diff --git a/README.md b/README.md index 09096218e8..c9fe47a9a9 100644 --- a/README.md +++ b/README.md @@ -1869,6 +1869,9 @@ The following extractors use this feature: #### digitalconcerthall * `prefer_combined_hls`: Prefer extracting combined/pre-merged video and audio HLS formats. This will exclude 4K/HEVC video and lossless/FLAC audio formats, which are only available as split video/audio HLS formats +#### sonylivseries +* `sort_order`: Episode sort order for series extraction - one of `asc` (ascending, oldest first) or `desc` (descending, newest first). Default is `asc` + **Note**: These options may be changed/removed in the future without concern for backward compatibility diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 25a233a2d6..967010826e 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -946,6 +946,10 @@ from .kaltura import KalturaIE from .kankanews import KankaNewsIE from .karaoketv import KaraoketvIE from .kelbyone import KelbyOneIE +from .kenh14 import ( + Kenh14PlaylistIE, + Kenh14VideoIE, +) from .khanacademy import ( KhanAcademyIE, KhanAcademyUnitIE, @@ -1135,12 +1139,6 @@ from .microsoftembed import ( MicrosoftMediusIE, ) from .microsoftstream import MicrosoftStreamIE -from .mildom import ( - MildomClipIE, - MildomIE, - MildomUserVodIE, - MildomVodIE, -) from .minds import ( MindsChannelIE, MindsGroupIE, @@ -1522,8 +1520,8 @@ from .pgatour import PGATourIE from .philharmoniedeparis import PhilharmonieDeParisIE from .phoenix import PhoenixIE from .photobucket import PhotobucketIE +from .pialive import PiaLiveIE from .piapro import PiaproIE -from .piaulizaportal import PIAULIZAPortalIE from .picarto import ( PicartoIE, PicartoVodIE, @@ -1559,10 +1557,6 @@ from .podbayfm import ( ) from .podchaser import PodchaserIE from .podomatic import PodomaticIE -from .pokemon import ( - PokemonIE, - PokemonWatchIE, -) from .pokergo import ( PokerGoCollectionIE, PokerGoIE, @@ -2256,6 +2250,10 @@ from .ufctv import ( ) from .ukcolumn import UkColumnIE from .uktvplay import UKTVPlayIE +from .uliza import ( + UlizaPlayerIE, + UlizaPortalIE, +) from .umg import UMGDeIE from .unistra import UnistraIE from .unity import UnityIE @@ -2284,10 +2282,6 @@ from .utreon import UtreonIE from .varzesh3 import Varzesh3IE from .vbox7 import Vbox7IE from .veo import VeoIE -from .veoh import ( - VeohIE, - VeohUserIE, -) from .vesti import VestiIE from .vevo import ( VevoIE, diff --git a/yt_dlp/extractor/chaturbate.py b/yt_dlp/extractor/chaturbate.py index aa70f26a1b..a40b7d39c7 100644 --- a/yt_dlp/extractor/chaturbate.py +++ b/yt_dlp/extractor/chaturbate.py @@ -79,7 +79,7 @@ class ChaturbateIE(InfoExtractor): 'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True), } - def _extract_from_webpage(self, video_id, tld): + def _extract_from_html(self, video_id, tld): webpage = self._download_webpage( f'https://chaturbate.{tld}/{video_id}/', video_id, headers=self.geo_verification_headers(), impersonate=True) @@ -151,4 +151,4 @@ class ChaturbateIE(InfoExtractor): def _real_extract(self, url): video_id, tld = self._match_valid_url(url).group('id', 'tld') - return self._extract_from_api(video_id, tld) or self._extract_from_webpage(video_id, tld) + return self._extract_from_api(video_id, tld) or self._extract_from_html(video_id, tld) diff --git a/yt_dlp/extractor/ctvnews.py b/yt_dlp/extractor/ctvnews.py index ebed9eb2d3..c3ddcdbee4 100644 --- a/yt_dlp/extractor/ctvnews.py +++ b/yt_dlp/extractor/ctvnews.py @@ -1,14 +1,27 @@ +import json import re +import urllib.parse from .common import InfoExtractor -from ..utils import orderedSet +from .ninecninemedia import NineCNineMediaIE +from ..utils import extract_attributes, orderedSet +from ..utils.traversal import find_element, traverse_obj class CTVNewsIE(InfoExtractor): - _VALID_URL = r'https?://(?:.