diff --git a/README.md b/README.md index 0636d2f6e..5965d600e 100644 --- a/README.md +++ b/README.md @@ -2123,7 +2123,7 @@ # CHANGES FROM YOUTUBE-DL ### New features -* Forked from [**yt-dlc@f9401f2**](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee) and merged with [**youtube-dl@be008e6**](https://github.com/ytdl-org/youtube-dl/commit/be008e657d79832642e2158557c899249c9e31cd) ([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21)) +* Forked from [**yt-dlc@f9401f2**](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee) and merged with [**youtube-dl@a08f2b7**](https://github.com/ytdl-org/youtube-dl/commit/a08f2b7e4567cdc50c0614ee0a4ffdff49b8b6e6) ([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21)) * **[SponsorBlock Integration](#sponsorblock-options)**: You can mark/remove sponsor sections in YouTube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index e287e04bc..37e6fc318 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -308,6 +308,7 @@ from .buzzfeed import BuzzFeedIE from .byutv import BYUtvIE from .c56 import C56IE +from .caffeinetv import CaffeineTVIE from .callin import CallinIE from .caltrans import CaltransIE from .cam4 import CAM4IE @@ -720,6 +721,7 @@ from .gamestar import GameStarIE from .gaskrank import GaskrankIE from .gazeta import GazetaIE +from .gbnews import GBNewsIE from .gdcvault import GDCVaultIE from .gedidigital import GediDigitalIE from .generic import GenericIE @@ -2501,7 +2503,15 @@ YouNowLiveIE, YouNowMomentIE, ) -from .youporn import YouPornIE +from .youporn import ( + YouPornCategoryIE, + YouPornChannelIE, + YouPornCollectionIE, + YouPornIE, + YouPornStarIE, + YouPornTagIE, + YouPornVideosIE, +) from .zaiko import ( ZaikoETicketIE, ZaikoIE, diff --git a/yt_dlp/extractor/caffeinetv.py b/yt_dlp/extractor/caffeinetv.py new file mode 100644 index 000000000..aa107f858 --- /dev/null +++ b/yt_dlp/extractor/caffeinetv.py @@ -0,0 +1,74 @@ +from .common import InfoExtractor +from ..utils import ( + determine_ext, + int_or_none, + parse_iso8601, + traverse_obj, + urljoin, +) + + +class CaffeineTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?caffeine\.tv/[^/?#]+/video/(?P[\da-f-]+)' + _TESTS = [{ + 'url': 'https://www.caffeine.tv/TsuSurf/video/cffc0a00-e73f-11ec-8080-80017d29f26e', + 'info_dict': { + 'id': 'cffc0a00-e73f-11ec-8080-80017d29f26e', + 'ext': 'mp4', + 'title': 'GOOOOD MORNINNNNN #highlights', + 'timestamp': 1654702180, + 'upload_date': '20220608', + 'uploader': 'RahJON Wicc', + 'uploader_id': 'TsuSurf', + 'duration': 3145, + 'age_limit': 17, + 'thumbnail': 'https://www.caffeine.tv/broadcasts/776b6f84-9cd5-42e3-af1d-4a776eeed697/replay/lobby.jpg', + 'comment_count': int, + 'view_count': int, + 'like_count': int, + 'tags': ['highlights', 'battlerap'], + }, + 'params': { + 'skip_download': 'm3u8', + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + json_data = self._download_json( + f'https://api.caffeine.tv/social/public/activity/{video_id}', video_id) + broadcast_info = traverse_obj(json_data, ('broadcast_info', {dict})) or {} + + video_url = broadcast_info['video_url'] + ext = determine_ext(video_url) + if ext == 'm3u8': + formats = self._extract_m3u8_formats(video_url, video_id, 'mp4') + else: + formats = [{'url': video_url}] + + return { + 'id': video_id, + 'formats': formats, + **traverse_obj(json_data, { + 'like_count': ('like_count', {int_or_none}), + 'view_count': ('view_count', {int_or_none}), + 'comment_count': ('comment_count', {int_or_none}), + 'tags': ('tags', ..., {str}, {lambda x: x or None}), + 'uploader': ('user', 'name', {str}), + 'uploader_id': (((None, 'user'), 'username'), {str}, any), + 