jcgruenhage/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[rutube] Improve video extractor

Browse source
This commit is contained in:
dst 2014-01-28 08:19:45 +07:00
parent 1547c8cc88
commit a2fb2a2134
1 changed files with 23 additions and 24 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

47
youtube_dl/extractor/rutube.py
View file

@ -7,8 +7,8 @@ import itertools
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urlparse,
compat_str, compat_str,
unified_strdate,
ExtractorError, ExtractorError,
) )
@ -32,20 +32,18 @@ class RutubeIE(InfoExtractor):
}, },
} }
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): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
long_id = mobj.group('long_id') long_id = mobj.group('long_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' % long_id,
short_id = compat_urlparse.urlparse(og_video).path[1:] long_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' % long_id,
long_id, 'Downloading trackinfo JSON')
trackinfo = json.loads(api_response)
# Some videos don't have the author field # Some videos don't have the author field
author = trackinfo.get('author') or {} author = trackinfo.get('author') or {}
m3u8_url = trackinfo['video_balancer'].get('m3u8') m3u8_url = trackinfo['video_balancer'].get('m3u8')
@ -53,13 +51,18 @@ class RutubeIE(InfoExtractor):
raise ExtractorError('Couldn\'t find m3u8 manifest url') raise ExtractorError('Couldn\'t find m3u8 manifest url')
return { 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, 'url': m3u8_url,
'ext': 'mp4', 'ext': 'mp4',
'thumbnail': options['thumbnail_url'], 'thumbnail': video['thumbnail_url'],
'uploader': author.get('name'), 'uploader': author.get('name'),
'uploader_id': compat_str(author['id']) if author else None, '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,
} }
@ -73,15 +76,13 @@ class RutubeChannelIE(InfoExtractor):
def _extract_videos(self, channel_id, channel_title=None): def _extract_videos(self, channel_id, channel_title=None):
entries = [] entries = []
for pagenum in itertools.count(1): for pagenum in itertools.count(1):
response_json = self._download_webpage(self._PAGE_TEMPLATE % (channel_id, pagenum), api_response = self._download_webpage(self._PAGE_TEMPLATE % (channel_id, pagenum),
channel_id, 'Downloading page %s' % pagenum) channel_id, 'Downloading page %s' % pagenum)
page = json.loads(response_json) page = json.loads(api_response)
if 'detail' in page and page['detail'] == 'Not found':
raise ExtractorError('Channel %s does not exist' % channel_id, expected=True)
results = page['results'] results = page['results']
if len(results) == 0: if len(results) == 0:
break; break;
entries.extend(self.url_result(v['video_url'], 'Rutube') for v in results) entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
if page['has_next'] is False: if page['has_next'] is False:
break; break;
return self.playlist_result(entries, channel_id, channel_title) return self.playlist_result(entries, channel_id, channel_title)
@ -103,10 +104,8 @@ class RutubeMovieIE(RutubeChannelIE):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
movie_id = mobj.group('id') movie_id = mobj.group('id')
movie_json = self._download_webpage(self._MOVIE_TEMPLATE % movie_id, movie_id, api_response = self._download_webpage(self._MOVIE_TEMPLATE % movie_id, movie_id,
'Downloading movie JSON') 'Downloading movie JSON')
movie = json.loads(movie_json) movie = json.loads(api_response)
if 'detail' in movie and movie['detail'] == 'Not found':
raise ExtractorError('Movie %s does not exist' % movie_id, expected=True)
movie_name = movie['name'] movie_name = movie['name']
return self._extract_videos(movie_id, movie_name) return self._extract_videos(movie_id, movie_name)