Imported Upstream version 2014.11.21

[youtubedl] / youtube_dl / extractor / rutube.py

diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py
index 4922dd764eb119a4993bad607a3a01afccf99f51..0c8790da28c4b06cfbc941bdff7ad4e64b47ac74 100644 (file)
--- a/youtube_dl/extractor/rutube.py
+++ b/youtube_dl/extractor/rutube.py
@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re

-import json

 import itertools
 
 from .common import InfoExtractor
 import itertools
 
 from .common import InfoExtractor


@@ -20,8 +19,9 @@ class RutubeIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
 
     _TEST = {
         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',

-        'file': '3eac3b4561676c17df9132a9a1e62e3e.mp4',

         'info_dict': {
         'info_dict': {

+            'id': '3eac3b4561676c17df9132a9a1e62e3e',
+            'ext': 'mp4',

             'title': 'Раненный кенгуру забежал в аптеку',
             'description': 'http://www.ntdtv.ru ',
             'duration': 80,
             'title': 'Раненный кенгуру забежал в аптеку',
             'description': 'http://www.ntdtv.ru ',
             'duration': 80,


@@ -38,18 +38,19 @@ class RutubeIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')

-        
-        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' % video_id,
-                                              video_id, 'Downloading trackinfo JSON')
-        trackinfo = json.loads(api_response)
-        
+
+        video = self._download_json(
+            'http://rutube.ru/api/video/%s/?format=json' % video_id,
+            video_id, 'Downloading video JSON')
+

         # Some videos don't have the author field
         # Some videos don't have the author field

-        author = trackinfo.get('author') or {}
-        m3u8_url = trackinfo['video_balancer'].get('m3u8')
+        author = video.get('author') or {}
+
+        options = self._download_json(
+            'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
+            video_id, 'Downloading options JSON')
+
+        m3u8_url = options['video_balancer'].get('m3u8')

         if m3u8_url is None:
             raise ExtractorError('Couldn\'t find m3u8 manifest url')
 
         if m3u8_url is None:
             raise ExtractorError('Couldn\'t find m3u8 manifest url')
 


@@ -73,16 +74,22 @@ class RutubeChannelIE(InfoExtractor):
     IE_NAME = 'rutube:channel'
     IE_DESC = 'Rutube channels'
     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
     IE_NAME = 'rutube:channel'
     IE_DESC = 'Rutube channels'
     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'

+    _TESTS = [{
+        'url': 'http://rutube.ru/tags/video/1800/',
+        'info_dict': {
+            'id': '1800',
+        },
+        'playlist_mincount': 68,
+    }]

 
     _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):
 
     _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(
+            page = self._download_json(

                 self._PAGE_TEMPLATE % (channel_id, pagenum),
                 channel_id, 'Downloading page %s' % pagenum)
                 self._PAGE_TEMPLATE % (channel_id, pagenum),
                 channel_id, 'Downloading page %s' % pagenum)

-            page = json.loads(api_response)

             results = page['results']
             if not results:
                 break
             results = page['results']
             if not results:
                 break


@@ -101,6 +108,7 @@ class RutubeMovieIE(RutubeChannelIE):
     IE_NAME = 'rutube:movie'
     IE_DESC = 'Rutube movies'
     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
     IE_NAME = 'rutube:movie'
     IE_DESC = 'Rutube movies'
     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'

+    _TESTS = []

 
     _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'
 
     _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'


@@ -108,10 +116,9 @@ class RutubeMovieIE(RutubeChannelIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         movie_id = mobj.group('id')
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         movie_id = mobj.group('id')

-        api_response = self._download_webpage(
+        movie = self._download_json(

             self._MOVIE_TEMPLATE % movie_id, movie_id,
             'Downloading movie JSON')
             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)
 
         movie_name = movie['name']
         return self._extract_videos(movie_id, movie_name)
 


@@ -120,5 +127,12 @@ class RutubePersonIE(RutubeChannelIE):
     IE_NAME = 'rutube:person'
     IE_DESC = 'Rutube person videos'
     _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
     IE_NAME = 'rutube:person'
     IE_DESC = 'Rutube person videos'
     _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'

+    _TESTS = [{
+        'url': 'http://rutube.ru/video/person/313878/',
+        'info_dict': {
+            'id': '313878',
+        },
+        'playlist_mincount': 37,
+    }]

 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'