+?\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P[0-9.]+)' + _BASE_REGEX = r'https?://(?:[^.]+\.)?ctvnews\.ca/' + _VIDEO_ID_RE = r'(?P\d{5,})' + _PLAYLIST_ID_RE = r'(?P\d\.\d{5,})' + _VALID_URL = [ + rf'{_BASE_REGEX}video/c{_VIDEO_ID_RE}', + rf'{_BASE_REGEX}video(?:-gallery)?/?\?clipId={_VIDEO_ID_RE}', + rf'{_BASE_REGEX}video/?\?(?:playlist|bin)Id={_PLAYLIST_ID_RE}', + rf'{_BASE_REGEX}(?!video/)[^?#]*?{_PLAYLIST_ID_RE}/?(?:$|[?#])', + rf'{_BASE_REGEX}(?!video/)[^?#]+\?binId={_PLAYLIST_ID_RE}', + ] _TESTS = [{ 'url': 'http://www.ctvnews.ca/video?clipId=901995', - 'md5': '9b8624ba66351a23e0b6e1391971f9af', + 'md5': 'b608f466c7fa24b9666c6439d766ab7e', 'info_dict': { 'id': '901995', 'ext': 'flv', @@ -16,6 +29,33 @@ class CTVNewsIE(InfoExtractor): 'description': 'md5:958dd3b4f5bbbf0ed4d045c790d89285', 'timestamp': 1467286284, 'upload_date': '20160630', + 'categories': [], + 'season_number': 0, + 'season': 'Season 0', + 'tags': [], + 'series': 'CTV News National | Archive | Stories 2', + 'season_id': '57981', + 'thumbnail': r're:https?://.*\.jpg$', + 'duration': 764.631, + }, + }, { + 'url': 'https://barrie.ctvnews.ca/video/c3030933-here_s-what_s-making-news-for-nov--15?binId=1272429', + 'md5': '8b8c2b33c5c1803e3c26bc74ff8694d5', + 'info_dict': { + 'id': '3030933', + 'ext': 'flv', + 'title': 'Here’s what’s making news for Nov. 15', + 'description': 'Here are the top stories we’re working on for CTV News at 11 for Nov. 15', + 'thumbnail': 'http://images2.9c9media.com/image_asset/2021_2_22_a602e68e-1514-410e-a67a-e1f7cccbacab_png_2000x1125.jpg', + 'season_id': '58104', + 'season_number': 0, + 'tags': [], + 'season': 'Season 0', + 'categories': [], + 'series': 'CTV News Barrie', + 'upload_date': '20241116', + 'duration': 42.943, + 'timestamp': 1731722452, }, }, { 'url': 'http://www.ctvnews.ca/video?playlistId=1.2966224', @@ -31,6 +71,72 @@ class CTVNewsIE(InfoExtractor): 'id': '1.2876780', }, 'playlist_mincount': 100, + }, { + 'url': 'https://www.ctvnews.ca/it-s-been-23-years-since-toronto-called-in-the-army-after-a-major-snowstorm-1.5736957', + 'info_dict': + { + 'id': '1.5736957', + }, + 'playlist_mincount': 6, + }, { + 'url': 'https://www.ctvnews.ca/business/respondents-to-bank-of-canada-questionnaire-largely-oppose-creating-a-digital-loonie-1.6665797', + 'md5': '24bc4b88cdc17d8c3fc01dfc228ab72c', + 'info_dict': { + 'id': '2695026', + 'ext': 'flv', + 'season_id': '89852', + 'series': 'From CTV News Channel', + 'description': 'md5:796a985a23cacc7e1e2fafefd94afd0a', + 'season': '2023', + 'title': 'Bank of Canada asks public about digital currency', + 'categories': [], + 'tags': [], + 'upload_date': '20230526', + 'season_number': 2023, + 'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg', + 'timestamp': 1685105157, + 'duration': 253.553, + }, + }, { + 'url': 'https://stox.ctvnews.ca/video-gallery?clipId=582589', + 'md5': '135cc592df607d29dddc931f1b756ae2', + 'info_dict': { + 'id': '582589', + 'ext': 'flv', + 'categories': [], + 'timestamp': 1427906183, + 'season_number': 0, + 'duration': 125.559, + 'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg', + 'series': 'CTV News Stox', + 'description': 'CTV original