[youtube] Add ability to authenticate with cookies

[youtube-dl] / youtube_dl / extractor / azmedien.py

diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py
index a89f71c20c08ac95cd5e78814afe5da783ed2ca3..68f26e2cad635bd8eb23a14ced3e1b90b2b320fc 100644 (file)
--- 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
@@ -6,7 +7,9 @@ from .common import InfoExtractor
 from .kaltura import KalturaIE
 from ..utils import (
     get_element_by_class,
+    get_element_by_id,
     strip_or_none,
+    urljoin,
 )
 
 
@@ -44,7 +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',
@@ -83,8 +86,8 @@ 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 +96,12 @@ class AZMedienShowIE(AZMedienBaseIE):
                             telebaern\.tv|
                             telem1\.ch
                         )/
-                        (?P<id>[0-9]+-show-[^/\#]+
+                        (?P<id>[0-9]+-
+                            (?:
+                                show|
+                                topic|
+                                themen
+                            )-[^/\#]+
                             (?:
                                 /[0-9]+-episode-[^/\#]+
                             )?
@@ -108,6 +116,18 @@ 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 +156,58 @@ 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\.)?
+                        (?:
+                            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)