From 79819f441beadb0dac3936c6b63464dca04c12da Mon Sep 17 00:00:00 2001 From: dirkf Date: Thu, 9 Jun 2022 23:42:06 +0100 Subject: [PATCH 1/5] [BitChute] Back-port from yt-dlp and upgrade BitChute * extract timestamp instead of upload date * improve title and description extraction BitChuteChannel * fix listing entries Throughout * relax regexes --- youtube_dl/extractor/bitchute.py | 107 +++++++++++++++++++------------ 1 file changed, 67 insertions(+), 40 deletions(-) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 0c773e66e..459602079 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -6,8 +6,15 @@ import re from .common import InfoExtractor from ..utils import ( + clean_html, + ExtractorError, + GeoRestrictedError, + get_element_by_class, + get_element_by_id, orderedSet, + strip_or_none, unified_strdate, + unified_timestamp, urlencode_postdata, ) @@ -15,16 +22,17 @@ from ..utils import ( class BitChuteIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P[^/?#&]+)' _TESTS = [{ - 'url': 'https://www.bitchute.com/video/szoMrox2JEI/', - 'md5': '66c4a70e6bfc40dcb6be3eb1d74939eb', + 'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/', + 'md5': '7e427d7ed7af5a75b5855705ec750e2b', 'info_dict': { - 'id': 'szoMrox2JEI', + 'id': 'UGlrF9o9b-Q', 'ext': 'mp4', - 'title': 'Fuck bitches get money', - 'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a', + 'title': 'This is the first video on #BitChute !', + 'timestamp': 1483425420, + 'upload_date': '20170103', + 'description': 'md5:a0337e7b1fe39e32336974af8173a034', 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'Victoria X Rave', - 'upload_date': '20170813', + 'uploader': 'BitChute', }, }, { 'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/', @@ -34,6 +42,13 @@ class BitChuteIE(InfoExtractor): 'only_matching': True, }] + @staticmethod + def _extract_urls(webpage): + urls = re.finditer( + r'''<(?:script|iframe)\b[^>]+\bsrc\s*=\s*(["'])(?P%s)''' % (BitChuteIE._VALID_URL, ), + webpage) + return (mobj.group('url') for mobj in urls) + def _real_extract(self, url): video_id = self._match_id(url) @@ -42,43 +57,55 @@ class BitChuteIE(InfoExtractor): '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', }) - title = self._html_search_regex( - (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'([^<]+)'), - webpage, 'title', default=None) or self._html_search_meta( - 'description', webpage, 'title', - default=None) or self._og_search_description(webpage) + title = ( + self._og_search_title(webpage, default=None) + or strip_or_none(clean_html(get_element_by_id('video-title', webpage))) + or self._html_search_regex(r'(?s)<title\b[^>]*>.*?</title', webpage, 'title')) - 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)) + format_urls = [ + mobj.group('url') + for mobj in re.finditer( + r'''\baddWebSeed\s*\(\s*(["'])(?P<url>(?:(?!\1).)+)\1''', webpage)] + format_urls.extend(re.findall(r'''as=(https?://[^&"']+)''', webpage)) formats = [ {'url': format_url} for format_url in orderedSet(format_urls)] if not formats: - formats = self._parse_html5_media_entries( - url, webpage, video_id)[0]['formats'] + entries = self._parse_html5_media_entries( + url, webpage, video_id) + if not entries: + error = strip_or_none(clean_html(self.get_element_by_id('video-title'))) or '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') + description = ( + self._og_search_description(webpage) + or clean_html(get_element_by_id('video-description', webpage)) + or self._html_search_regex( + r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>', + webpage, 'description', fatal=False)) + thumbnail = self._html_search_meta( + ('og:image', 'twitter:image:src'), webpage, 'thumbnail', fatal=False) uploader = self._html_search_regex( - (r'(?s)<div class=["\']channel-banner.*?<p\b[^>]+\bclass=["\']name[^>]+>(.+?)</p>', - r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'), + (r'''(?s)<div\b[^>]+?\bclass\s*=\s*["']channel-banner.*?<p\b[^>]+\bclass\s*=\s*["']name\b[^>]+>(.+?)</p>''', + r'''(?s)<p\b[^>]+\bclass\s*=\s*["']video-author\b[^>]+>(.+?)</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)) + def more_unified_timestamp(x): + # ... at hh:mm TZ on month nth. + y = re.split(r'\s+at\s+', x or '')[-1] + y = re.sub(r'(?:^\s+|\s+$|\.+$|(?<=\d)(?:st|nd|rd|th))', '', y) + y = ' '.join(reversed(re.split(r'\s+on\s+', y, 1))) + return unified_timestamp(y) or unified_timestamp(x) + + timestamp = more_unified_timestamp(get_element_by_class('video-publish-date', webpage)) return { 'id': video_id, @@ -86,7 +113,7 @@ class BitChuteIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, - 'upload_date': upload_date, + 'timestamp': timestamp, 'formats': formats, } @@ -94,22 +121,22 @@ class BitChuteIE(InfoExtractor): class BitChuteChannelIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)' _TEST = { - 'url': 'https://www.bitchute.com/channel/victoriaxrave/', - 'playlist_mincount': 185, + 'url': 'https://www.bitchute.com/channel/livesonnet/', + 'playlist_mincount': 135, 'info_dict': { - 'id': 'victoriaxrave', + 'id': 'livesonnet', }, } _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7' def _entries(self, channel_id): - channel_url = 'https://www.bitchute.com/channel/%s/' % 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, + channel_url + '/extend/', channel_id, + 'Downloading channel page %d' % (page_num, ), data=urlencode_postdata({ 'csrfmiddlewaretoken': self._TOKEN, 'name': '', @@ -118,7 +145,7 @@ class BitChuteChannelIE(InfoExtractor): 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', 'Referer': channel_url, 'X-Requested-With': 'XMLHttpRequest', - 'Cookie': 'csrftoken=%s' % self._TOKEN, + 'Cookie': 'csrftoken=' + self._TOKEN, }) if data.get('success') is False: break @@ -126,14 +153,14 @@ class BitChuteChannelIE(InfoExtractor): if not html: break video_ids = re.findall( - r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)', + r'''class\s*=\s*["']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref\s*=\s*["']/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, + 'https://www.bitchute.com/video/' + video_id, ie=BitChuteIE.ie_key(), video_id=video_id) def _real_extract(self, url): From 1f627925519156b4dde65e222f0dcc0cefc50532 Mon Sep 17 00:00:00 2001 From: dirkf <fieldhouse@gmx.net> Date: Fri, 10 Jun 2022 01:31:53 +0100 Subject: [PATCH 2/5] [BitChute] Added BitChutePlaylistIE * closes #26725 --- youtube_dl/extractor/bitchute.py | 162 ++++++++++++++++++++--------- youtube_dl/extractor/extractors.py | 1 + 2 files changed, 115 insertions(+), 48 deletions(-) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 459602079..8946933b8 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -11,15 +11,67 @@ from ..utils import ( GeoRestrictedError, get_element_by_class, get_element_by_id, + merge_dicts, orderedSet, strip_or_none, - unified_strdate, unified_timestamp, urlencode_postdata, ) -class BitChuteIE(InfoExtractor): +class BitChuteBaseIE(InfoExtractor): + _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' + + def _list_entries(self, list_id): + TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7' + list_url = self._API_URL + list_id + offset = 0 + for page_num in itertools.count(1): + data = self._download_json( + list_url + '/extend/', list_id, + 'Downloading list page %d' % (page_num, ), + data=urlencode_postdata({ + 'csrfmiddlewaretoken': TOKEN, + 'name': '', + 'offset': offset, + }), headers={ + 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', + 'Referer': list_url, + 'X-Requested-With': 'XMLHttpRequest', + 'Cookie': 'csrftoken=' + TOKEN, + }) + if data.get('success') is False: + break + html = data.get('html') + if not html: + break + video_ids = re.findall( + r'''class\s*=\s*["'](?:channel-videos-)?image-container[^>]+>\s*<a\b[^>]+\bhref\s*=\s*["']/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/' + video_id, + ie=BitChuteIE.ie_key(), video_id=video_id) + + def _search_title(self, html, title_id, **kwargs): + return ( + strip_or_none(clean_html(get_element_by_id(title_id, html))) + or self._og_search_title(html, default=None) + or self._html_search_regex(r'(?s)<title\b[^>]*>.*?</title', html, 'title', **kwargs)) + + def _search_description(self, html, descr_id): + return ( + self._og_search_description(html) + or (descr_id and clean_html(get_element_by_id(descr_id, html))) + or self._html_search_regex( + r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>', + html, 'description', fatal=False)) + + +class BitChuteIE(BitChuteBaseIE): _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/', @@ -53,14 +105,12 @@ class BitChuteIE(InfoExtractor): 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', + 'https://www.bitchute.com/video/' + video_id, video_id, + headers={ + 'User-Agent': self._USER_AGENT, }) - title = ( - self._og_search_title(webpage, default=None) - or strip_or_none(clean_html(get_element_by_id('video-title', webpage))) - or self._html_search_regex(r'(?s)<title\b[^>]*>.*?</title', webpage, 'title')) + title = self._search_title(webpage, 'video-title') format_urls = [ mobj.group('url') @@ -86,8 +136,7 @@ class BitChuteIE(InfoExtractor): self._sort_formats(formats) description = ( - self._og_search_description(webpage) - or clean_html(get_element_by_id('video-description', webpage)) + self._search_description(webpage, 'video-description') or self._html_search_regex( r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>', webpage, 'description', fatal=False)) @@ -118,52 +167,69 @@ class BitChuteIE(InfoExtractor): } -class BitChuteChannelIE(InfoExtractor): +class BitChuteChannelIE(BitChuteBaseIE): _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)' _TEST = { 'url': 'https://www.bitchute.com/channel/livesonnet/', 'playlist_mincount': 135, 'info_dict': { 'id': 'livesonnet', + 'title': 'livesonnet_vidz', + 'description': 'md5:b0017be20656a1347eeb84f1049fc424', }, } - - _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7' - - 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( - channel_url + '/extend/', 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=' + self._TOKEN, - }) - if data.get('success') is False: - break - html = data.get('html') - if not html: - break - video_ids = re.findall( - r'''class\s*=\s*["']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref\s*=\s*["']/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/' + video_id, - ie=BitChuteIE.ie_key(), video_id=video_id) + _API_URL = 'https://www.bitchute.com/channel/' def _real_extract(self, url): channel_id = self._match_id(url) - return self.playlist_result( - self._entries(channel_id), playlist_id=channel_id) + + webpage = self._download_webpage( + 'https://www.bitchute.com/channel/' + channel_id, channel_id, + headers={ + 'User-Agent': self._USER_AGENT, + }) + + title = self._search_title(webpage, 'channel-title', default=None) + + result = self.playlist_result( + self._list_entries(channel_id), playlist_id=channel_id, playlist_title=title) + + return merge_dicts( + result, + {'description': self._search_description(webpage, 'channel-description')}) + + +class BitChutePlaylistIE(BitChuteBaseIE): + _VALID_URL = r'https?://(?:www\.)