footage of the rise and fall of the Berlin Wall.', + 'title': 'Berlin Wall', + 'season_id': '63817', + 'season': 'Season 0', + 'tags': [], + 'upload_date': '20150401', + }, + }, { + 'url': 'https://ottawa.ctvnews.ca/features/regional-contact/regional-contact-archive?binId=1.1164587#3023759', + 'md5': 'a14c0603557decc6531260791c23cc5e', + 'info_dict': { + 'id': '3023759', + 'ext': 'flv', + 'season_number': 2024, + 'timestamp': 1731798000, + 'season': '2024', + 'episode': 'Episode 125', + 'description': 'CTV News Ottawa at Six', + 'duration': 2712.076, + 'episode_number': 125, + 'upload_date': '20241116', + 'title': 'CTV News Ottawa at Six for Saturday, November 16, 2024', + 'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg', + 'categories': [], + 'tags': [], + 'series': 'CTV News Ottawa at Six', + 'season_id': '92667', + }, }, { 'url': 'http://www.ctvnews.ca/1.810401', 'only_matching': True, @@ -42,29 +148,35 @@ class CTVNewsIE(InfoExtractor): 'only_matching': True, }] + def _ninecninemedia_url_result(self, clip_id): + return self.url_result(f'9c9media:ctvnews_web:{clip_id}', NineCNineMediaIE, clip_id) + def _real_extract(self, url): page_id = self._match_id(url) - def ninecninemedia_url_result(clip_id): - return { - '_type': 'url_transparent', - 'id': clip_id, - 'url': f'9c9media:ctvnews_web:{clip_id}', - 'ie_key': 'NineCNineMedia', - } + if mobj := re.fullmatch(self._VIDEO_ID_RE, urllib.parse.urlparse(url).fragment): + page_id = mobj.group('id') - if page_id.isdigit(): - return ninecninemedia_url_result(page_id) - else: - webpage = self._download_webpage(f'http://www.ctvnews.ca/{page_id}', page_id, query={ - 'ot': 'example.AjaxPageLayout.ot', - 'maxItemsPerPage': 1000000, - }) - entries = [ninecninemedia_url_result(clip_id) for clip_id in orderedSet( - re.findall(r'clip\.id\s*=\s*(\d+);', webpage))] - if not entries: - webpage = self._download_webpage(url, page_id) - if 'getAuthStates("' in webpage: - entries = [ninecninemedia_url_result(clip_id) for clip_id in - self._search_regex(r'getAuthStates\("([\d+,]+)"', webpage, 'clip ids').split(',')] - return self.playlist_result(entries, page_id) + if re.fullmatch(self._VIDEO_ID_RE, page_id): + return self._ninecninemedia_url_result(page_id) + + webpage = self._download_webpage(f'https://www.ctvnews.ca/{page_id}', page_id, query={ + 'ot': 'example.AjaxPageLayout.ot', + 'maxItemsPerPage': 1000000, + }) + entries = [self._ninecninemedia_url_result(clip_id) + for clip_id in orderedSet(re.findall(r'clip\.id\s*=\s*(\d+);', webpage))] + if not entries: + webpage = self._download_webpage(url, page_id) + if 'getAuthStates("' in webpage: + entries = [self._ninecninemedia_url_result(clip_id) for clip_id in + self._search_regex(r'getAuthStates\("([\d+,]+)"', webpage, 'clip ids').split(',')] + else: + entries = [ + self._ninecninemedia_url_result(clip_id) for clip_id in + traverse_obj(webpage, ( + {find_element(tag='jasper-player-container', html=True)}, + {extract_attributes}, 'axis-ids', {json.loads}, ..., 'axisId')) + ] + + return self.playlist_result(entries, page_id) diff --git a/yt_dlp/extractor/kenh14.py b/yt_dlp/extractor/kenh14.py new file mode 100644 index 0000000000..3c46020e8b --- /dev/null +++ b/yt_dlp/extractor/kenh14.py @@ -0,0 +1,160 @@ +from .common import InfoExtractor +from ..utils import ( + clean_html, + extract_attributes, + get_element_by_class, + get_element_html_by_attribute, + get_elements_html_by_class, + int_or_none, + parse_duration, + parse_iso8601, + remove_start, + strip_or_none, + unescapeHTML, + update_url, + url_or_none, +) +from ..utils.traversal import traverse_obj + + +class Kenh14VideoIE(InfoExtractor): + _VALID_URL = r'https?://video\.kenh14\.vn/(?:video/)?