'is_live': ('is_live', {bool}), + }), + **traverse_obj(broadcast_info, { + 'title': ('broadcast_title', {str}), + 'duration': ('content_duration', {int_or_none}), + 'timestamp': ('broadcast_start_time', {parse_iso8601}), + 'thumbnail': ('preview_image_path', {lambda x: urljoin(url, x)}), + }), + 'age_limit': { + # assume Apple Store ratings: https://en.wikipedia.org/wiki/Mobile_software_content_rating_system + 'FOUR_PLUS': 0, + 'NINE_PLUS': 9, + 'TWELVE_PLUS': 12, + 'SEVENTEEN_PLUS': 17, + }.get(broadcast_info.get('content_rating'), 17), + } diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index a33cef354..38daad72e 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -3384,23 +3384,16 @@ def manifest_url(manifest): return formats def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json): - mobj = re.search( - r'''(?s)jwplayer\s*\(\s*(?P'|")(?!(?P=q)).+(?P=q)\s*\)(?!).*?\.\s*setup\s*\(\s*(?P(?:\([^)]*\)|[^)])+)\s*\)''', - webpage) - if mobj: - try: - jwplayer_data = self._parse_json(mobj.group('options'), - video_id=video_id, - transform_source=transform_source) - except ExtractorError: - pass - else: - if isinstance(jwplayer_data, dict): - return jwplayer_data + return self._search_json( + r'''(?'|")(?!(?P=q)).+(?P=q)\s*\)(?:(?!).)*?\.\s*(?:setup\s*\(|(?Pload)\s*\(\s*\[)''', + webpage, 'JWPlayer data', video_id, + # must be a {...} or sequence, ending + contains_pattern=r'\{(?s:.*)}(?(load)(?:\s*,\s*\{(?s:.*)})*)', end_pattern=r'(?(load)\]|\))', + transform_source=transform_source, default=None) - def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs): + def _extract_jwplayer_data(self, webpage, video_id, *args, transform_source=js_to_json, **kwargs): jwplayer_data = self._find_jwplayer_data( - webpage, video_id, transform_source=js_to_json) + webpage, video_id, transform_source=transform_source) return self._parse_jwplayer_data( jwplayer_data, video_id, *args, **kwargs) @@ -3432,22 +3425,14 @@ def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True, mpd_id=mpd_id, rtmp_params=rtmp_params, base_url=base_url) subtitles = {} - tracks = video_data.get('tracks') - if tracks and isinstance(tracks, list): - for track in tracks: - if not isinstance(track, dict): - continue - track_kind = track.get('kind') - if not track_kind or not isinstance(track_kind, str): - continue - if track_kind.lower() not in ('captions', 'subtitles'): - continue - track_url = urljoin(base_url, track.get('file')) - if not track_url: - continue - subtitles.setdefault(track.get('label') or 'en', []).append({ - 'url': self._proto_relative_url(track_url) - }) + for track in traverse_obj(video_data, ( + 'tracks', lambda _, v: v['kind'].lower() in ('captions', 'subtitles'))): + track_url = urljoin(base_url, track.get('file')) + if not track_url: + continue + subtitles.setdefault(track.get('label') or 'en', []).append({ + 'url': self._proto_relative_url(track_url) + }) entry = { 'id': this_video_id, diff --git a/yt_dlp/extractor/gbnews.py b/yt_dlp/extractor/gbnews.py new file mode 100644 index 000000000..bb1554eea --- /dev/null +++ b/yt_dlp/extractor/gbnews.py @@ -0,0 +1,107 @@ +import functools + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + extract_attributes, + get_elements_html_by_class, + url_or_none, +) +from ..utils.traversal import traverse_obj + + +class GBNewsIE(InfoExtractor): + IE_DESC = 'GB News clips, features and live streams' + _VALID_URL = r'https?://(?:www\.)?gbnews\.(?:uk|com)/(?:\w+/)?(?P[^#?]+)' + + _PLATFORM = 'safari' + _SSMP_URL = 'https://mm-v2.simplestream.com/ssmp/api.php' + _TESTS = [{ + 'url': 'https://www.gbnews.com/news/bbc-claudine-gay-harvard-university-antisemitism-row', + 'info_dict': { + 'id': '52264136', + 'ext': 'mp4', + 'thumbnail': r're:https?://www\.gbnews\.