projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
6ab30ff
)
[vivo] Fix extraction (closes #18906)
author
Daniel Höpfl
<daniel@hoepfl.de>
Wed, 13 Feb 2019 15:29:43 +0000
(16:29 +0100)
committer
Sergey M․
<dstftw@gmail.com>
Wed, 22 May 2019 20:06:07 +0000
(
03:06
+0700)
youtube_dl/extractor/shared.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/shared.py
b/youtube_dl/extractor/shared.py
index 931a0f70e0e0924689dfb6b71c374e6fa2c14457..eade8fd9e0148b5906c5ad8d89c1a8ab5fe17cda 100644
(file)
--- a/
youtube_dl/extractor/shared.py
+++ b/
youtube_dl/extractor/shared.py
@@
-1,5
+1,7
@@
from __future__ import unicode_literals
from __future__ import unicode_literals
+import re
+
from .common import InfoExtractor
from ..compat import compat_b64decode
from ..utils import (
from .common import InfoExtractor
from ..compat import compat_b64decode
from ..utils import (
@@
-7,6
+9,7
@@
from ..utils import (
int_or_none,
url_or_none,
urlencode_postdata,
int_or_none,
url_or_none,
urlencode_postdata,
+ unescapeHTML,
)
)
@@
-22,8
+25,7
@@
class SharedBaseIE(InfoExtractor):
video_url = self._extract_video_url(webpage, video_id, url)
video_url = self._extract_video_url(webpage, video_id, url)
- title = compat_b64decode(self._html_search_meta(
- 'full:title', webpage, 'title')).decode('utf-8')
+ title = self._extract_title(webpage)
filesize = int_or_none(self._html_search_meta(
'full:size', webpage, 'file size', fatal=False))
filesize = int_or_none(self._html_search_meta(
'full:size', webpage, 'file size', fatal=False))
@@
-35,6
+37,10
@@
class SharedBaseIE(InfoExtractor):
'title': title,
}
'title': title,
}
+ def _extract_title(self, webpage):
+ return compat_b64decode(self._html_search_meta(
+ 'full:title', webpage, 'title')).decode('utf-8')
+
class SharedIE(SharedBaseIE):
IE_DESC = 'shared.sx'
class SharedIE(SharedBaseIE):
IE_DESC = 'shared.sx'
@@
-86,6
+92,14
@@
class VivoIE(SharedBaseIE):
},
}
},
}
+ def _extract_title(self, webpage):
+ data_title = self._search_regex(
+ r'data-name\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', webpage,
+ 'title', default=None, group='title')
+ if data_title:
+ return unescapeHTML(re.sub(r"\.[a-z0-9]{3,4}$", "", data_title))
+ return self._og_search_title(webpage)
+
def _extract_video_url(self, webpage, video_id, *args):
def decode_url(encoded_url):
return compat_b64decode(encoded_url).decode('utf-8')
def _extract_video_url(self, webpage, video_id, *args):
def decode_url(encoded_url):
return compat_b64decode(encoded_url).decode('utf-8')