- 'id': 'szoMrox2JEI',
+ 'id': 'UGlrF9o9b-Q',
'ext': 'mp4',
'title': 'This is the first video on #BitChute !',
'description': 'md5:a0337e7b1fe39e32336974af8173a034',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'BitChute',
'upload_date': '20170103',
+ 'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
+ 'channel': 'BitChute',
+ 'channel_url': 'https://www.bitchute.com/channel/bitchute/',
},
+ }, {
+ # test case: video with different channel and uploader
+ 'url': 'https://www.bitchute.com/video/Yti_j9A-UZ4/',
+ 'md5': 'f10e6a8e787766235946d0868703f1d0',
+ 'info_dict': {
+ 'id': 'Yti_j9A-UZ4',
+ 'ext': 'mp4',
+ 'title': 'Israel at War | Full Measure',
+ 'description': 'md5:38cf7bc6f42da1a877835539111c69ef',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'uploader': 'sharylattkisson',
+ 'upload_date': '20231106',
+ 'uploader_url': 'https://www.bitchute.com/profile/9K0kUWA9zmd9/',
+ 'channel': 'Full Measure with Sharyl Attkisson',
+ 'channel_url': 'https://www.bitchute.com/channel/sharylattkisson/',
+ },
+ }, {
+ # video not downloadable in browser, but we can recover it
+ 'url': 'https://www.bitchute.com/video/2s6B3nZjAk7R/',
+ 'md5': '05c12397d5354bf24494885b08d24ed1',
+ 'info_dict': {
+ 'id': '2s6B3nZjAk7R',
+ 'ext': 'mp4',
+ 'filesize': 71537926,
+ 'title': 'STYXHEXENHAMMER666 - Election Fraud, Clinton 2020, EU Armies, and Gun Control',
+ 'description': 'md5:228ee93bd840a24938f536aeac9cf749',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'uploader': 'BitChute',
+ 'upload_date': '20181113',
+ 'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
+ 'channel': 'BitChute',
+ 'channel_url': 'https://www.bitchute.com/channel/bitchute/',
+ },
+ 'params': {'check_formats': None},
+ }, {
+ # restricted video
+ 'url': 'https://www.bitchute.com/video/WEnQU7XGcTdl/',
+ 'info_dict': {
+ 'id': 'WEnQU7XGcTdl',
+ 'ext': 'mp4',
+ 'title': 'Impartial Truth - Ein Letzter Appell an die Vernunft',
+ },
+ 'params': {'skip_download': True},
+ 'skip': 'Georestricted in DE',
}, {
'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
'only_matching': True,
'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
'only_matching': True,
}]
+ _GEO_BYPASS = False
+
+ _HEADERS = {
+ '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',
+ 'Referer': 'https://www.bitchute.com/',
+ }
+
+ def _check_format(self, video_url, video_id):
+ urls = orderedSet(
+ re.sub(r'(^https?://)(seed\d+)(?=\.bitchute\.com)', fr'\g<1>{host}', video_url)
+ for host in (r'\g<2>', 'seed122', 'seed125', 'seed126', 'seed128',
+ 'seed132', 'seed150', 'seed151', 'seed152', 'seed153',
+ 'seed167', 'seed171', 'seed177', 'seed305', 'seed307',
+ 'seedp29xb', 'zb10-7gsop1v78'))
+ for url in urls:
+ try:
+ response = self._request_webpage(
+ HEADRequest(url), video_id=video_id, note=f'Checking {url}', headers=self._HEADERS)
+ except ExtractorError as e:
+ self.to_screen(f'{video_id}: URL is invalid, skipping: {e.cause}')
+ continue
+ return {
+ 'url': url,
+ 'filesize': int_or_none(response.headers.get('Content-Length')),
+ }
+
+ def _raise_if_restricted(self, webpage):
+ page_title = clean_html(get_element_by_class('page-title', webpage)) or ''
+ if re.fullmatch(r'(?:Channel|Video) Restricted', page_title):
+ reason = clean_html(get_element_by_id('page-detail', webpage)) or page_title
+ self.raise_geo_restricted(reason)
+
+ @staticmethod
+ def _make_url(html):
+ path = extract_attributes(get_element_html_by_class('spa', html) or '').get('href')
+ return urljoin('https://www.bitchute.com', path)
def _real_extract(self, url):
video_id = self._match_id(url)
-
webpage = self._download_webpage(
- 'https://www.bitchute.com/video/%s' % video_id, video_id, headers={
- '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',
- })
+ f'https://www.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
- title = self._html_search_regex(
- (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'),