\w+/.+\.(?:jpe?g|png|webp)', + 'display_id': 'bbc-claudine-gay-harvard-university-antisemitism-row', + 'description': 'The post was criticised by former employers of the broadcaster', + 'title': 'BBC deletes post after furious backlash over headline downplaying antisemitism', + }, + }, { + 'url': 'https://www.gbnews.com/royal/prince-harry-in-love-with-kate-meghan-markle-jealous-royal', + 'info_dict': { + 'id': '52328390', + 'ext': 'mp4', + 'thumbnail': r're:https?://www\.gbnews\.\w+/.+\.(?:jpe?g|png|webp)', + 'display_id': 'prince-harry-in-love-with-kate-meghan-markle-jealous-royal', + 'description': 'Ingrid Seward has published 17 books documenting the highs and lows of the Royal Family', + 'title': 'Royal author claims Prince Harry was \'in love\' with Kate - Meghan was \'jealous\'', + } + }, { + 'url': 'https://www.gbnews.uk/watchlive', + 'info_dict': { + 'id': '1069', + 'ext': 'mp4', + 'thumbnail': r're:https?://www\.gbnews\.\w+/.+\.(?:jpe?g|png|webp)', + 'display_id': 'watchlive', + 'live_status': 'is_live', + 'title': r're:^GB News Live', + }, + 'params': {'skip_download': 'm3u8'}, + }] + + @functools.lru_cache + def _get_ss_endpoint(self, data_id, data_env): + if not data_id: + data_id = 'GB003' + if not data_env: + data_env = 'production' + + json_data = self._download_json( + self._SSMP_URL, None, 'Downloading Simplestream JSON metadata', query={ + 'id': data_id, + 'env': data_env, + }) + meta_url = traverse_obj(json_data, ('response', 'api_hostname', {url_or_none})) + if not meta_url: + raise ExtractorError('No API host found') + + return meta_url + + def _real_extract(self, url): + display_id = self._match_id(url).rpartition('/')[2] + webpage = self._download_webpage(url, display_id) + + video_data = None + elements = get_elements_html_by_class('simplestream', webpage) + for html_tag in elements: + attributes = extract_attributes(html_tag) + if 'sidebar' not in (attributes.get('class') or ''): + video_data = attributes + if not video_data: + raise ExtractorError('Could not find video element', expected=True) + + endpoint_url = self._get_ss_endpoint(video_data.get('data-id'), video_data.get('data-env')) + + uvid = video_data['data-uvid'] + video_type = video_data.get('data-type') + if not video_type or video_type == 'vod': + video_type = 'show' + stream_data = self._download_json( + f'{endpoint_url}/api/{video_type}/stream/{uvid}', + uvid, 'Downloading stream JSON', query={ + 'key': video_data.get('data-key'), + 'platform': self._PLATFORM, + }) + if traverse_obj(stream_data, 'drm'): + self.report_drm(uvid) + + return { + 'id': uvid, + 'display_id': display_id, + 'title': self._og_search_title(webpage, default=None), + 'description': self._og_search_description(webpage, default=None), + 'formats': self._extract_m3u8_formats(traverse_obj(stream_data, ( + 'response', 'stream', {url_or_none})), uvid, 'mp4'), + 'thumbnail': self._og_search_thumbnail(webpage, default=None), + 'is_live': video_type == 'live', + } diff --git a/yt_dlp/extractor/youporn.py b/yt_dlp/extractor/youporn.py index 6d4e31bf3..0e047aa16 100644 --- a/yt_dlp/extractor/youporn.py +++ b/yt_dlp/extractor/youporn.py @@ -1,19 +1,27 @@ +import itertools import re from .common import InfoExtractor from ..utils import ( + ExtractorError, + clean_html, extract_attributes, + get_element_by_class, + get_element_by_id, + get_elements_html_by_class, int_or_none, merge_dicts, - str_to_int, + parse_count, + parse_qs, traverse_obj, unified_strdate, url_or_none, + urljoin, ) class YouPornIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P\d+)(?:/(?P[^/?