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):
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': {
+ 'id': '3eac3b4561676c17df9132a9a1e62e3e',
+ 'ext': 'mp4',
'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)
},
}
- 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,
- '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')
+
+ 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
- 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')
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'
+ 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):
- response_json = self._download_webpage(self._PAGE_TEMPLATE % (channel_id, pagenum),
- channel_id, 'Downloading page %s' % pagenum)
- page = json.loads(response_json)
- if 'detail' in page and page['detail'] == 'Not found':
- raise ExtractorError('Channel %s does not exist' % channel_id, expected=True)
+ page = self._download_json(
+ self._PAGE_TEMPLATE % (channel_id, pagenum),
+ channel_id, 'Downloading page %s' % pagenum)
results = page['results']
- if len(results) == 0:
- break;
- entries.extend(self.url_result(v['video_url'], 'Rutube') for v in results)
- if page['has_next'] is False:
- break;
+ 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):
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+)'
+ _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'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
movie_id = mobj.group('id')
- movie_json = self._download_webpage(self._MOVIE_TEMPLATE % movie_id, movie_id,
- 'Downloading movie JSON')
- movie = json.loads(movie_json)
- if 'detail' in movie and movie['detail'] == 'Not found':
- raise ExtractorError('Movie %s does not exist' % movie_id, expected=True)
+ movie = self._download_json(
+ self._MOVIE_TEMPLATE % movie_id, movie_id,
+ 'Downloading movie JSON')
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+)'
+ _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'
projects / youtube-dl / blobdiff