X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/b8d8e13c1f9e4d3cdd7d41c5c9d711a36dd5f9c3..fe3f5064d6bfc2fe705eef08b4f75309b95b55b2:/youtube_dl/extractor/azmedien.py diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py index cbc3ed5..68f26e2 100644 --- a/youtube_dl/extractor/azmedien.py +++ b/youtube_dl/extractor/azmedien.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import re @@ -5,6 +6,7 @@ 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, @@ -45,7 +47,7 @@ class AZMedienIE(AZMedienBaseIE): 'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom', 'info_dict': { 'id': '1_2444peh4', - 'ext': 'mov', + 'ext': 'mp4', 'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom', 'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8', 'uploader_id': 'TeleZ?ri', @@ -170,3 +172,42 @@ class AZMedienPlaylistIE(AZMedienBaseIE): '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[^/?#&]+) + ''' + + _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']+href=(["\'])(?P(?:(?!\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)