#&]+))?' + _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P\d+)(?:/(?P[^/?#&]+))?/?(?:[#?]|$)' _EMBED_REGEX = [r']+\bsrc=["\'](?P(?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)'] _TESTS = [{ 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', @@ -34,7 +42,7 @@ class YouPornIE(InfoExtractor): 'tags': list, 'age_limit': 18, }, - 'skip': 'This video has been disabled', + 'skip': 'This video has been deactivated', }, { # Unknown uploader 'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4', @@ -72,7 +80,6 @@ class YouPornIE(InfoExtractor): 'id': '16290308', 'age_limit': 18, 'categories': [], - 'description': str, # TODO: detect/remove SEO spam description in ytdl backport 'display_id': 'tinderspecial-trailer1', 'duration': 298.0, 'ext': 'mp4', @@ -90,7 +97,17 @@ def _real_extract(self, url): video_id, display_id = self._match_valid_url(url).group('id', 'display_id') self._set_cookie('.youporn.com', 'age_verified', '1') webpage = self._download_webpage(f'https://www.youporn.com/watch/{video_id}', video_id) - definitions = self._search_json(r'\bplayervars\s*:', webpage, 'player vars', video_id)['mediaDefinitions'] + + watchable = self._search_regex( + r'''(]*\bid\s*=\s*('|")?watch-container(?(2)\2|(?!-)\b)[^>]*>)''', + webpage, 'watchability', default=None) + if not watchable: + msg = re.split(r'\s{2}', clean_html(get_element_by_id('mainContent', webpage)) or '')[0] + raise ExtractorError( + f'{self.IE_NAME} says: {msg}' if msg else 'Video unavailable', expected=True) + + player_vars = self._search_json(r'\bplayervars\s*:', webpage, 'player vars', video_id) + definitions = player_vars['mediaDefinitions'] def get_format_data(data, stream_type): info_url = traverse_obj(data, (lambda _, v: v['format'] == stream_type, 'videoUrl', {url_or_none}, any)) @@ -143,8 +160,10 @@ def get_format_data(data, stream_type): thumbnail = self._search_regex( r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P.+?)\1', webpage, 'thumbnail', fatal=False, group='thumbnail') - duration = int_or_none(self._html_search_meta( - 'video:duration', webpage, 'duration', fatal=False)) + duration = traverse_obj(player_vars, ('duration', {int_or_none})) + if duration is None: + duration = int_or_none(self._html_search_meta( + 'video:duration', webpage, 'duration', fatal=False)) uploader = self._html_search_regex( r'(?s)]+class=["\']submitByLink["\'][^>]*>(.+?)', @@ -160,11 +179,11 @@ def get_format_data(data, stream_type): view_count = None views = self._search_regex( - r'(]+\bclass=["\']js_videoInfoViews["\']>)', webpage, - 'views', default=None) + r'(
]*\bdata-value\s*=[^>]+>)\s*', + webpage, 'views', default=None) if views: - view_count = str_to_int(extract_attributes(views).get('data-value')) - comment_count = str_to_int(self._search_regex( + view_count = parse_count(extract_attributes(views).get('data-value')) + comment_count = parse_count(self._search_regex( r'>All [Cc]omments? \(([\d,.]+)\)', webpage, 'comment count', default=None)) @@ -182,7 +201,8 @@ def extract_tag_box(regex, title): data = self._search_json_ld(webpage, video_id, expected_type='VideoObject', fatal=False) data.pop('url', None) - return merge_dicts(data, { + + result = merge_dicts(data, { 'id': video_id, 'display_id': display_id, 'title': title, @@ -198,3 +218,350 @@ def extract_tag_box(regex, title): 'age_limit': age_limit, 'formats': formats, }) + + # Remove SEO spam "description" + description = result.get('description') + if description and description.startswith(f'Watch {result.get("title")} online'): + del result['description'] + + return result + + +class YouPornListBase(InfoExtractor): + def _get_next_url(self, url, pl_id, html): + return urljoin(url, self._search_regex( + r''']*?