compat_str,
compat_urllib_request
)
-from ..utils import url_sanitize_consecutive_slashes
+from ..utils import sanitize_url_path_consecutive_slashes
class SohuIE(InfoExtractor):
'ext': 'mp4',
'title': '【爱范品】第31期:MWC见不到的奇葩手机',
}
+ }, {
+ 'note': 'Multipart video',
+ 'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml',
+ 'info_dict': {
+ 'id': '78910339',
+ 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+ },
+ 'playlist': [{
+ 'md5': 'bdbfb8f39924725e6589c146bc1883ad',
+ 'info_dict': {
+ 'id': '78910339_part1',
+ 'ext': 'mp4',
+ 'duration': 294,
+ 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+ }
+ }, {
+ 'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',
+ 'info_dict': {
+ 'id': '78910339_part2',
+ 'ext': 'mp4',
+ 'duration': 300,
+ 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+ }
+ }, {
+ 'md5': '8407e634175fdac706766481b9443450',
+ 'info_dict': {
+ 'id': '78910339_part3',
+ 'ext': 'mp4',
+ 'duration': 150,
+ 'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+ }
+ }]
+ }, {
+ 'note': 'Video with title containing dash',
+ 'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml',
+ 'info_dict': {
+ 'id': '78932792',
+ 'ext': 'mp4',
+ 'title': 'youtube-dl testing video',
+ },
+ 'params': {
+ 'skip_download': True
+ }
}]
def _real_extract(self, url):
if cn_verification_proxy:
req.add_header('Ytdl-request-proxy', cn_verification_proxy)
- return self._download_json(req, video_id,
- 'Downloading JSON data for %s' % vid_id)
+ return self._download_json(
+ req, video_id,
+ 'Downloading JSON data for %s' % vid_id)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
mytv = mobj.group('mytv') is not None
webpage = self._download_webpage(url, video_id)
- raw_title = self._html_search_regex(
- r'(?s)<title>(.+?)</title>',
- webpage, 'video title')
- title = raw_title.partition('-')[0].strip()
+
+ title = re.sub(r' - 搜狐视频$', '', self._og_search_title(webpage))
vid = self._html_search_regex(
r'var vid ?= ?["\'](\d+)["\']',
part_info = part_str.split('|')
- video_url = url_sanitize_consecutive_slashes(
+ video_url = sanitize_url_path_consecutive_slashes(
'%s%s?key=%s' % (part_info[0], su[i], part_info[3]))
formats.append({
info['id'] = video_id
else:
info = {
- '_type': 'playlist',
+ '_type': 'multi_video',
'entries': playlist,
'id': video_id,
+ 'title': title,
}
return info