X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fazmedien.py;h=817fc6d570caa2e33b3480b708458c0c3a191b31;hb=948519b35dec420c3b3ca5369bcba1dead31fcc6;hp=059dc6e4bbc9303a23585cff503004257b5e07f1;hpb=94629e537f2f6ed80b19e3863456f9ba8073af36;p=youtube-dl.git

diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py
index 059dc6e4b..817fc6d57 100644
--- a/youtube_dl/extractor/azmedien.py
+++ b/youtube_dl/extractor/azmedien.py
@@ -6,7 +6,9 @@ from .common import InfoExtractor
 from .kaltura import KalturaIE
 from ..utils import (
     get_element_by_class,
+    get_element_by_id,
     strip_or_none,
+    urljoin,
 )
 
 
@@ -83,9 +85,27 @@ class AZMedienIE(AZMedienBaseIE):
         return self._kaltura_video(partner_id, entry_id)
 
 
-class AZMedienShowIE(AZMedienBaseIE):
-    IE_DESC = 'AZ Medien shows'
-    _VALID_URL = r'https?://(?:www\.)?(?:telezueri\.ch|telebaern\.tv|telem1\.ch)/(?P<id>[0-9]+-show-[^/#]+(?:/[0-9]+-episode-[^/#]+)?)$'
+class AZMedienPlaylistIE(AZMedienBaseIE):
+    IE_DESC = 'AZ Medien playlists'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?:
+                            telezueri\.ch|
+                            telebaern\.tv|
+                            telem1\.ch
+                        )/
+                        (?P<id>[0-9]+-
+                            (?:
+                                show|
+                                topic|
+                                themen
+                            )-[^/\#]+
+                            (?:
+                                /[0-9]+-episode-[^/\#]+
+                            )?
+                        )$
+                    '''
 
     _TESTS = [{
         # URL with 'episode'
@@ -95,6 +115,18 @@ 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',
@@ -123,10 +155,67 @@ class AZMedienShowIE(AZMedienBaseIE):
                 for m in re.finditer(
                     r'<a[^>]+data-real=(["\'])(?P<url>http.+?)\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'<a[^>]+name=[^>]+href=(["\'])(?P<url>/.+?)\1', webpage)]
+
         title = self._search_regex(
             r'episodeShareTitle\s*=\s*(["\'])(?P<title>(?:(?!\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)
+
+
+class AZMedienShowPlaylistIE(AZMedienBaseIE):
+    IE_DESC = 'AZ Medien Show playlists'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?P<id>
+                        (?:
+                            telezueri\.ch|
+                            telebaern\.tv|
+                            telem1\.ch
+                        )/
+                        (?:
+                            all-episodes|
+                            alle-episoden
+                        )
+                        /[^/]+
+                        )
+                    '''
+
+    _TEST = {
+        'url': 'http://www.telezueri.ch/all-episodes/astrotalk',
+        'info_dict': {
+            'id': 'telezueri.ch/all-episodes/astrotalk',
+            'title': 'TeleZüri: AstroTalk - alle episoden',
+            'description': 'md5:4c0f7e7d741d906004266e295ceb4a26',
+        },
+        'playlist_mincount': 13,
+        'params': {
+            'skip_download': True,
+        }
+    }
+
+    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', episodes)]
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        return self.playlist_result(
+            entries,
+            playlist_id=playlist_id,
+            playlist_title=title,
+            playlist_description=description)