?bitchute\.com/playlist/(?P<id>[^/?#&]+)' + _TEST = { + 'url': 'https://www.bitchute.com/playlist/g4WTfWTdYEQa/', + 'playlist_mincount': 1, + 'info_dict': { + 'id': 'g4WTfWTdYEQa', + 'title': 'Podcasts', + 'description': 'Podcast Playlist', + }, + } + _API_URL = 'https://www.bitchute.com/playlist/' + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage( + 'https://www.bitchute.com/playlist/' + playlist_id, playlist_id, + headers={ + 'User-Agent': self._USER_AGENT, + }) + + title = self._search_title(webpage, 'playlist-title', default=None) + + result = self.playlist_result( + self._list_entries(playlist_id), playlist_id=playlist_id, playlist_title=title) + + description = ( + strip_or_none(clean_html(get_element_by_class('description', webpage))) + or self._search_description(webpage, None)) + + return merge_dicts( + result, + {'description': description}) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 751fc38b6..d82b1e15b 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -132,6 +132,7 @@ from .biobiochiletv import BioBioChileTVIE from .bitchute import ( BitChuteIE, BitChuteChannelIE, + BitChutePlaylistIE, ) from .biqle import BIQLEIE from .bleacherreport import ( From 5ed0057798f636782985e890b61aba2829188897 Mon Sep 17 00:00:00 2001 From: dirkf <fieldhouse@gmx.net> Date: Fri, 10 Jun 2022 05:06:21 +0100 Subject: [PATCH 3/5] [BitChute] Handle NSFW in listings and single videos * listing: include NSFW if --age-limit 18 (or higher) * single video: extract 'age_limit': 18 if NSFW Resolves #24419 --- youtube_dl/extractor/bitchute.py | 75 +++++++++++++++++++++++++++----- 1 file changed, 65 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 8946933b8..0cc8d8fcf 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -11,6 +11,7 @@ from ..utils import ( GeoRestrictedError, get_element_by_class, get_element_by_id, + int_or_none, merge_dicts, orderedSet, strip_or_none, @@ -26,6 +27,7 @@ class BitChuteBaseIE(InfoExtractor): TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7' list_url = self._API_URL + list_id offset = 0 + query = {'showall': '1'} if 18 <= int_or_none(self._downloader.params.get('age_limit')) or 0 else None for page_num in itertools.count(1): data = self._download_json( list_url + '/extend/', list_id, @@ -39,7 +41,7 @@ class BitChuteBaseIE(InfoExtractor): 'Referer': list_url, 'X-Requested-With': 'XMLHttpRequest', 'Cookie': 'csrftoken=' + TOKEN, - }) + }, query=query) if data.get('success') is False: break html = data.get('html') @@ -85,6 +87,22 @@ class BitChuteIE(BitChuteBaseIE): 'description': 'md5:a0337e7b1fe39e32336974af8173a034', 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'BitChute', + 'age_limit': None, + }, + }, { + # NSFW (#24419) + 'url': 'https://www.bitchute.com/video/wrTrKp7PmFZC/', + 'md5': '4ef880ce8d24e322172d41a0cf6f8096', + 'info_dict': { + 'id': 'wrTrKp7PmFZC', + 'ext': 'mp4', + 'title': "You Can't Stop Progress | Episode 2", + 'timestamp': 1541476920, + 'upload_date': '20181106', + 'description': 'md5:f191b538a2c4d8f57540141a6bfd7eb0', + 'thumbnail': r're:^https?://.*\.jpg$', + 'uploader': "You Can't Stop Progress", + 'age_limit': 18, }, }, { 'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/', @@ -104,11 +122,20 @@ class BitChuteIE(BitChuteBaseIE): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( + def get_error_title(html): + return strip_or_none(clean_html(get_element_by_class('page-title', html))) + + def get_error_text(html): + return strip_or_none(clean_html(get_element_by_id('page-detail', html))) + + webpage, urlh = self._download_webpage_handle( 'https://www.bitchute.com/video/' + video_id, video_id, headers={ 