projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
12810c9
)
[crunchyroll] Fix uploader and upload date extraction
author
Sergey M․
<dstftw@gmail.com>
Tue, 8 Sep 2015 08:37:53 +0000
(14:37 +0600)
committer
Sergey M․
<dstftw@gmail.com>
Tue, 8 Sep 2015 08:37:53 +0000
(14:37 +0600)
youtube_dl/extractor/crunchyroll.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/crunchyroll.py
b/youtube_dl/extractor/crunchyroll.py
index c5dbc682dbdafd13446d540483a3531768eeb53a..95952bc292c05548a88876b7b52cf236f8bdc826 100644
(file)
--- a/
youtube_dl/extractor/crunchyroll.py
+++ b/
youtube_dl/extractor/crunchyroll.py
@@
-275,10
+275,14
@@
Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
if not video_description:
video_description = None
video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
if not video_description:
video_description = None
- video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
+ video_upload_date = self._html_search_regex(
+ [r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'],
+ webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
if video_upload_date:
video_upload_date = unified_strdate(video_upload_date)
if video_upload_date:
video_upload_date = unified_strdate(video_upload_date)
- video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, 'video_uploader', fatal=False, flags=re.DOTALL)
+ video_uploader = self._html_search_regex(
+ r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage,
+ 'video_uploader', fatal=False)
playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
playerdata_req = compat_urllib_request.Request(playerdata_url)
playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
playerdata_req = compat_urllib_request.Request(playerdata_url)