Merge pull request #9288 from reyyed/issue#9063fix

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

diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py
index 2f728d3dc08c6d1149fa30a43f48fce9999042ac..54c2d0aa6c0d234f9f747550ab841c409bfbc079 100644 (file)
--- a/youtube_dl/extractor/toutv.py
+++ b/youtube_dl/extractor/toutv.py
@@ -1,74 +1,41 @@
 # coding: utf-8
-import re
-import xml.etree.ElementTree
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    unified_strdate,
-)
+from ..utils import int_or_none
 
 
 class TouTvIE(InfoExtractor):
-    IE_NAME = u'tou.tv'
-    _VALID_URL = r'https?://www\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/(?P<episode>S[0-9]+E[0-9]+)))'
+    IE_NAME = 'tou.tv'
+    _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+/S[0-9]+E[0-9]+)'
 
     _TEST = {
-        u'url': u'http://www.tou.tv/30-vies/S04E41',
-        u'file': u'30-vies_S04E41.mp4',
-        u'info_dict': {
-            u'title': u'30 vies Saison 4 / Épisode 41',
-            u'description': u'md5:da363002db82ccbe4dafeb9cab039b09',
-            u'age_limit': 8,
-            u'uploader': u'Groupe des Nouveaux Médias',
-            u'duration': 1296,
-            u'upload_date': u'20131118',
-            u'thumbnail': u'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg',
+        'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17',
+        'info_dict': {
+            'id': '122017',
+            'ext': 'mp4',
+            'title': 'Saison 2015 Épisode 17',
+            'description': 'La photo de famille 2',
+            'upload_date': '20100717',
         },
-        u'params': {
-            u'skip_download': True,  # Requires rtmpdump
+        'params': {
+            # m3u8 download
+            'skip_download': True,
         },
-        u'skip': 'Only available in Canada'
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-
-        mediaId = self._search_regex(
-            r'"idMedia":\s*"([^"]+)"', webpage, u'media ID')
-
-        streams_url = u'http://release.theplatform.com/content.select?pid=' + mediaId
-        streams_webpage = self._download_webpage(
-            streams_url, video_id, note=u'Downloading stream list')
-
-        streams_doc = xml.etree.ElementTree.fromstring(
-            streams_webpage.encode('utf-8'))
-        video_url = next(n.text
-                         for n in streams_doc.findall('.//choice/url')
-                         if u'//ad.doubleclick' not in n.text)
-        if video_url.endswith('/Unavailable.flv'):
-            raise ExtractorError(
-                u'Access to this video is blocked from outside of Canada',
-                expected=True)
-
-        duration_str = self._html_search_meta(
-            'video:duration', webpage, u'duration')
-        duration = int(duration_str) if duration_str else None
-        upload_date_str = self._html_search_meta(
-            'video:release_date', webpage, u'upload date')
-        upload_date = unified_strdate(upload_date_str) if upload_date_str else None
+        path = self._match_id(url)
+        metadata = self._download_json('http://ici.tou.tv/presentation/%s' % path, path)
+        video_id = metadata['IdMedia']
+        details = metadata['Details']
+        title = details['OriginalTitle']
 
         return {
+            '_type': 'url_transparent',
+            'url': 'radiocanada:%s:%s' % (metadata.get('AppCode', 'toutv'), video_id),
             'id': video_id,
-            'title': self._og_search_title(webpage),
-            'url': video_url,
-            'description': self._og_search_description(webpage),
-            'uploader': self._dc_search_uploader(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'age_limit': self._media_rating_search(webpage),
-            'duration': duration,
-            'upload_date': upload_date,
-            'ext': 'mp4',
+            'title': title,
+            'thumbnail': details.get('ImageUrl'),
+            'duration': int_or_none(details.get('LengthInSeconds')),
         }