\bhref\s*=\s*("|')(?P(?:(?!\1)[^>])+)\1''', + get_element_by_id('next', html) or '', 'next page', + group='url', default=None)) + + @classmethod + def _get_title_from_slug(cls, title_slug): + return re.sub(r'[_-]', ' ', title_slug) + + def _entries(self, url, pl_id, html=None, page_num=None): + start = page_num or 1 + for page in itertools.count(start): + if not html: + html = self._download_webpage( + url, pl_id, note=f'Downloading page {page}', fatal=page == start) + if not html: + return + for element in get_elements_html_by_class('video-title', html): + if video_url := traverse_obj(element, ({extract_attributes}, 'href', {lambda x: urljoin(url, x)})): + yield self.url_result(video_url) + + if page_num is not None: + return + next_url = self._get_next_url(url, pl_id, html) + if not next_url or next_url == url: + return + url = next_url + html = None + + def _real_extract(self, url, html=None): + m_dict = self._match_valid_url(url).groupdict() + pl_id, page_type, sort = (m_dict.get(k) for k in ('id', 'type', 'sort')) + qs = {k: v[-1] for k, v in parse_qs(url).items() if v} + + base_id = pl_id or 'YouPorn' + title = self._get_title_from_slug(base_id) + if page_type: + title = f'{page_type.capitalize()} {title}' + base_id = [base_id.lower()] + if sort is None: + title += ' videos' + else: + title = f'{title} videos by {re.sub(r"[_-]", " ", sort)}' + base_id.append(sort) + if qs: + filters = list(map('='.join, sorted(qs.items()))) + title += f' ({",".join(filters)})' + base_id.extend(filters) + pl_id = '/'.join(base_id) + + return self.playlist_result( + self._entries(url, pl_id, html=html, page_num=int_or_none(qs.get('page'))), + playlist_id=pl_id, playlist_title=title) + + +class YouPornCategoryIE(YouPornListBase): + IE_DESC = 'YouPorn category, with sorting, filtering and pagination' + _VALID_URL = r'''(?x) + https?://(?:www\.)?youporn\.com/ + (?Pcategory)/(?P[^/?#&]+) + (?:/(?Ppopular|views|rating|time|duration))?/?(?:[#?]|$) + ''' + _TESTS = [{ + 'note': 'Full list with pagination', + 'url': 'https://www.youporn.com/category/popular-with-women/popular/', + 'info_dict': { + 'id': 'popular-with-women/popular', + 'title': 'Category popular with women videos by popular', + }, + 'playlist_mincount': 39, + }, { + 'note': 'Filtered paginated list with single page result', + 'url': 'https://www.youporn.com/category/popular-with-women/duration/?min_minutes=10', + 'info_dict': { + 'id': 'popular-with-women/duration/min_minutes=10', + 'title': 'Category popular with women videos by duration (min_minutes=10)', + }, + 'playlist_mincount': 2, + # 'playlist_maxcount': 30, + }, { + 'note': 'Single page of full list', + 'url': 'https://www.youporn.com/category/popular-with-women/popular?page=1', + 'info_dict': { + 'id': 'popular-with-women/popular/page=1', + 'title': 'Category popular with women videos by popular (page=1)', + }, + 'playlist_count': 36, + }] + + +class YouPornChannelIE(YouPornListBase): + IE_DESC = 'YouPorn channel, with sorting and pagination' + _VALID_URL = r'''(?x) + https?://(?:www\.)?youporn\.com/ + (?Pchannel)/(?P[^/?#&]+) + (?:/(?Prating|views|duration))?/?(?:[#?]