Merge remote-tracking branch 'dstftw/rutube-channel'

test/test_playlists.py

@@ -33,6 +33,7 @@
     ImdbListIE,
     KhanAcademyIE,
     EveryonesMixtapeIE,
+    RutubeChannelIE,
 )
 
 
@@ -220,6 +221,14 @@ def test_EveryonesMixtape(self):
         self.assertEqual(result['title'], 'Driving')
         self.assertEqual(len(result['entries']), 24)
         
+    def test_rutube_channel(self):
+        dl = FakeYDL()
+        ie = RutubeChannelIE(dl)
+        result = ie.extract('http://rutube.ru/tags/video/1409')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '1409')
+        self.assertTrue(len(result['entries']) >= 34)
+
 
 if __name__ == '__main__':
     unittest.main()

youtube_dl/extractor/__init__.py

@@ -161,7 +161,12 @@
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtlnow import RTLnowIE
-from .rutube import RutubeIE
+from .rutube import (
+    RutubeIE,
+    RutubeChannelIE,
+    RutubeMovieIE,
+    RutubePersonIE,
+)
 from .servingsys import ServingSysIE
 from .sina import SinaIE
 from .slashdot import SlashdotIE

youtube_dl/extractor/rutube.py

@@ -1,58 +1,119 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 import json
+import itertools
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urlparse,
     compat_str,
+    unified_strdate,
     ExtractorError,
 )
 
 
 class RutubeIE(InfoExtractor):
-    _VALID_URL = r'https?://rutube\.ru/video/(?P<long_id>\w+)'
+    IE_NAME = 'rutube'
+    IE_DESC = 'Rutube videos'    
+    _VALID_URL = r'https?://rutube\.ru/video/(?P<id>[\da-z]{32})'
 
     _TEST = {
-        u'url': u'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
+        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
-        u'file': u'3eac3b4561676c17df9132a9a1e62e3e.mp4',
+        'file': '3eac3b4561676c17df9132a9a1e62e3e.mp4',
-        u'info_dict': {
+        'info_dict': {
-            u'title': u'Раненный кенгуру забежал в аптеку',
+            'title': 'Раненный кенгуру забежал в аптеку',
-            u'uploader': u'NTDRussian',
+            'uploader': 'NTDRussian',
-            u'uploader_id': u'29790',
+            'uploader_id': '29790',
         },
-        u'params': {
+        'params': {
             # It requires ffmpeg (m3u8 download)
-            u'skip_download': True,
+            'skip_download': True,
         },
     }
 
-    def _get_api_response(self, short_id, subpath):
-        api_url = 'http://rutube.ru/api/play/%s/%s/?format=json' % (subpath, short_id)
-        response_json = self._download_webpage(api_url, short_id,
-            u'Downloading %s json' % subpath)
-        return json.loads(response_json)
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        long_id = mobj.group('long_id')
+        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, long_id)
+        
-        og_video = self._og_search_video_url(webpage)
+        api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % video_id,
-        short_id = compat_urlparse.urlparse(og_video).path[1:]
+                                              video_id, 'Downloading video JSON')
-        options = self._get_api_response(short_id, 'options')
+        video = json.loads(api_response)
-        trackinfo = self._get_api_response(short_id, 'trackinfo')
+        
+        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
         author = trackinfo.get('author') or {}
         m3u8_url = trackinfo['video_balancer'].get('m3u8')
         if m3u8_url is None:
-            raise ExtractorError(u'Couldn\'t find m3u8 manifest url')
+            raise ExtractorError('Couldn\'t find m3u8 manifest url')
 
         return {
-            'id': trackinfo['id'],
+            'id': video['id'],
-            'title': trackinfo['title'],
+            'title': video['title'],
+            'description': video['description'],
+            'duration': video['duration'],
+            'view_count': video['hits'],
             'url': m3u8_url,
             'ext': 'mp4',
-            'thumbnail': options['thumbnail_url'],
+            'thumbnail': video['thumbnail_url'],
             'uploader': author.get('name'),
             'uploader_id': compat_str(author['id']) if author else None,
+            'upload_date': unified_strdate(video['created_ts']),
+            'age_limit': 18 if video['is_adult'] else 0,
         }
+
+
+class RutubeChannelIE(InfoExtractor):
+    IE_NAME = 'rutube:channel'
+    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'
+
+    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)
+            page = json.loads(api_response)
+            results = page['results']
+            if len(results) == 0:
+                break;
+            entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
+            if page['has_next'] is False:
+                break;
+        return self.playlist_result(entries, channel_id, channel_title)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        channel_id = mobj.group('id')
+        return self._extract_videos(channel_id)
+
+
+class RutubeMovieIE(RutubeChannelIE):
+    IE_NAME = 'rutube:movie'
+    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'
+    _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
+
+    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')
+        movie = json.loads(api_response)
+        movie_name = movie['name']
+        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'