class YoukuIE(InfoExtractor):
IE_NAME = 'youku'
+ IE_DESC = '优酷'
_VALID_URL = r'''(?x)
(?:
http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
},
'playlist_count': 13,
'skip': 'Available in China only',
+ }, {
+ 'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html',
+ 'note': 'Video protected with password',
+ 'info_dict': {
+ 'id': 'XNjA1NzA2Njgw',
+ 'title': '邢義田复旦讲座之想象中的胡人—从“左衽孔子”说起',
+ },
+ 'playlist_count': 19,
+ 'params': {
+ 'videopassword': '100600',
+ },
}]
def construct_video_urls(self, data1, data2):
raw_data = self._download_json(req, video_id, note=note)
return raw_data['data'][0]
+ video_password = self._downloader.params.get('videopassword', None)
+
# request basic data
+ basic_data_url = 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id
+ if video_password:
+ basic_data_url += '?password=%s' % video_password
+
data1 = retrieve_data(
- 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id,
+ basic_data_url,
'Downloading JSON metadata 1')
data2 = retrieve_data(
'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id,
video_urls_dict = self.construct_video_urls(data1, data2)
# construct info
- entries = []
+ entries = [{
+ 'id': '%s_part%d' % (video_id, i + 1),
+ 'title': title,
+ 'formats': [],
+ # some formats are not available for all parts, we have to detect
+ # which one has all
+ } for i in range(max(len(v) for v in data1['segs'].values()))]
for fm in data1['streamtypes']:
video_urls = video_urls_dict[fm]
- for i in range(len(video_urls)):
- if len(entries) < i + 1:
- entries.append({'formats': []})
- entries[i]['formats'].append(
- {
- 'url': video_urls[i],
- 'format_id': self.get_format_name(fm),
- 'ext': self.parse_ext_l(fm),
- 'filesize': int(data1['segs'][fm][i]['size'])
- }
- )
-
- for i in range(len(entries)):
- entries[i].update(
- {
- 'id': '%s_part%d' % (video_id, i + 1),
- 'title': title,
- }
- )
+ for video_url, seg, entry in zip(video_urls, data1['segs'][fm], entries):
+ entry['formats'].append({
+ 'url': video_url,
+ 'format_id': self.get_format_name(fm),
+ 'ext': self.parse_ext_l(fm),
+ 'filesize': int(seg['size']),
+ })
return {
'_type': 'multi_video',