- webpage, 'title', default=None) or self._html_search_meta(
- 'description', webpage, 'title',
- default=None) or self._og_search_description(webpage)
+ self._raise_if_restricted(webpage)
+ publish_date = clean_html(get_element_by_class('video-publish-date', webpage))
+ entries = self._parse_html5_media_entries(url, webpage, video_id)
- format_urls = []
- for mobj in re.finditer(
- r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
- format_urls.append(mobj.group('url'))
- format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage))
-
- formats = [
- {'url': format_url}
- for format_url in orderedSet(format_urls)]
+ formats = []
+ for format_ in traverse_obj(entries, (0, 'formats', ...)):
+ if self.get_param('check_formats') is not False:
+ format_.update(self._check_format(format_.pop('url'), video_id) or {})
+ if 'url' not in format_:
+ continue
+ formats.append(format_)
if not formats:
- entries = self._parse_html5_media_entries(
- url, webpage, video_id)
- if not entries:
- error = self._html_search_regex(r'<h1 class="page-title">([^<]+)</h1>', webpage, 'error', default='Cannot find video')
- if error == 'Video Unavailable':
- raise GeoRestrictedError(error)
- raise ExtractorError(error)
- formats = entries[0]['formats']
-
- self._check_formats(formats, video_id)
- self._sort_formats(formats)
-
- description = self._html_search_regex(
- r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
- webpage, 'description', fatal=False)
- thumbnail = self._og_search_thumbnail(
- webpage, default=None) or self._html_search_meta(
- 'twitter:image:src', webpage, 'thumbnail')
- uploader = self._html_search_regex(
- (r'(?s)<div class=["\']channel-banner.*?<p\b[^>]+\bclass=["\']name[^>]+>(.+?)</p>',
- r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'),
- webpage, 'uploader', fatal=False)
-
- upload_date = unified_strdate(self._search_regex(
- r'class=["\']video-publish-date[^>]+>[^<]+ at \d+:\d+ UTC on (.+?)\.',
- webpage, 'upload date', fatal=False))
+ self.raise_no_formats(
+ 'Video is unavailable. Please make sure this video is playable in the browser '
+ 'before reporting this issue.', expected=True, video_id=video_id)
+
+ details = get_element_by_class('details', webpage) or ''
+ uploader_html = get_element_html_by_class('creator', details) or ''
+ channel_html = get_element_html_by_class('name', details) or ''
return {
'id': video_id,
- 'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'uploader': uploader,
- 'upload_date': upload_date,
+ 'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
+ 'description': self._og_search_description(webpage, default=None),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ 'uploader': clean_html(uploader_html),
+ 'uploader_url': self._make_url(uploader_html),
+ 'channel': clean_html(channel_html),
+ 'channel_url': self._make_url(channel_html),
+ 'upload_date': unified_strdate(self._search_regex(
+ r'at \d+:\d+ UTC on (.+?)\.', publish_date, 'upload date', fatal=False)),
'formats': formats,
}
class BitChuteChannelIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
- _TEST = {
- 'url': 'https://www.bitchute.com/channel/victoriaxrave/',
- 'playlist_mincount': 185,
+ _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?P<type>channel|playlist)/(?P<id>[^/?#&]+)'
+ _TESTS = [{
+ 'url': 'https://www.bitchute.com/channel/bitchute/',
'info_dict': {
- 'id': 'victoriaxrave',
+ 'id': 'bitchute',
+ 'title': 'BitChute',
+ 'description': 'md5:5329fb3866125afa9446835594a9b138',
},
- }
+ 'playlist': [
+ {
+ 'md5': '7e427d7ed7af5a75b5855705ec750e2b',
+ 'info_dict': {
+ 'id': 'UGlrF9o9b-Q',
+ 'ext': 'mp4',
+ 'title': 'This is the first video on #BitChute !',
+ 'description': 'md5:a0337e7b1fe39e32336974af8173a034',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'uploader': 'BitChute',
+ 'upload_date': '20170103',
+ 'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
+ 'channel': 'BitChute',