|$) + ''' + _TESTS = [{ + 'note': 'Full list with pagination', + 'url': 'https://www.youporn.com/channel/x-feeds/', + 'info_dict': { + 'id': 'x-feeds', + 'title': 'Channel X-Feeds videos', + }, + 'playlist_mincount': 37, + }, { + 'note': 'Single page of full list (no filters here)', + 'url': 'https://www.youporn.com/channel/x-feeds/duration?page=1', + 'info_dict': { + 'id': 'x-feeds/duration/page=1', + 'title': 'Channel X-Feeds videos by duration (page=1)', + }, + 'playlist_count': 24, + }] + + @staticmethod + def _get_title_from_slug(title_slug): + return re.sub(r'_', ' ', title_slug).title() + + +class YouPornCollectionIE(YouPornListBase): + IE_DESC = 'YouPorn collection (user playlist), with sorting and pagination' + _VALID_URL = r'''(?x) + https?://(?:www\.)?youporn\.com/ + (?Pcollection)s/videos/(?P\d+) + (?:/(?Prating|views|time|duration))?/?(?:[#?]|$) + ''' + _TESTS = [{ + 'note': 'Full list with pagination', + 'url': 'https://www.youporn.com/collections/videos/33044251/', + 'info_dict': { + 'id': '33044251', + 'title': 'Collection Sexy Lips videos', + 'uploader': 'ph-littlewillyb', + }, + 'playlist_mincount': 50, + }, { + 'note': 'Single page of full list (no filters here)', + 'url': 'https://www.youporn.com/collections/videos/33044251/time?page=1', + 'info_dict': { + 'id': '33044251/time/page=1', + 'title': 'Collection Sexy Lips videos by time (page=1)', + 'uploader': 'ph-littlewillyb', + }, + 'playlist_count': 20, + }] + + def _real_extract(self, url): + pl_id = self._match_id(url) + html = self._download_webpage(url, pl_id) + playlist = super()._real_extract(url, html=html) + infos = re.sub(r'\s+', ' ', clean_html(get_element_by_class( + 'collection-infos', html)) or '') + title, uploader = self._search_regex( + r'^\s*Collection: (?P.+?) \d+ VIDEOS \d+ VIEWS \d+ days LAST UPDATED From: (?P<uploader>[\w_-]+)', + infos, 'title/uploader', group=('title', 'uploader'), default=(None, None)) + if title: + playlist.update({ + 'title': playlist['title'].replace(playlist['id'].split('/')[0], title), + 'uploader': uploader, + }) + + return playlist + + +class YouPornTagIE(YouPornListBase): + IE_DESC = 'YouPorn tag (porntags), with sorting, filtering and pagination' + _VALID_URL = r'''(?x) + https?://(?:www\.)?youporn\.com/ + porn(?P<type>tag)s/(?P<id>[^/?#&]+) + (?:/(?P<sort>views|rating|time|duration))?/?(?:[#?]|$) + ''' + _TESTS = [{ + 'note': 'Full list with pagination', + 'url': 'https://www.youporn.com/porntags/austrian', + 'info_dict': { + 'id': 'austrian', + 'title': 'Tag austrian videos', + }, + 'playlist_mincount': 33, + 'expected_warnings': ['YouPorn tag pages are not correctly cached'], + }, { + 'note': 'Filtered paginated list with single page result', + 'url': 'https://www.youporn.com/porntags/austrian/duration/?min_minutes=10', + 'info_dict': { + 'id': 'austrian/duration/min_minutes=10', + 'title': 'Tag austrian videos by duration (min_minutes=10)', + }, + 'playlist_mincount': 10, + # number of videos per page is (row x col) 2x3 + 6x4 + 2, or + 3, + # or more, varying with number of ads; let's set max as 9x4 + # NB col 1 may not be shown in non-JS page with site CSS and zoom 100% + # 'playlist_maxcount': 32, + 'expected_warnings': ['YouPorn tag pages are not correctly cached'], + }, { + 'note': 'Single page of full list', + 'url': 'https://www.youporn.com/porntags/austrian/?page=1', + 'info_dict': { + 'id': 'austrian/page=1', + 'title': 'Tag austrian videos (page=1)', + }, + 'playlist_mincount': 32, + # 'playlist_maxcount': 34, + 'expected_warnings': ['YouPorn tag pages are not correctly cached'], + }] + + def _real_extract(self, url): + self.report_warning( + 'YouPorn tag pages are not correctly cached and ' + 'often return incorrect results', only_once=True) + return super()._real_extract(url) + + +class YouPornStarIE(YouPornListBase): + IE_DESC = 'YouPorn Pornstar, with description, sorting and pagination' + _VALID_URL = r'''(?x) + https?://(?:www\.)?youporn\.com/ + (?P<type>pornstar)/(?P<id>[^/?