[\w-]+-(?P[0-9]+)\.chn' + _TESTS = [{ + 'url': 'https://video.kenh14.vn/video/mo-hop-iphone-14-pro-max-nguon-unbox-therapy-316173.chn', + 'md5': '1ed67f9c3a1e74acf15db69590cf6210', + 'info_dict': { + 'id': '316173', + 'ext': 'mp4', + 'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)', + 'description': 'Video mở hộp iPhone 14 Pro MaxVideo mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)', + 'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$', + 'tags': [], + 'uploader': 'Unbox Therapy', + 'upload_date': '20220517', + 'view_count': int, + 'duration': 722.86, + 'timestamp': 1652764468, + }, + }, { + 'url': 'https://video.kenh14.vn/video-316174.chn', + 'md5': '2b41877d2afaf4a3f487ceda8e5c7cbd', + 'info_dict': { + 'id': '316174', + 'ext': 'mp4', + 'title': 'Khoảnh khắc VĐV nằm gục khóc sau chiến thắng: 7 năm trời Việt Nam mới có HCV kiếm chém nữ, chỉ có 8 tháng để khổ luyện trước khi lên sàn đấu', + 'description': 'md5:de86aa22e143e2b277bce8ec9c6f17dc', + 'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$', + 'tags': [], + 'upload_date': '20220517', + 'view_count': int, + 'duration': 70.04, + 'timestamp': 1652766021, + }, + }, { + 'url': 'https://video.kenh14.vn/0-344740.chn', + 'md5': 'b843495d5e728142c8870c09b46df2a9', + 'info_dict': { + 'id': '344740', + 'ext': 'mov', + 'title': 'Kỳ Duyên đầy căng thẳng trong buổi ra quân đi Miss Universe, nghi thức tuyên thuệ lần đầu xuất hiện gây nhiều tranh cãi', + 'description': 'md5:2a2dbb4a7397169fb21ee68f09160497', + 'thumbnail': r're:^https?://kenh14cdn\.com/.*\.jpg$', + 'tags': ['kỳ duyên', 'Kỳ Duyên tuyên thuệ', 'miss universe'], + 'uploader': 'Quang Vũ', + 'upload_date': '20241024', + 'view_count': int, + 'duration': 198.88, + 'timestamp': 1729741590, + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + attrs = extract_attributes(get_element_html_by_attribute('type', 'VideoStream', webpage) or '') + direct_url = attrs['data-vid'] + + metadata = self._download_json( + 'https://api.kinghub.vn/video/api/v1/detailVideoByGet?FileName={}'.format( + remove_start(direct_url, 'kenh14cdn.com/')), video_id, fatal=False) + + formats = [{'url': f'https://{direct_url}', 'format_id': 'http', 'quality': 1}] + subtitles = {} + video_data = self._download_json( + f'https://{direct_url}.json', video_id, note='Downloading video data', fatal=False) + if hls_url := traverse_obj(video_data, ('hls', {url_or_none})): + fmts, subs = self._extract_m3u8_formats_and_subtitles( + hls_url, video_id, m3u8_id='hls', fatal=False) + formats.extend(fmts) + self._merge_subtitles(subs, target=subtitles) + if dash_url := traverse_obj(video_data, ('mpd', {url_or_none})): + fmts, subs = self._extract_mpd_formats_and_subtitles( + dash_url, video_id, mpd_id='dash', fatal=False) + formats.extend(fmts) + self._merge_subtitles(subs, target=subtitles) + + return { + **traverse_obj(metadata, { + 'duration': ('duration', {parse_duration}), + 'uploader': ('author', {strip_or_none}), + 'timestamp': ('uploadtime', {parse_iso8601(delimiter=' ')}), + 'view_count': ('views', {int_or_none}), + }), + 'id': video_id, + 'title': ( + traverse_obj(metadata, ('title', {strip_or_none})) + or clean_html(self._og_search_title(webpage)) + or clean_html(get_element_by_class('vdbw-title', webpage))), + 