[pbs] Add support for article pages (Fixes #870)

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

diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py
index 6075296ffe666cf055a434195e2445a38e5709aa..4922dd764eb119a4993bad607a3a01afccf99f51 100644 (file)
--- a/youtube_dl/extractor/rutube.py
+++ b/youtube_dl/extractor/rutube.py
@@ -15,16 +15,19 @@ from ..utils import (
 
 class RutubeIE(InfoExtractor):
     IE_NAME = 'rutube'
-    IE_DESC = 'Rutube videos'    
-    _VALID_URL = r'https?://rutube\.ru/video/(?P<long_id>\w+)'
+    IE_DESC = 'Rutube videos'
+    _VALID_URL = r'https?://rutube\.ru/video/(?P<id>[\da-z]{32})'
 
     _TEST = {
         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
         'file': '3eac3b4561676c17df9132a9a1e62e3e.mp4',
         'info_dict': {
             'title': 'Раненный кенгуру забежал в аптеку',
+            'description': 'http://www.ntdtv.ru ',
+            'duration': 80,
             'uploader': 'NTDRussian',
             'uploader_id': '29790',
+            'upload_date': '20131016',
         },
         'params': {
             # It requires ffmpeg (m3u8 download)
@@ -34,14 +37,14 @@ class RutubeIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        long_id = mobj.group('long_id')
+        video_id = mobj.group('id')
         
-        api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % long_id,
-                                              long_id, 'Downloading video JSON')
+        api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % video_id,
+                                              video_id, 'Downloading video JSON')
         video = json.loads(api_response)
         
-        api_response = self._download_webpage('http://rutube.ru/api/play/trackinfo/%s/?format=json' % long_id,
-                                              long_id, 'Downloading trackinfo JSON')
+        api_response = self._download_webpage('http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id,
+                                              video_id, 'Downloading trackinfo JSON')
         trackinfo = json.loads(api_response)
         
         # Some videos don't have the author field
@@ -68,7 +71,7 @@ class RutubeIE(InfoExtractor):
 
 class RutubeChannelIE(InfoExtractor):
     IE_NAME = 'rutube:channel'
-    IE_DESC = 'Rutube channels'    
+    IE_DESC = 'Rutube channels'
     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
@@ -76,15 +79,16 @@ class RutubeChannelIE(InfoExtractor):
     def _extract_videos(self, channel_id, channel_title=None):
         entries = []
         for pagenum in itertools.count(1):
-            api_response = self._download_webpage(self._PAGE_TEMPLATE % (channel_id, pagenum),
-                                                   channel_id, 'Downloading page %s' % pagenum)
+            api_response = self._download_webpage(
+                self._PAGE_TEMPLATE % (channel_id, pagenum),
+                channel_id, 'Downloading page %s' % pagenum)
             page = json.loads(api_response)
             results = page['results']
-            if len(results) == 0:
-                break;
+            if not results:
+                break
             entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
-            if page['has_next'] is False:
-                break;
+            if not page['has_next']:
+                break
         return self.playlist_result(entries, channel_id, channel_title)
 
     def _real_extract(self, url):
@@ -95,7 +99,7 @@ class RutubeChannelIE(InfoExtractor):
 
 class RutubeMovieIE(RutubeChannelIE):
     IE_NAME = 'rutube:movie'
-    IE_DESC = 'Rutube movies'    
+    IE_DESC = 'Rutube movies'
     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 
     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
@@ -104,8 +108,17 @@ class RutubeMovieIE(RutubeChannelIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         movie_id = mobj.group('id')
-        api_response = self._download_webpage(self._MOVIE_TEMPLATE % movie_id, movie_id,
-                                            'Downloading movie JSON')
+        api_response = self._download_webpage(
+            self._MOVIE_TEMPLATE % movie_id, movie_id,
+            'Downloading movie JSON')
         movie = json.loads(api_response)
         movie_name = movie['name']
-        return self._extract_videos(movie_id, movie_name)
\ No newline at end of file
+        return self._extract_videos(movie_id, movie_name)
+
+
+class RutubePersonIE(RutubeChannelIE):
+    IE_NAME = 'rutube:person'
+    IE_DESC = 'Rutube person videos'
+    _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
+
+    _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'