projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Merge pull request #5556 from jaimeMF/best-format-nodash
[youtube-dl]
/
youtube_dl
/
extractor
/
sohu.py
diff --git
a/youtube_dl/extractor/sohu.py
b/youtube_dl/extractor/sohu.py
index ea5cc06b980771fb4c9ab29459846084269c75a2..f8a4840f7b210d0092154a0910188a22efd9bf8b 100644
(file)
--- a/
youtube_dl/extractor/sohu.py
+++ b/
youtube_dl/extractor/sohu.py
@@
-8,7
+8,7
@@
from ..compat import (
compat_str,
compat_urllib_request
)
compat_str,
compat_urllib_request
)
-from ..utils import
url_sanitize
_consecutive_slashes
+from ..utils import
sanitize_url_path
_consecutive_slashes
class SohuIE(InfoExtractor):
class SohuIE(InfoExtractor):
@@
-47,6
+47,7
@@
class SohuIE(InfoExtractor):
'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml',
'info_dict': {
'id': '78910339',
'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',
},
'playlist': [{
'md5': 'bdbfb8f39924725e6589c146bc1883ad',
@@
-74,7
+75,7
@@
class SohuIE(InfoExtractor):
}
}]
}, {
}
}]
}, {
- '
info
': 'Video with title containing dash',
+ '
note
': 'Video with title containing dash',
'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml',
'info_dict': {
'id': '78932792',
'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml',
'info_dict': {
'id': '78932792',
@@
-100,8
+101,9
@@
class SohuIE(InfoExtractor):
if cn_verification_proxy:
req.add_header('Ytdl-request-proxy', cn_verification_proxy)
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')
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
@@
-109,7
+111,7
@@
class SohuIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
webpage = self._download_webpage(url, video_id)
- title =
self._og_search_title(webpage
)
+ title =
re.sub(r' - 搜狐视频$', '', self._og_search_title(webpage)
)
vid = self._html_search_regex(
r'var vid ?= ?["\'](\d+)["\']',
vid = self._html_search_regex(
r'var vid ?= ?["\'](\d+)["\']',
@@
-146,7
+148,7
@@
class SohuIE(InfoExtractor):
part_info = part_str.split('|')
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({
'%s%s?key=%s' % (part_info[0], su[i], part_info[3]))
formats.append({
@@
-171,9
+173,10
@@
class SohuIE(InfoExtractor):
info['id'] = video_id
else:
info = {
info['id'] = video_id
else:
info = {
- '_type': '
playlist
',
+ '_type': '
multi_video
',
'entries': playlist,
'id': video_id,
'entries': playlist,
'id': video_id,
+ 'title': title,
}
return info
}
return info