From da56fb631fb6389849f2f021bdd047aa1c55dc0a Mon Sep 17 00:00:00 2001 From: Alexander Seiler Date: Tue, 2 Oct 2018 14:49:01 +0200 Subject: [PATCH] [azmedien] Adopt to major site redesign (closes #17745) --- youtube_dl/extractor/azmedien.py | 222 +++++++---------------------- youtube_dl/extractor/extractors.py | 6 +- 2 files changed, 53 insertions(+), 175 deletions(-) diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py index 68f26e2ca..9d606ee67 100644 --- a/youtube_dl/extractor/azmedien.py +++ b/youtube_dl/extractor/azmedien.py @@ -1,19 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals +import json import re from .common import InfoExtractor from .kaltura import KalturaIE -from ..utils import ( - get_element_by_class, - get_element_by_id, - strip_or_none, - urljoin, -) class AZMedienBaseIE(InfoExtractor): + _PARTNER_ID = '1719221' + def _kaltura_video(self, partner_id, entry_id): return self.url_result( 'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(), @@ -25,189 +22,74 @@ class AZMedienIE(AZMedienBaseIE): _VALID_URL = r'''(?x) https?:// (?:www\.)? - (?: + (?P telezueri\.ch| telebaern\.tv| telem1\.ch )/ - [0-9]+-show-[^/\#]+ - (?: - /[0-9]+-episode-[^/\#]+ - (?: - /[0-9]+-segment-(?:[^/\#]+\#)?| - \# - )| - \# + [^/]+/ + (?P + [^/]+-(?P\d+) ) - (?P[^\#]+) + (?: + \#video= + (?P + [_0-9a-z]+ + ) + )? ''' _TESTS = [{ - # URL with 'segment' - 'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom', + 'url': 'https://www.telezueri.ch/sonntalk/bundesrats-vakanzen-eu-rahmenabkommen-133214569', 'info_dict': { - 'id': '1_2444peh4', + 'id': '1_anruz3wy', 'ext': 'mp4', - 'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom', - 'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8', - 'uploader_id': 'TeleZ?ri', - 'upload_date': '20161218', - 'timestamp': 1482084490, + 'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen', + 'description': 'md5:dd9f96751ec9c35e409a698a328402f3', + 'uploader_id': 'TVOnline', + 'upload_date': '20180930', + 'timestamp': 1538328802, }, 'params': { 'skip_download': True, }, }, { - # URL with 'segment' and fragment: - 'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger', - 'only_matching': True - }, { - # URL with 'episode' and fragment: - 'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz', - 'only_matching': True - }, { - # URL with 'show' and fragment: - 'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch', + 'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1', 'only_matching': True }] def _real_extract(self, url): video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + entry_id = mobj.group('kaltura_id') - webpage = self._download_webpage(url, video_id) + if not entry_id: + webpage = self._download_webpage(url, video_id) + api_path = self._search_regex( + r'["\']apiPath["\']\s*:\s*["\']([^"^\']+)["\']', + webpage, 'api path') + api_url = 'https://www.%s%s' % (mobj.group('host'), api_path) + payload = { + 'query': '''query VideoContext($articleId: ID!) { + article: node(id: $articleId) { + ... on Article { + mainAssetRelation { + asset { + ... on VideoAsset { + kalturaId + } + } + } + } + } + }''', + 'variables': {'articleId': 'Article:%s' % mobj.group('article_id')}, + } + json_data = self._download_json( + api_url, video_id, headers={ + 'Content-Type': 'application/json', + }, + data=json.dumps(payload).encode()) + entry_id = json_data['data']['article']['mainAssetRelation']['asset']['kalturaId'] - partner_id = self._search_regex( - r']+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)', - webpage, 'kaltura partner id') - entry_id = self._html_search_regex( - r']+data-id=(["\'])(?P(?:(?!\1).)