ImdbListIE,
KhanAcademyIE,
EveryonesMixtapeIE,
+ RutubeChannelIE,
)
def test_imdb_list(self):
dl = FakeYDL()
ie = ImdbListIE(dl)
- result = ie.extract('http://www.imdb.com/list/sMjedvGDd8U')
+ result = ie.extract('http://www.imdb.com/list/JFs9NWw6XI0')
self.assertIsPlaylist(result)
- self.assertEqual(result['id'], 'sMjedvGDd8U')
- self.assertEqual(result['title'], 'Animated and Family Films')
- self.assertTrue(len(result['entries']) >= 48)
+ self.assertEqual(result['id'], 'JFs9NWw6XI0')
+ self.assertEqual(result['title'], 'March 23, 2012 Releases')
+ self.assertEqual(len(result['entries']), 7)
def test_khanacademy_topic(self):
dl = FakeYDL()
self.assertEqual(result['id'], 'm7m0jJAbMQi')
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__':
class BrightcoveIE(InfoExtractor):
_VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)'
_FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
- _PLAYLIST_URL_TEMPLATE = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s'
_TESTS = [
{
'description': 'md5:363109c02998fee92ec02211bd8000df',
'uploader': 'National Ballet of Canada',
},
- },
+ }
]
@classmethod
"""Try to extract the brightcove url from the wepbage, returns None
if it can't be found
"""
+
+ url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage)
+ if url_m:
+ return url_m.group(1)
+
m_brightcove = re.search(
r'''(?sx)<object
(?:
return self._extract_video_info(video_info)
def _get_playlist_info(self, player_key):
- playlist_info = self._download_webpage(self._PLAYLIST_URL_TEMPLATE % player_key,
- player_key, 'Downloading playlist information')
+ info_url = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s' % player_key
+ playlist_info = self._download_webpage(
+ info_url, player_key, 'Downloading playlist information')
json_data = json.loads(playlist_info)
if 'videoList' not in json_data:
# 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/',
- u'file': u'3eac3b4561676c17df9132a9a1e62e3e.mp4',
- u'info_dict': {
- u'title': u'Раненный кенгуру забежал в аптеку',
- u'uploader': u'NTDRussian',
- u'uploader_id': u'29790',
+ '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',
},
- 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')
- webpage = self._download_webpage(url, long_id)
- og_video = self._og_search_video_url(webpage)
- short_id = compat_urlparse.urlparse(og_video).path[1:]
- options = self._get_api_response(short_id, 'options')
- trackinfo = self._get_api_response(short_id, 'trackinfo')
+ 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)
+
# 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'],
- 'title': trackinfo['title'],
+ 'id': video['id'],
+ '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 not results:
+ break
+ entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
+ if not page['has_next']:
+ 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'
projects / youtube-dl / commitdiff