[srgssr] handle all play urls only in SRGSSRIE and keep RTSIE for articles

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

diff --git a/youtube_dl/extractor/srgssr.py b/youtube_dl/extractor/srgssr.py
index f759e5600e5e33f88e48d3482ad1380d29218aa3..563851b3f74353ef6a672025395ef6e9fb920e11 100644 (file)
--- a/youtube_dl/extractor/srgssr.py
+++ b/youtube_dl/extractor/srgssr.py
@@ -17,25 +17,29 @@ class SRGSSRIE(InfoExtractor):
     _ERRORS = {
         'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.',
         'AGERATING18': 'To protect children under the age of 18, this video is only available between 11 p.m. and 5 a.m.',
-#        'ENDDATE': 'For legal reasons, this video was only available for a specified period of time.',
+        # 'ENDDATE': 'For legal reasons, this video was only available for a specified period of time.',
         'GEOBLOCK': 'For legal reasons, this video is only available in Switzerland.',
         'LEGAL': 'The video cannot be transmitted for legal reasons.',
         'STARTDATE': 'This video is not yet available. Please try again later.',
     }
 
-    def _real_extract(self, url):
-        bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
-
+    def get_media_data(self, bu, media_type, media_id):
         media_data = self._download_json(
             'http://il.srgssr.ch/integrationlayer/1.0/ue/%s/%s/play/%s.json' % (bu, media_type, media_id),
             media_id)[media_type.capitalize()]
 
         if media_data.get('block') and media_data['block'] in self._ERRORS:
-            raise ExtractorError(
-                    '%s said: %s' % (
-                        self.IE_NAME,
-                        self._ERRORS[media_data['block']]),
-                    expected=True)
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, self._ERRORS[media_data['block']]), expected=True)
+
+        return media_data
+
+    def _real_extract(self, url):
+        bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
+
+        if bu == 'rts':
+            return self.url_result('rts:%s' % media_id, 'RTS')
+
+        media_data = self.get_media_data(bu, media_type, media_id)
 
         metadata = media_data['AssetMetadatas']['AssetMetadata'][0]
         title = metadata['title']
@@ -61,9 +65,13 @@ class SRGSSRIE(InfoExtractor):
                     assets[quality['@quality']] = quality['text']
                 asset_url = assets.get('HD') or assets.get('HQ') or assets.get('SD') or assets.get('MQ') or assets.get('LQ')
                 if '.f4m' in asset_url:
-                    formats.extend(self._extract_f4m_formats(asset_url + '?hdcore=3.4.0', media_id, f4m_id='hds'))
+                    f4m_formats = formats.extend(self._extract_f4m_formats(asset_url + '?hdcore=3.4.0', media_id, f4m_id='hds', fatal=False))
+                    if f4m_formats:
+                        formats.extend(f4m_formats)
                 elif '.m3u8' in asset_url:
-                    formats.extend(self._extract_m3u8_formats(asset_url, media_id, m3u8_id='hls'))
+                    m3u8_formats = formats.extend(self._extract_m3u8_formats(asset_url, media_id, m3u8_id='hls', fatal=False))
+                    if m3u8_formats:
+                        formats.extend(m3u8_formats)
             else:
                 for asset in source['url']:
                     asset_url = asset['text']
@@ -122,7 +130,7 @@ class SRGSSRPlayIE(InfoExtractor):
             'description': 'md5:88604432b60d5a38787f152dec89cd56',
             'timestamp': 1373493600,
         },
-    },{
+    }, {
         'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc',
         'info_dict': {
             'id': '63cb0778-27f8-49af-9284-8c7a8c6d15fc',
@@ -135,8 +143,25 @@ class SRGSSRPlayIE(InfoExtractor):
             # rtmp download
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260',
+        'md5': '67a2a9ae4e8e62a68d0e9820cc9782df',
+        'info_dict': {
+            'id': '6348260',
+            'display_id': '6348260',
+            'ext': 'flv',
+            'duration': 1796,
+            'title': 'Le 19h30',
+            'description': '',
+            'uploader': '19h30',
+            'upload_date': '20141201',
+            'timestamp': 1417458600,
+            'thumbnail': 're:^https?://.*\.image',
+            'view_count': int,
+        },
     }]
 
     def _real_extract(self, url):
         bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
+        # other info can be extracted from url + '&layout=json'
         return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')