+ 'channel_url': 'https://www.bitchute.com/channel/bitchute/',
+ 'duration': 16,
+ 'view_count': int,
+ },
+ },
+ ],
+ 'params': {
+ 'skip_download': True,
+ 'playlist_items': '-1',
+ },
+ }, {
+ 'url': 'https://www.bitchute.com/playlist/wV9Imujxasw9/',
+ 'playlist_mincount': 20,
+ 'info_dict': {
+ 'id': 'wV9Imujxasw9',
+ 'title': 'Bruce MacDonald and "The Light of Darkness"',
+ 'description': 'md5:747724ef404eebdfc04277714f81863e',
+ },
+ }]
_TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
+ PAGE_SIZE = 25
+ HTML_CLASS_NAMES = {
+ 'channel': {
+ 'container': 'channel-videos-container',
+ 'title': 'channel-videos-title',
+ 'description': 'channel-videos-text',
+ },
+ 'playlist': {
+ 'container': 'playlist-video',
+ 'title': 'title',
+ 'description': 'description',
+ },
- def _entries(self, channel_id):
- channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
- offset = 0
- for page_num in itertools.count(1):
- data = self._download_json(
- '%sextend/' % channel_url, channel_id,
- 'Downloading channel page %d' % page_num,
- data=urlencode_postdata({
- 'csrfmiddlewaretoken': self._TOKEN,
- 'name': '',
- 'offset': offset,
- }), headers={
- 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
- 'Referer': channel_url,
- 'X-Requested-With': 'XMLHttpRequest',
- 'Cookie': 'csrftoken=%s' % self._TOKEN,
- })
- if data.get('success') is False:
- break
- html = data.get('html')
- if not html:
- break
- video_ids = re.findall(
- r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
- html)
- if not video_ids:
- break
- offset += len(video_ids)
- for video_id in video_ids:
- yield self.url_result(
- 'https://www.bitchute.com/video/%s' % video_id,
- ie=BitChuteIE.ie_key(), video_id=video_id)
+ }
+
+ @staticmethod
+ def _make_url(playlist_id, playlist_type):
+ return f'https://www.bitchute.com/{playlist_type}/{playlist_id}/'
+
+ def _fetch_page(self, playlist_id, playlist_type, page_num):
+ playlist_url = self._make_url(playlist_id, playlist_type)
+ data = self._download_json(
+ f'{playlist_url}extend/', playlist_id, f'Downloading page {page_num}',
+ data=urlencode_postdata({
+ 'csrfmiddlewaretoken': self._TOKEN,
+ 'name': '',
+ 'offset': page_num * self.PAGE_SIZE,
+ }), headers={
+ 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+ 'Referer': playlist_url,
+ 'X-Requested-With': 'XMLHttpRequest',
+ 'Cookie': f'csrftoken={self._TOKEN}',
+ })
+ if not data.get('success'):
+ return
+ classes = self.HTML_CLASS_NAMES[playlist_type]
+ for video_html in get_elements_html_by_class(classes['container'], data.get('html')):
+ video_id = self._search_regex(
+ r'<a\s[^>]*\bhref=["\']/video/([^"\'/]+)', video_html, 'video id', default=None)
+ if not video_id:
+ continue
+ yield self.url_result(
+ f'https://www.bitchute.com/video/{video_id}', BitChuteIE, video_id, url_transparent=True,
+ title=clean_html(get_element_by_class(classes['title'], video_html)),
+ description=clean_html(get_element_by_class(classes['description'], video_html)),
+ duration=parse_duration(get_element_by_class('video-duration', video_html)),
+ view_count=parse_count(clean_html(get_element_by_class('video-views', video_html))))
def _real_extract(self, url):
- channel_id = self._match_id(url)
+ playlist_type, playlist_id = self._match_valid_url(url).group('type', 'id')
+ webpage = self._download_webpage(self._make_url(playlist_id, playlist_type), playlist_id)
+
+ page_func = functools.partial(self._fetch_page, playlist_id, playlist_type)
return self.playlist_result(
- self._entries(channel_id), playlist_id=channel_id)
+ OnDemandPagedList(page_func, self.PAGE_SIZE), playlist_id,
+ title=self._html_extract_title(webpage, default=None),
+ description=self._html_search_meta(
+ ('description', 'og:description', 'twitter:description'), webpage, default=None),
+ playlist_count=int_or_none(self._html_search_regex(
+ r'<span>(\d+)\s+videos?</span>', webpage, 'playlist count', default=None)))
projects / yt-dlp.git / blobdiff