'User-Agent': self._USER_AGENT, - }) + }, expected_status=404) + + if urlh.getcode() == 404: + raise ExtractorError(get_error_title(webpage) or 'Cannot find video', expected=True) title = self._search_title(webpage, 'video-title') @@ -126,10 +153,16 @@ class BitChuteIE(BitChuteBaseIE): entries = self._parse_html5_media_entries( url, webpage, video_id) if not entries: - error = strip_or_none(clean_html(self.get_element_by_id('video-title'))) or 'Cannot find video' + error = strip_or_none(clean_html(get_element_by_id('video-title', webpage))) if error == 'Video Unavailable': - raise GeoRestrictedError(error) - raise ExtractorError(error) + raise GeoRestrictedError(error, expected=True) + error = get_error_title(webpage) + if error: + reason = get_error_text(webpage) + if reason: + self.to_screen(reason) + raise ExtractorError(error, expected=True) + raise ExtractorError('Cannot find video', ) formats = entries[0]['formats'] self._check_formats(formats, video_id) @@ -164,20 +197,42 @@ class BitChuteIE(BitChuteBaseIE): 'uploader': uploader, 'timestamp': timestamp, 'formats': formats, + 'age_limit': 18 if '>This video has been marked as Not Safe For Work' in webpage else None, } class BitChuteChannelIE(BitChuteBaseIE): _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)' - _TEST = { + _TESTS = [{ 'url': 'https://www.bitchute.com/channel/livesonnet/', 'playlist_mincount': 135, 'info_dict': { 'id': 'livesonnet', 'title': 'livesonnet_vidz', 'description': 'md5:b0017be20656a1347eeb84f1049fc424', + } + }, { + # channel with NSFW content, not listed + 'url': 'https://www.bitchute.com/channel/hQl9oMSgUyMX/', + 'playlist_maxcount': 150, + 'info_dict': { + 'id': 'hQl9oMSgUyMX', + 'title': "You Can't Stop Progress", + 'description': 'md5:a7e3fd8cf02e96ddcc73e9f13d2ce768', }, - } + }, { + # channel with NSFW content, listed with adult age limit + 'url': 'https://www.bitchute.com/channel/hQl9oMSgUyMX/', + 'playlist_mincount': 160, + 'info_dict': { + 'id': 'hQl9oMSgUyMX', + 'title': "You Can't Stop Progress", + 'description': 'md5:a7e3fd8cf02e96ddcc73e9f13d2ce768', + }, + 'params': { + 'age_limit': 18, + } + }] _API_URL = 'https://www.bitchute.com/channel/' def _real_extract(self, url): @@ -201,7 +256,7 @@ class BitChuteChannelIE(BitChuteBaseIE): class BitChutePlaylistIE(BitChuteBaseIE): _VALID_URL = r'https?://(?:www\.)?bitchute\.com/playlist/(?P<id>[^/?#&]+)' - _TEST = { + _TESTS = [{ 'url': 'https://www.bitchute.com/playlist/g4WTfWTdYEQa/', 'playlist_mincount': 1, 'info_dict': { @@ -209,7 +264,7 @@ class BitChutePlaylistIE(BitChuteBaseIE): 'title': 'Podcasts', 'description': 'Podcast Playlist', }, - } + }] _API_URL = 'https://www.bitchute.com/playlist/' def _real_extract(self, url): From add5e7dced00484343692dc04d568bc6b46ceeb3 Mon Sep 17 00:00:00 2001 From: dirkf <fieldhouse@gmx.net> Date: Fri, 10 Jun 2022 17:03:05 +0100 Subject: [PATCH 4/5] [BitChute] Extract `channel_url` * resolves #28500 --- youtube_dl/extractor/bitchute.py | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 0cc8d8fcf..533f555e3 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -17,6 +17,7 @@ from ..utils import ( strip_or_none, unified_timestamp, urlencode_postdata, + urljoin, ) @@ -88,6 +89,7 @@ class BitChuteIE(BitChuteBaseIE): 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'BitChute', 'age_limit': None, + 'channel_url': 'https://www.bitchute.com/channel/bitchute/', }, }, { # NSFW (#24419) @@ -103,6 +105,7 @@ class BitChuteIE(BitChuteBaseIE): 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': "You Can't Stop Progress", 'age_limit': 18, + 'channel_url': 'https://www.bitchute.com/channel/ycsp/', }, }, { 'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/', @@ -142,7 +145,7 @@ class BitChuteIE(BitChuteBaseIE): format_urls = [ mobj.group('url') for mobj in re.finditer( - r'''\baddWebSeed\s*\(\s*(["'])(?P<url>(?:(?!