From 9997eee4af137ab46fc00336b1d4b7d7eb6431d4 Mon Sep 17 00:00:00 2001 From: The Hatsune Daishi Date: Wed, 4 Aug 2021 18:14:37 +0900 Subject: [PATCH] [openrec] Add extractors (#624) Authored by: nao20010128nao --- README.md | 2 +- yt_dlp/extractor/extractors.py | 4 ++ yt_dlp/extractor/openrec.py | 126 +++++++++++++++++++++++++++++++++ 3 files changed, 131 insertions(+), 1 deletion(-) create mode 100644 yt_dlp/extractor/openrec.py diff --git a/README.md b/README.md index 7fb2c08740..9ac50dbe00 100644 --- a/README.md +++ b/README.md @@ -88,7 +88,7 @@ The major new features from the latest release of [blackjack4494/yt-dlc](https:/ * **Aria2c with HLS/DASH**: You can use `aria2c` as the external downloader for DASH(mpd) and HLS(m3u8) formats -* **New extractors**: AnimeLab, Philo MSO, Spectrum MSO, SlingTV MSO, Rcs, Gedi, bitwave.tv, mildom, audius, zee5, mtv.it, wimtv, pluto.tv, niconico users, discoveryplus.in, mediathek, NFHSNetwork, nebula, ukcolumn, whowatch, MxplayerShow, parlview (au), YoutubeWebArchive, fancode, Saitosan, ShemarooMe, telemundo, VootSeries, SonyLIVSeries, HotstarSeries, VidioPremier, VidioLive, RCTIPlus, TBS Live, douyin, pornflip, ParamountPlusSeries, ScienceChannel, Utreon +* **New extractors**: AnimeLab, Philo MSO, Spectrum MSO, SlingTV MSO, Rcs, Gedi, bitwave.tv, mildom, audius, zee5, mtv.it, wimtv, pluto.tv, niconico users, discoveryplus.in, mediathek, NFHSNetwork, nebula, ukcolumn, whowatch, MxplayerShow, parlview (au), YoutubeWebArchive, fancode, Saitosan, ShemarooMe, telemundo, VootSeries, SonyLIVSeries, HotstarSeries, VidioPremier, VidioLive, RCTIPlus, TBS Live, douyin, pornflip, ParamountPlusSeries, ScienceChannel, Utreon, OpenRec * **Fixed/improved extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, akamai, ina, rumble, tennistv, amcnetworks, la7 podcasts, linuxacadamy, nitter, twitcasting, viu, crackle, curiositystream, mediasite, rmcdecouverte, sonyliv, tubi, tenplay, patreon, videa, yahoo, BravoTV, crunchyroll playlist, RTP, viki, Hotstar, vidio, vimeo, mediaset, Mxplayer diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py index e121210735..99fd7cb781 100644 --- a/yt_dlp/extractor/extractors.py +++ b/yt_dlp/extractor/extractors.py @@ -936,6 +936,10 @@ from .ooyala import ( OoyalaIE, OoyalaExternalIE, ) +from .openrec import ( + OpenRecIE, + OpenRecCaptureIE, +) from .ora import OraTVIE from .orf import ( ORFTVthekIE, diff --git a/yt_dlp/extractor/openrec.py b/yt_dlp/extractor/openrec.py new file mode 100644 index 0000000000..d7073ab445 --- /dev/null +++ b/yt_dlp/extractor/openrec.py @@ -0,0 +1,126 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + traverse_obj, + try_get, + unified_strdate +) +from ..compat import compat_str + + +class OpenRecIE(InfoExtractor): + IE_NAME = 'openrec' + _VALID_URL = r'https?://(?:www\.)?openrec\.tv/live/(?P[^/]+)' + _TESTS = [{ + 'url': 'https://www.openrec.tv/live/2p8v31qe4zy', + 'only_matching': True, + }, { + 'url': 'https://www.openrec.tv/live/wez93eqvjzl', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage('https://www.openrec.tv/live/%s' % video_id, video_id) + + window_stores = self._parse_json( + self._search_regex(r'(?m)window\.pageStore\s*=\s*(\{.+?\});$', webpage, 'window.pageStore'), video_id) + movie_store = traverse_obj( + window_stores, + ('v8', 'state', 'movie'), + ('v8', 'movie'), + expected_type=dict) + if not movie_store: + raise ExtractorError('Failed to extract live info') + + title = movie_store.get('title') + description = movie_store.get('introduction') + thumbnail = movie_store.get('thumbnailUrl') + + channel_user = movie_store.get('channel', {}).get('user') + uploader = try_get(channel_user, lambda x: x['name'], compat_str) + uploader_id = try_get(channel_user, lambda x: x['id'], compat_str) + + timestamp = traverse_obj(movie_store, ('startedAt', 'time'), expected_type=int) + + m3u8_playlists = movie_store.get('media') + formats = [] + for (name, m3u8_url) in m3u8_playlists.items(): + if not m3u8_url: + continue + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', entry_protocol='m3u8', + m3u8_id='hls-%s' % name, live=True)) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'timestamp': timestamp, + 'is_live': True, + } + + +class OpenRecCaptureIE(InfoExtractor): + IE_NAME = 'openrec:capture' + _VALID_URL = r'https?://(?:www\.)?openrec\.tv/capture/(?P[^/]+)' + _TESTS = [{ + 'url': 'https://www.openrec.tv/capture/l9nk2x4gn14', + 'only_matching': True, + }, { + 'url': 'https://www.openrec.tv/capture/mldjr82p7qk', + 'info_dict': { + 'id': 'mldjr82p7qk', + 'title': 'たいじの恥ずかしい英語力', + 'uploader': 'たいちゃんねる', + 'uploader_id': 'Yaritaiji', + 'upload_date': '20210803', + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage('https://www.openrec.tv/capture/%s' % video_id, video_id) + + window_stores = self._parse_json( + self._search_regex(r'(?m)window\.pageStore\s*=\s*(\{.+?\});$', webpage, 'window.pageStore'), video_id) + movie_store = window_stores.get('movie') + + capture_data = window_stores.get('capture') + if not capture_data: + raise ExtractorError('Cannot extract title') + title = capture_data.get('title') + thumbnail = capture_data.get('thumbnailUrl') + upload_date = unified_strdate(capture_data.get('createdAt')) + + channel_info = movie_store.get('channel') or {} + uploader = channel_info.get('name') + uploader_id = channel_info.get('id') + + m3u8_url = capture_data.get('source') + if not m3u8_url: + raise ExtractorError('Cannot extract m3u8 url') + formats = self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'upload_date': upload_date, + }