projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
80faa7a
)
[iconosquare] fix info extraction
author
remitamine
<remitamine@gmail.com>
Thu, 24 Sep 2015 20:55:44 +0000
(21:55 +0100)
committer
Sergey M․
<dstftw@gmail.com>
Thu, 24 Sep 2015 22:36:15 +0000
(
04:36
+0600)
youtube_dl/extractor/iconosquare.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/iconosquare.py
b/youtube_dl/extractor/iconosquare.py
index 70e4c0d4173816e990749759cf2d36fe902904ee..4fff8c0b30b04111855e89335ea7f9e3066e168f 100644
(file)
--- a/
youtube_dl/extractor/iconosquare.py
+++ b/
youtube_dl/extractor/iconosquare.py
@@
-1,7
+1,10
@@
from __future__ import unicode_literals
from .common import InfoExtractor
from __future__ import unicode_literals
from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+ int_or_none,
+ get_element_by_id,
+)
class IconosquareIE(InfoExtractor):
class IconosquareIE(InfoExtractor):
@@
-12,7
+15,7
@@
class IconosquareIE(InfoExtractor):
'info_dict': {
'id': '522207370455279102_24101272',
'ext': 'mp4',
'info_dict': {
'id': '522207370455279102_24101272',
'ext': 'mp4',
- 'title': '
Instagram media by @aguynamedpatrick (Patrick Janelle)
',
+ 'title': '
A little over a year ago, I posted my first #dailycortado, a drink introduced to...
',
'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
'timestamp': 1376471991,
'upload_date': '20130814',
'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
'timestamp': 1376471991,
'upload_date': '20130814',
@@
-29,8
+32,7
@@
class IconosquareIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
media = self._parse_json(
webpage = self._download_webpage(url, video_id)
media = self._parse_json(
- self._search_regex(
- r'window\.media\s*=\s*({.+?});\n', webpage, 'media'),
+ get_element_by_id('mediaJson', webpage),
video_id)
formats = [{
video_id)
formats = [{
@@
-42,7
+44,7
@@
class IconosquareIE(InfoExtractor):
self._sort_formats(formats)
title = self._html_search_regex(
self._sort_formats(formats)
title = self._html_search_regex(
- r'<title>(.+?)
(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)
</title>',
+ r'<title>(.+?)</title>',
webpage, 'title')
timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time'))
webpage, 'title')
timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time'))