\1).)+)\1''', webpage)] + r'''\baddWebSeed\s*\(\s*("|')(?P<url>(?:(?!\1).)+)\1''', webpage)] format_urls.extend(re.findall(r'''as=(https?://[^&"']+)''', webpage)) formats = [ @@ -189,6 +192,14 @@ class BitChuteIE(BitChuteBaseIE): timestamp = more_unified_timestamp(get_element_by_class('video-publish-date', webpage)) + # TODO: remove this work-around for class matching bug + webpage = re.split(r'''('|")channel-banner\1''', webpage, 1)[-1] + channel_details = get_element_by_class('details', webpage) + channel_details = channel_details and get_element_by_class('name', channel_details) + channel_url = urljoin(url, self._search_regex( + r'''<a\b[^>]*?\bhref\s*=\s*('|")(?P<url>(?:(?!\1).)+)''', + channel_details or '', 'channel url', group='url', default=None)) + return { 'id': video_id, 'title': title, @@ -198,6 +209,7 @@ class BitChuteIE(BitChuteBaseIE): 'timestamp': timestamp, 'formats': formats, 'age_limit': 18 if '>This video has been marked as Not Safe For Work' in webpage else None, + 'channel_url': channel_url, } From ab362c8031b3ae63e174a1330133276b01e34f80 Mon Sep 17 00:00:00 2001 From: dirkf <fieldhouse@gmx.net> Date: Sat, 4 Feb 2023 02:36:34 +0000 Subject: [PATCH 5/5] Small update, force CI --- youtube_dl/extractor/bitchute.py | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 533f555e3..111a69c9a 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -14,7 +14,6 @@ from ..utils import ( int_or_none, merge_dicts, orderedSet, - strip_or_none, unified_timestamp, urlencode_postdata, urljoin, @@ -61,7 +60,7 @@ class BitChuteBaseIE(InfoExtractor): def _search_title(self, html, title_id, **kwargs): return ( - strip_or_none(clean_html(get_element_by_id(title_id, html))) + clean_html(get_element_by_id(title_id, html)) or None or self._og_search_title(html, default=None) or self._html_search_regex(r'(?s)<title\b[^>]*>.*?</title', html, 'title', **kwargs)) @@ -118,7 +117,7 @@ class BitChuteIE(BitChuteBaseIE): @staticmethod def _extract_urls(webpage): urls = re.finditer( - r'''<(?:script|iframe)\b[^>]+\bsrc\s*=\s*(["'])(?P<url>%s)''' % (BitChuteIE._VALID_URL, ), + r'''<(?:script|iframe)\b[^>]+\bsrc\s*=\s*("|')(?P<url>%s)''' % (BitChuteIE._VALID_URL, ), webpage) return (mobj.group('url') for mobj in urls) @@ -126,10 +125,10 @@ class BitChuteIE(BitChuteBaseIE): video_id = self._match_id(url) def get_error_title(html): - return strip_or_none(clean_html(get_element_by_class('page-title', html))) + return clean_html(get_element_by_class('page-title', html)) or None def get_error_text(html): - return strip_or_none(clean_html(get_element_by_id('page-detail', html))) + return clean_html(get_element_by_id('page-detail', html)) or None webpage, urlh = self._download_webpage_handle( 'https://www.bitchute.com/video/' + video_id, video_id, @@ -156,7 +155,7 @@ class BitChuteIE(BitChuteBaseIE): entries = self._parse_html5_media_entries( url, webpage, video_id) if not entries: - error = strip_or_none(clean_html(get_element_by_id('video-title', webpage))) + error = clean_html(get_element_by_id('video-title', webpage)) or None if error == 'Video Unavailable': raise GeoRestrictedError(error, expected=True) error = get_error_title(webpage) @@ -294,7 +293,7 @@ class BitChutePlaylistIE(BitChuteBaseIE): self._list_entries(playlist_id), playlist_id=playlist_id, playlist_title=title) description = ( - strip_or_none(clean_html(get_element_by_class('description', webpage))) + clean_html(get_element_by_class('description', webpage)) or self._search_description(webpage, None)) return merge_dicts(