BBCIE: Fix missing .mp4 formats on news sites

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

diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py
index 115cc64cc6e08ec414de3c0dc671a19c33f1d7bc..1631faf29f61c9cc15bca99394966c1917ca1a08 100644 (file)
--- a/youtube_dl/extractor/rai.py
+++ b/youtube_dl/extractor/rai.py
@@ -62,6 +62,17 @@ class RaiIE(InfoExtractor):
                 'description': 'Edizione delle ore 20:30 ',
             }
         },
+        {
+            'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
+            'md5': '02b64456f7cc09f96ff14e7dd489017e',
+            'info_dict': {
+                'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
+                'ext': 'flv',
+                'title': 'Il Candidato - Primo episodio: "Le Primarie"',
+                'description': 'Primo appuntamento con "Il candidato" con Filippo Timi, alias Piero Zucca presidente!',
+                'uploader': 'RaiTre',
+            }
+        }
     ]
 
     def _extract_relinker_url(self, webpage):
@@ -82,9 +93,9 @@ class RaiIE(InfoExtractor):
             iframe_path = self._search_regex(
                 r'<iframe[^>]+src="/?(dl/[^"]+\?iframe\b[^"]*)"',
                 webpage, 'iframe')
-            iframe_page = self._download_webpage(
+            webpage = self._download_webpage(
                 '%s/%s' % (host, iframe_path), video_id)
-            relinker_url = self._extract_relinker_url(iframe_page)
+            relinker_url = self._extract_relinker_url(webpage)
 
         relinker = self._download_json(
             '%s&output=47' % relinker_url, video_id)
@@ -112,15 +123,15 @@ class RaiIE(InfoExtractor):
             uploader = media.get('author')
             upload_date = unified_strdate(media.get('date'))
         else:
-            title = self._search_regex(
-                r'var\s+videoTitolo\s*=\s*"([^"]+)";',
-                webpage, 'title', default=None) or self._og_search_title(webpage)
+            title = (self._search_regex(
+                r'var\s+videoTitolo\s*=\s*"(.+?)";',
+                webpage, 'title', default=None) or self._og_search_title(webpage)).replace('\\"', '"')
             description = self._og_search_description(webpage)
             thumbnail = self._og_search_thumbnail(webpage)
             duration = None
             uploader = self._html_search_meta('Editore', webpage, 'uploader')
             upload_date = unified_strdate(self._html_search_meta(
-                'item-date', webpage, 'upload date'))
+                'item-date', webpage, 'upload date', default=None))
 
         subtitles = self.extract_subtitles(video_id, webpage)