From f13da8af289d7d9365e34ef705a53ac62aa3b570 Mon Sep 17 00:00:00 2001 From: Alex Seiler Date: Sat, 28 Jan 2017 17:52:07 +0100 Subject: [PATCH] [azmedien:playlist] Add support for topic and themen playlists --- youtube_dl/extractor/azmedien.py | 39 +++++++++++++++++++++++++----- youtube_dl/extractor/extractors.py | 2 +- 2 files changed, 34 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py index a89f71c20c..cbc3ed5640 100644 --- a/youtube_dl/extractor/azmedien.py +++ b/youtube_dl/extractor/azmedien.py @@ -5,8 +5,9 @@ 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, ) @@ -83,8 +84,8 @@ class AZMedienIE(AZMedienBaseIE): return self._kaltura_video(partner_id, entry_id) -class AZMedienShowIE(AZMedienBaseIE): - IE_DESC = 'AZ Medien shows' +class AZMedienPlaylistIE(AZMedienBaseIE): + IE_DESC = 'AZ Medien playlists' _VALID_URL = r'''(?x) https?:// (?:www\.)? @@ -93,7 +94,12 @@ class AZMedienShowIE(AZMedienBaseIE): telebaern\.tv| telem1\.ch )/ - (?P[0-9]+-show-[^/\#]+ + (?P[0-9]+- + (?: + show| + topic| + themen + )-[^/\#]+ (?: /[0-9]+-episode-[^/\#]+ )? @@ -108,6 +114,18 @@ class AZMedienShowIE(AZMedienBaseIE): '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', @@ -136,10 +154,19 @@ class AZMedienShowIE(AZMedienBaseIE): 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_class( - 'title-block-cell', webpage)), group='title') + default=strip_or_none(get_element_by_id( + 'video-title', webpage)), group='title') return self.playlist_result(entries, show_id, title) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 086a2296dc..2590b5e1b2 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -82,7 +82,7 @@ from .awaan import ( ) from .azmedien import ( AZMedienIE, - AZMedienShowIE, + AZMedienPlaylistIE, ) from .azubu import AzubuIE, AzubuLiveIE from .baidu import BaiduVideoIE