'formats': formats, + 'subtitles': subtitles, + 'description': ( + clean_html(self._og_search_description(webpage)) + or clean_html(get_element_by_class('vdbw-sapo', webpage))), + 'thumbnail': (self._og_search_thumbnail(webpage) or attrs.get('data-thumb')), + 'tags': traverse_obj(self._html_search_meta('keywords', webpage), ( + {lambda x: x.split(';')}, ..., filter)), + } + + +class Kenh14PlaylistIE(InfoExtractor): + _VALID_URL = r'https?://video\.kenh14\.vn/playlist/[\w-]+-(?P[0-9]+)\.chn' + _TESTS = [{ + 'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn', + 'info_dict': { + 'id': '71', + 'title': 'Trần Tình (Naked love) mùa 2', + 'description': 'md5:e9522339304956dea931722dd72eddb2', + 'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$', + }, + 'playlist_count': 9, + }, { + 'url': 'https://video.kenh14.vn/playlist/0-72.chn', + 'info_dict': { + 'id': '72', + 'title': 'Lau Lại Đầu Từ', + 'description': 'Cùng xem xưa và nay có gì khác biệt nhé!', + 'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$', + }, + 'playlist_count': 6, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + webpage = self._download_webpage(url, playlist_id) + + category_detail = get_element_by_class('category-detail', webpage) or '' + embed_info = traverse_obj( + self._yield_json_ld(webpage, playlist_id), + (lambda _, v: v['name'] and v['alternateName'], any)) or {} + + return self.playlist_from_matches( + get_elements_html_by_class('video-item', webpage), playlist_id, + (clean_html(get_element_by_class('name', category_detail)) or unescapeHTML(embed_info.get('name'))), + getter=lambda x: 'https://video.kenh14.vn/video/video-{}.chn'.format(extract_attributes(x)['data-id']), + ie=Kenh14VideoIE, playlist_description=( + clean_html(get_element_by_class('description', category_detail)) + or unescapeHTML(embed_info.get('alternateName'))), + thumbnail=traverse_obj( + self._og_search_thumbnail(webpage), + ({url_or_none}, {update_url(query=None)}))) diff --git a/yt_dlp/extractor/mildom.py b/yt_dlp/extractor/mildom.py deleted file mode 100644 index 88a2b9e891..0000000000 --- a/yt_dlp/extractor/mildom.py +++ /dev/null @@ -1,291 +0,0 @@ -import functools -import json -import uuid - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - OnDemandPagedList, - determine_ext, - dict_get, - float_or_none, - traverse_obj, -) - - -class MildomBaseIE(InfoExtractor): - _GUEST_ID = None - - def _call_api(self, url, video_id, query=None, note='Downloading JSON metadata', body=None): - if not self._GUEST_ID: - self._GUEST_ID = f'pc-gp-{uuid.uuid4()}' - - content = self._download_json( - url, video_id, note=note, data=json.dumps(body).encode() if body else None, - headers={'Content-Type': 'application/json'} if body else {}, - query={ - '__guest_id': self._GUEST_ID, - '__platform': 'web', - **(query or {}), - }) - - if content['code'] != 0: - raise ExtractorError( - f'Mildom says: {content["message"]} (code {content["code"]})', - expected=True) - return content['body'] - - -class MildomIE(MildomBaseIE): - IE_NAME = 'mildom' - IE_DESC = 'Record ongoing live by specific user in Mildom' - _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/(?P\d+)' - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(f'https://www.mildom.com/{video_id}', video_id) - - enterstudio = self._call_api( - 'https://cloudac.mildom.com/nonolive/gappserv/live/enterstudio', video_id, - note='Downloading live metadata', query={'user_id': video_id}) - result_video_id = enterstudio.get('log_id', video_id) - - servers = self._call_api( - 'https://cloudac.mildom.com/nonolive/gappserv/live/liveserver', result_video_id, - note='Downloading live server list', query={ - 'user_id': video_id, - 'live_server_type': 'hls', - }) - - playback_token = self._call_api( - 'https://cloudac.mildom.com/nonolive/gappserv/live/token', result_video_id, - note='Obtaining live playback token', body={'host_id': video_id, 'type': 'hls'}) - playback_token = traverse_obj(playback_token, ('data', ..., 'token'), get_all=False) - if not playback_token: - raise ExtractorError('Failed to obtain live playback token') - - formats = self._extract_m3u8_formats( - f'{servers["stream_server"]}/{video_id}_master.m3u8?{playback_token}', - result_video_id, 'mp4', headers={ - 'Referer': 'https://www.mildom.com/', - 'Origin': 'https://www.mildom.com', - }) - - for fmt in formats: - fmt.setdefault('http_headers', {})['Referer'] = 'https://www.mildom.com/' - - return { - 'id': result_video_id, - 'title': self._html_search_meta('twitter:description', webpage, default=None) or traverse_obj(enterstudio, 'anchor_intro'), - 'description': traverse_obj(enterstudio, 'intro', 'live_intro', expected_type=str), - 'timestamp': float_or_none(enterstudio.get('live_start_ms'), scale=1000), - 'uploader': self._html_search_meta('twitter:title', webpage, default=None) or traverse_obj(enterstudio, 'loginname'), - 'uploader_id': video_id, - 'formats': formats, - 'is_live': True, - } - - -class MildomVodIE(MildomBaseIE): - IE_NAME = 'mildom:vod' - IE_DESC = 'VOD in Mildom' - _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/playback/(?P\d+)/(?P(?P=user_id)-[a-zA-Z0-9]+-?[0-9]*)' - _TESTS = [{ - 'url': 'https://www.mildom.com/playback/10882672/10882672-1597662269', - 'info_dict': { - 'id': '10882672-1597662269', - 'ext': 'mp4', - 'title': '始めてのミルダム配信じゃぃ！', - 'thumbnail': r're:^https?://.*\.(png|jpg)$', - 'upload_date': '20200817', - 'duration': 4138.37, - 'description': 'ゲームをしたくて！', - 'timestamp': 1597662269.0, - 'uploader_id': '10882672', - 'uploader': 'kson組長(けいそん)', - }, - }, { - 'url': 'https://www.mildom.com/playback/10882672/10882672-1597758589870-477', - 'info_dict': { - 'id': '10882672-1597758589870-477', - 'ext': 'mp4', - 'title': '【kson】感染メイズ！麻酔銃で無双する', - 'thumbnail': r're:^https?://.*\.(png|jpg)$', - 'timestamp': 1597759093.0, - 'uploader': 'kson組長(けいそん)', - 'duration': 4302.58, - 'uploader_id': '10882672', - 'description': 'このステージ絶対乗り越えたい', - 'upload_date': '20200818', - }, - }, { - 'url': 'https://www.mildom.com/playback/10882672/10882672-buha9td2lrn97fk2jme0', - 'info_dict': { - 'id': '10882672-buha9td2lrn97fk2jme0', - 'ext': 'mp4', - 'title': '【kson組長】CART RACER!!!', - 'thumbnail': r're:^https?://.*\.(png|jpg)$', - 'uploader_id': '10882672', - 'uploader': 'kson組長(けいそん)', - 'upload_date': '20201104', - 'timestamp': 1604494797.0, - 'duration': 4657.25, - 'description': 'WTF', - }, - }] - - def _real_extract(self, url): - user_id, video_id = self._match_valid_url(url).group('user_id', 'id') - webpage = self._download_webpage(f'https://www.mildom.com/playback/{user_id}/{video_id}', video_id) - - autoplay = self._call_api( - 'https://cloudac.mildom.com/nonolive/videocontent/playback/getPlaybackDetail', video_id, - note='Downloading playback metadata', query={ - 'v_id': video_id, - })['playback'] - - formats = [{ - 'url': autoplay['audio_url'], - 'format_id': 'audio', - 'protocol': 'm3u8_native', - 'vcodec': 'none', - 'acodec': 'aac', - 'ext': 'm4a', - }] - for fmt in