+)\1[^>]+data-slug=["\']%s' - % re.escape(video_id), webpage, 'kaltura entry id', group='id') - - return self._kaltura_video(partner_id, entry_id) - - -class AZMedienPlaylistIE(AZMedienBaseIE): - IE_DESC = 'AZ Medien playlists' - _VALID_URL = r'''(?x) - https?:// - (?:www\.)? - (?: - telezueri\.ch| - telebaern\.tv| - telem1\.ch - )/ - (?P[0-9]+- - (?: - show| - topic| - themen - )-[^/\#]+ - (?: - /[0-9]+-episode-[^/\#]+ - )? - )$ - ''' - - _TESTS = [{ - # URL with 'episode' - 'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016', - 'info_dict': { - 'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016', - 'title': 'News - Donnerstag, 15. Dezember 2016', - }, - 'playlist_count': 9, - }, { - # URL with 'themen' - 'url': 'http://www.telem1.ch/258-themen-tele-m1-classics', - 'info_dict': { - 'id': '258-themen-tele-m1-classics', - 'title': 'Tele M1 Classics', - }, - 'playlist_mincount': 15, - }, { - # URL with 'topic', contains nested playlists - 'url': 'http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen', - 'only_matching': True, - }, { - # URL with 'show' only - 'url': 'http://www.telezueri.ch/86-show-talktaeglich', - 'only_matching': True - }] - - def _real_extract(self, url): - show_id = self._match_id(url) - webpage = self._download_webpage(url, show_id) - - entries = [] - - partner_id = self._search_regex( - r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)', - webpage, 'kaltura partner id', default=None) - - if partner_id: - entries = [ - self._kaltura_video(partner_id, m.group('id')) - for m in re.finditer( - r'data-id=(["\'])(?P(?:(?!\1).)+)\1', webpage)] - - if not entries: - entries = [ - self.url_result(m.group('url'), ie=AZMedienIE.ie_key()) - for m in re.finditer( - r']+data-real=(["\'])(?Phttp.+?)\1', webpage)] - - if not entries: - entries = [ - # May contain nested playlists (e.g. [1]) thus no explicit - # ie_key - # 1. http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen) - self.url_result(urljoin(url, m.group('url'))) - for m in re.finditer( - r']+name=[^>]+href=(["\'])(?P/.+?)\1', webpage)] - - title = self._search_regex( - r'episodeShareTitle\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', - webpage, 'title', - default=strip_or_none(get_element_by_id( - 'video-title', webpage)), group='title') - - return self.playlist_result(entries, show_id, title) - - -class AZMedienShowPlaylistIE(AZMedienBaseIE): - IE_DESC = 'AZ Medien show playlists' - _VALID_URL = r'''(?x) - https?:// - (?:www\.)? - (?: - telezueri\.ch| - telebaern\.tv| - telem1\.ch - )/ - (?: - all-episodes| - alle-episoden - )/ - (?P<id>[^/?#&]+) - ''' - - _TEST = { - 'url': 'http://www.telezueri.ch/all-episodes/astrotalk', - 'info_dict': { - 'id': 'astrotalk', - 'title': 'TeleZüri: AstroTalk - alle episoden', - 'description': 'md5:4c0f7e7d741d906004266e295ceb4a26', - }, - 'playlist_mincount': 13, - } - - def _real_extract(self, url): - playlist_id = self._match_id(url) - webpage = self._download_webpage(url, playlist_id) - episodes = get_element_by_class('search-mobile-box', webpage) - entries = [self.url_result( - urljoin(url, m.group('url'))) for m in re.finditer( - r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', episodes)] - title = self._og_search_title(webpage, fatal=False) - description = self._og_search_description(webpage) - return self.playlist_result(entries, playlist_id, title, description) + return self._kaltura_video(self._PARTNER_ID, entry_id) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index b41cd65d7..9b68c9efe 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -88,11 +88,7 @@ from .awaan import ( AWAANLiveIE, AWAANSeasonIE, ) -from .azmedien import ( - AZMedienIE, - AZMedienPlaylistIE, - AZMedienShowPlaylistIE, -) +from .azmedien import AZMedienIE from .baidu import BaiduVideoIE from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE