Update README.md

[youtubedl] / youtube_dl / extractor / azmedien.py

diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py
index cbc3ed5640ca00818144abf312ee65c896207a2a..b1e20def5343e6b1a077ff3ba0b36f6a96c4f2c4 100644 (file)
--- a/youtube_dl/extractor/azmedien.py
+++ b/youtube_dl/extractor/azmedien.py
@@ -1,172 +1,66 @@
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

+import json

 import re
 
 from .common import InfoExtractor
 from .kaltura import KalturaIE
 import re
 
 from .common import InfoExtractor
 from .kaltura import KalturaIE

-from ..utils import (
-    get_element_by_id,
-    strip_or_none,
-    urljoin,
-)

 
 
 
 

-class AZMedienBaseIE(InfoExtractor):
-    def _kaltura_video(self, partner_id, entry_id):
-        return self.url_result(
-            'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(),
-            video_id=entry_id)
-
-
-class AZMedienIE(AZMedienBaseIE):
+class AZMedienIE(InfoExtractor):

     IE_DESC = 'AZ Medien videos'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:www\.)?
     IE_DESC = 'AZ Medien videos'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:www\.)?

-                        (?:
+                        (?P<host>

                             telezueri\.ch|
                             telebaern\.tv|
                             telem1\.ch
                         )/
                             telezueri\.ch|
                             telebaern\.tv|
                             telem1\.ch
                         )/

-                        [0-9]+-show-[^/\#]+
-                        (?:
-                            /[0-9]+-episode-[^/\#]+
-                            (?:
-                                /[0-9]+-segment-(?:[^/\#]+\#)?|
-                                \#
-                            )|
-                            \#
+                        [^/]+/
+                        (?P<id>
+                            [^/]+-(?P<article_id>\d+)

                         )
                         )

-                        (?P<id>[^\#]+)
+                        (?:
+                            \#video=
+                            (?P<kaltura_id>
+                                [_0-9a-z]+
+                            )
+                        )?

                     '''
 
     _TESTS = [{
                     '''
 
     _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': {
         'info_dict': {

-            'id': '1_2444peh4',
-            'ext': 'mov',
-            'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
-            'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
-            'uploader_id': 'TeleZ?ri',
-            'upload_date': '20161218',
-            'timestamp': 1482084490,
+            'id': '1_anruz3wy',
+            'ext': 'mp4',
+            'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen',
+            'uploader_id': 'TVOnline',
+            'upload_date': '20180930',
+            'timestamp': 1538328802,

         },
         'params': {
             'skip_download': True,
         },
     }, {
         },
         '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
     }]
         'only_matching': True
     }]

+    _API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/cb9f2f81ed22e9b47f4ca64ea3cc5a5d13e88d1d'
+    _PARTNER_ID = '1719221'

 
     def _real_extract(self, url):
 
     def _real_extract(self, url):

-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
+        host, display_id, article_id, entry_id = re.match(self._VALID_URL, url).groups()

 
 

-        partner_id = self._search_regex(
-            r'<script[^>]+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)',
-            webpage, 'kaltura partner id')
-        entry_id = self._html_search_regex(
-            r'<a[^>]+data-id=(["\'])(?P<id>(?:(?!\1).)+)\1[^>]+data-slug=["\']%s'
-            % re.escape(video_id), webpage, 'kaltura entry id', group='id')
+        if not entry_id:
+            entry_id = self._download_json(
+                self._API_TEMPL % (host, host.split('.')[0]), display_id, query={
+                    'variables': json.dumps({
+                        'contextId': 'NewsArticle:' + article_id,
+                    }),
+                })['data']['context']['mainAsset']['video']['kaltura']['kalturaId']

 
 

-        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<id>[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<id>(?:(?!\1).)+)\1', webpage)]
-
-        if not entries:
-            entries = [
-                self.url_result(m.group('url'), ie=AZMedienIE.ie_key())
-                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_id(
-                'video-title', webpage)), group='title')
-
-        return self.playlist_result(entries, show_id, title)
+        return self.url_result(
+            'kaltura:%s:%s' % (self._PARTNER_ID, entry_id),
+            ie=KalturaIE.ie_key(), video_id=entry_id)