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

[viki:channel] Extract title from JSON

Browse source
This commit is contained in:
Sergey M․ 2015-05-20 21:28:04 +06:00
parent cc7051efd7
commit b0d619fde2
1 changed files with 24 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

40
youtube_dl/extractor/viki.py
View file

@ -23,7 +23,7 @@ class VikiIE(InfoExtractor):
# iPad2
_USER_AGENT = 'Mozilla/5.0(iPad; U; CPU OS 4_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8F191 Safari/6533.18.5'
_VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)'
_VALID_URL = r'https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)'
_TESTS = [{
'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14',
'info_dict': {
@ -149,7 +149,7 @@ class VikiIE(InfoExtractor):
class VikiChannelIE(InfoExtractor):
IE_NAME = 'viki:channel'
_VALID_URL = r'^https?://(?:www\.)?viki\.com/tv/(?P<id>[0-9]+c)'
_VALID_URL = r'https?://(?:www\.)?viki\.com/tv/(?P<id>[0-9]+c)'
_TESTS = [{
'url': 'http://www.viki.com/tv/50c-boys-over-flowers',
'info_dict': {
@ -167,27 +167,35 @@ class VikiChannelIE(InfoExtractor):
},
'playlist_count': 127,
}]
_API_BASE = 'http://api.viki.io/v4/containers'
_APP = '100000a'
_PER_PAGE = 25
def _real_extract(self, url):
show_id = self._match_id(url)
show_page = self._download_webpage(url, show_id, 'Download show page')
channel_id = self._match_id(url)
title = self._og_search_title(show_page)
description = self._og_search_description(show_page)
channel = self._download_json(
'%s/%s.json?app=%s' % (self._API_BASE, channel_id, self._APP),
channel_id, 'Downloading channel JSON')
titles = channel['titles']
title = titles.get('en') or titles[titles.keys()[0]]
descriptions = channel['descriptions']
description = descriptions.get('en') or descriptions[descriptions.keys()[0]]
entries = []
for video_type in ['episodes', 'clips']:
json_url = 'http://api.viki.io/v4/containers/%s/%s.json?app=100000a&per_page=%d&sort=number&direction=asc&with_paging=true&page=1' % (show_id, video_type, self._PER_PAGE)
while json_url is not None:
show_json = self._download_json(
json_url, show_id,
note='Downloading %s json page #%s' %
(video_type, re.search(r'[?&]page=([0-9]+)', json_url).group(1)))
for video in show_json['response']:
for video_type in ('episodes', 'clips'):
page_url = '%s/%s/%s.json?app=%s&per_page=%d&sort=number&direction=asc&with_paging=true&page=1' % (self._API_BASE, channel_id, video_type, self._APP, self._PER_PAGE)
while page_url:
page = self._download_json(
page_url, channel_id,
'Downloading %s JSON page #%s'
% (video_type, re.search(r'[?&]page=([0-9]+)', page_url).group(1)))
for video in page['response']:
video_id = video['id']
entries.append(self.url_result(
'http://www.viki.com/videos/%s' % video_id, 'Viki', video_id))
json_url = show_json['pagination']['next']
page_url = page['pagination']['next']
return self.playlist_result(entries, show_id, title, description)
return self.playlist_result(entries, channel_id, title, description)