autoplay['video_link']: - formats.append({ - 'format_id': 'video-{}'.format(fmt['name']), - 'url': fmt['url'], - 'protocol': 'm3u8_native', - 'width': fmt['level'] * autoplay['video_width'] // autoplay['video_height'], - 'height': fmt['level'], - 'vcodec': 'h264', - 'acodec': 'aac', - 'ext': 'mp4', - }) - - return { - 'id': video_id, - 'title': self._html_search_meta(('og:description', 'description'), webpage, default=None) or autoplay.get('title'), - 'description': traverse_obj(autoplay, 'video_intro'), - 'timestamp': float_or_none(autoplay.get('publish_time'), scale=1000), - 'duration': float_or_none(autoplay.get('video_length'), scale=1000), - 'thumbnail': dict_get(autoplay, ('upload_pic', 'video_pic')), - 'uploader': traverse_obj(autoplay, ('author_info', 'login_name')), - 'uploader_id': user_id, - 'formats': formats, - } - - -class MildomClipIE(MildomBaseIE): - IE_NAME = 'mildom:clip' - IE_DESC = 'Clip in Mildom' - _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/clip/(?P(?P\d+)-[a-zA-Z0-9]+)' - _TESTS = [{ - 'url': 'https://www.mildom.com/clip/10042245-63921673e7b147ebb0806d42b5ba5ce9', - 'info_dict': { - 'id': '10042245-63921673e7b147ebb0806d42b5ba5ce9', - 'title': '全然違ったよ', - 'timestamp': 1619181890, - 'duration': 59, - 'thumbnail': r're:https?://.+', - 'uploader': 'ざきんぽ', - 'uploader_id': '10042245', - }, - }, { - 'url': 'https://www.mildom.com/clip/10111524-ebf4036e5aa8411c99fb3a1ae0902864', - 'info_dict': { - 'id': '10111524-ebf4036e5aa8411c99fb3a1ae0902864', - 'title': 'かっこいい', - 'timestamp': 1621094003, - 'duration': 59, - 'thumbnail': r're:https?://.+', - 'uploader': '(ルーキー', - 'uploader_id': '10111524', - }, - }, { - 'url': 'https://www.mildom.com/clip/10660174-2c539e6e277c4aaeb4b1fbe8d22cb902', - 'info_dict': { - 'id': '10660174-2c539e6e277c4aaeb4b1fbe8d22cb902', - 'title': 'あ', - 'timestamp': 1614769431, - 'duration': 31, - 'thumbnail': r're:https?://.+', - 'uploader': 'ドルゴルスレンギーン＝ダグワドルジ', - 'uploader_id': '10660174', - }, - }] - - def _real_extract(self, url): - user_id, video_id = self._match_valid_url(url).group('user_id', 'id') - webpage = self._download_webpage(f'https://www.mildom.com/clip/{video_id}', video_id) - - clip_detail = self._call_api( - 'https://cloudac-cf-jp.mildom.com/nonolive/videocontent/clip/detail', video_id, - note='Downloading playback metadata', query={ - 'clip_id': video_id, - }) - - return { - 'id': video_id, - 'title': self._html_search_meta( - ('og:description', 'description'), webpage, default=None) or clip_detail.get('title'), - 'timestamp': float_or_none(clip_detail.get('create_time')), - 'duration': float_or_none(clip_detail.get('length')), - 'thumbnail': clip_detail.get('cover'), - 'uploader': traverse_obj(clip_detail, ('user_info', 'loginname')), - 'uploader_id': user_id, - - 'url': clip_detail['url'], - 'ext': determine_ext(clip_detail.get('url'), 'mp4'), - } - - -class MildomUserVodIE(MildomBaseIE): - IE_NAME = 'mildom:user:vod' - IE_DESC = 'Download all VODs from specific user in Mildom' - _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/profile/(?P\d+)' - _TESTS = [{ - 'url': 'https://www.mildom.com/profile/10093333', - 'info_dict': { - 'id': '10093333', - 'title': 'Uploads from ねこばたけ', - }, - 'playlist_mincount': 732, - }, { - 'url': 'https://www.mildom.com/profile/10882672', - 'info_dict': { - 'id': '10882672', - 'title': 'Uploads from kson組長(けいそん)', - }, - 'playlist_mincount': 201, - }] - - def _fetch_page(self, user_id, page): - page += 1 - reply = self._call_api( - 