#&]+) + (?:/(?P<sort>rating|views|duration))?/?(?:[#?]|$) + ''' + _TESTS = [{ + 'note': 'Full list with pagination', + 'url': 'https://www.youporn.com/pornstar/daynia/', + 'info_dict': { + 'id': 'daynia', + 'title': 'Pornstar Daynia videos', + 'description': r're:Daynia Rank \d+ Videos \d+ Views [\d,.]+ .+ Subscribers \d+', + }, + 'playlist_mincount': 40, + }, { + 'note': 'Single page of full list (no filters here)', + 'url': 'https://www.youporn.com/pornstar/daynia/?page=1', + 'info_dict': { + 'id': 'daynia/page=1', + 'title': 'Pornstar Daynia videos (page=1)', + 'description': 're:.{180,}', + }, + 'playlist_count': 26, + }] + + @staticmethod + def _get_title_from_slug(title_slug): + return re.sub(r'_', ' ', title_slug).title() + + def _real_extract(self, url): + pl_id = self._match_id(url) + html = self._download_webpage(url, pl_id) + playlist = super()._real_extract(url, html=html) + INFO_ELEMENT_RE = r'''(?x) + <div [^>]*\bclass\s*=\s*('|")(?:[\w$-]+\s+|\s)*?pornstar-info-wrapper(?:\s+[\w$-]+|\s)*\1[^>]*> + (?P<info>[\s\S]+?)(?:</div>\s*){6,} + ''' + + if infos := self._search_regex(INFO_ELEMENT_RE, html, 'infos', group='info', default=''): + infos = re.sub( + r'(?:\s*nl=nl)+\s*', ' ', + re.sub(r'(?u)\s+', ' ', clean_html(re.sub('\n', 'nl=nl', infos)))).replace('ribe Subsc', '') + + return { + **playlist, + 'description': infos.strip() or None, + } + + +class YouPornVideosIE(YouPornListBase): + IE_DESC = 'YouPorn video (browse) playlists, with sorting, filtering and pagination' + _VALID_URL = r'''(?x) + https?://(?:www\.)?youporn\.com/ + (?:(?P<id>browse)/)? + (?P<sort>(?(id) + (?:duration|rating|time|views)| + (?:most_(?:favou?rit|view)ed|recommended|top_rated)?)) + (?:[/#?]|$) + ''' + _TESTS = [{ + 'note': 'Full list with pagination (too long for test)', + 'url': 'https://www.youporn.com/', + 'info_dict': { + 'id': 'youporn', + 'title': 'YouPorn videos', + }, + 'only_matching': True, + }, { + 'note': 'Full list with pagination (too long for test)', + 'url': 'https://www.youporn.com/recommended', + 'info_dict': { + 'id': 'youporn/recommended', + 'title': 'YouPorn videos by recommended', + }, + 'only_matching': True, + }, { + 'note': 'Full list with pagination (too long for test)', + 'url': 'https://www.youporn.com/top_rated', + 'info_dict': { + 'id': 'youporn/top_rated', + 'title': 'YouPorn videos by top rated', + }, + 'only_matching': True, + }, { + 'note': 'Full list with pagination (too long for test)', + 'url': 'https://www.youporn.com/browse/time', + 'info_dict': { + 'id': 'browse/time', + 'title': 'YouPorn videos by time', + }, + 'only_matching': True, + }, { + 'note': 'Filtered paginated list with single page result', + 'url': 'https://www.youporn.com/most_favorited/?res=VR&max_minutes=2', + 'info_dict': { + 'id': 'youporn/most_favorited/max_minutes=2/res=VR', + 'title': 'YouPorn videos by most favorited (max_minutes=2,res=VR)', + }, + 'playlist_mincount': 10, + # 'playlist_maxcount': 28, + }, { + 'note': 'Filtered paginated list with several pages', + 'url': 'https://www.youporn.com/most_favorited/?res=VR&max_minutes=5', + 'info_dict': { + 'id': 'youporn/most_favorited/max_minutes=5/res=VR', + 'title': 'YouPorn videos by most favorited (max_minutes=5,res=VR)', + }, + 'playlist_mincount': 45, + }, { + 'note': 'Single page of full list', + 'url': 'https://www.youporn.com/browse/time?page=1', + 'info_dict': { + 'id': 'browse/time/page=1', + 'title': 'YouPorn videos by time (page=1)', + }, + 'playlist_count': 36, + }] + + @staticmethod + def _get_title_from_slug(title_slug): + return 'YouPorn' if title_slug == 'browse' else title_slug