'https://cloudac.mildom.com/nonolive/videocontent/profile/playbackList', - user_id, note=f'Downloading page {page}', query={ - 'user_id': user_id, - 'page': page, - 'limit': '30', - }) - if not reply: - return - for x in reply: - v_id = x.get('v_id') - if not v_id: - continue - yield self.url_result(f'https://www.mildom.com/playback/{user_id}/{v_id}') - - def _real_extract(self, url): - user_id = self._match_id(url) - self.to_screen(f'This will download all VODs belonging to user. To download ongoing live video, use "https://www.mildom.com/{user_id}" instead') - - profile = self._call_api( - 'https://cloudac.mildom.com/nonolive/gappserv/user/profileV2', user_id, - query={'user_id': user_id}, note='Downloading user profile')['user_info'] - - return self.playlist_result( - OnDemandPagedList(functools.partial(self._fetch_page, user_id), 30), - user_id, f'Uploads from {profile["loginname"]}') diff --git a/yt_dlp/extractor/pialive.py b/yt_dlp/extractor/pialive.py new file mode 100644 index 0000000000..7469135c1b --- /dev/null +++ b/yt_dlp/extractor/pialive.py @@ -0,0 +1,122 @@ +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + clean_html, + extract_attributes, + get_element_by_class, + get_element_html_by_class, + multipart_encode, + str_or_none, + unified_timestamp, + url_or_none, +) +from ..utils.traversal import traverse_obj + + +class PiaLiveIE(InfoExtractor): + _VALID_URL = r'https?://player\.pia-live\.jp/stream/(?P[\w-]+)' + _PLAYER_ROOT_URL = 'https://player.pia-live.jp/' + _PIA_LIVE_API_URL = 'https://api.pia-live.jp' + _API_KEY = 'kfds)FKFps-dms9e' + _TESTS = [{ + 'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krUDqGOwN4d61dCWQYOd6CTxl4hjya9dsfEZGsM4uGOUdax60lEI4twsXGXf7crmz8Gk__GhupTrWxA7RFRVt76', + 'info_dict': { + 'id': '88f3109a-f503-4d0f-a9f7-9f39ac745d84', + 'display_id': '2431867_001', + 'title': 'こながめでたい日２０２４の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)', + 'live_status': 'was_live', + 'comment_count': int, + }, + 'params': { + 'getcomments': True, + 'skip_download': True, + 'ignore_no_formats_error': True, + }, + 'skip': 'The video is no longer available', + }, { + 'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krJdu0GVBVbVy01IwpJ6J3qBEm3d9TCTt1d0eWpsZGj7DrOjVOmS7GAWGwyscMgiThopJvzgWC4H5b-7XQjAfRZ', + 'info_dict': { + 'id': '9ce8b8ba-f6d1-4d1f-83a0-18c3148ded93', + 'display_id': '2431867_002', + 'title': 'こながめでたい日２０２４の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)', + 'live_status': 'was_live', + 'comment_count': int, + }, + 'params': { + 'getcomments': True, + 'skip_download': True, + 'ignore_no_formats_error': True, + }, + 'skip': 'The video is no longer available', + }] + + def _extract_var(self, variable, html): + return self._search_regex( + rf'(?:var|const|let)\s+{variable}\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', + html, f'variable {variable}', group='value') + + def _real_extract(self, url): + video_key = self._match_id(url) + webpage = self._download_webpage(url, video_key) + + program_code = self._extract_var('programCode', webpage) + article_code = self._extract_var('articleCode', webpage) + title = self._html_extract_title(webpage) + + if get_element_html_by_class('play-end', webpage): + raise ExtractorError('The video is no longer available', expected=True, video_id=program_code) + + if start_info := clean_html(get_element_by_class('play-waiting__date', webpage)): + date, time = self._search_regex( + r'(?P\d{4}/\d{1,2}/\d{1,2})\([月火水木金土日]\)(?P