w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[iconosquare] fix info extraction

Browse source
This commit is contained in:
remitamine 2015-09-24 21:55:44 +01:00 committed by Sergey M․
parent 80faa7a152
commit 857421024d
1 changed files with 7 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
youtube_dl/extractor/iconosquare.py
View file

@ -1,7 +1,10 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor 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': { 'info_dict': {
'id': '522207370455279102_24101272', 'id': '522207370455279102_24101272',
'ext': 'mp4', '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', 'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
'timestamp': 1376471991, 'timestamp': 1376471991,
'upload_date': '20130814', 'upload_date': '20130814',
@ -29,8 +32,7 @@ class IconosquareIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
media = self._parse_json( media = self._parse_json(
self._search_regex( get_element_by_id('mediaJson', webpage),
r'window\.media\s*=\s*({.+?});\n', webpage, 'media'),
video_id) video_id)
formats = [{ formats = [{
@ -42,7 +44,7 @@ class IconosquareIE(InfoExtractor):
self._sort_formats(formats) self._sort_formats(formats)
title = self._html_search_regex( title = self._html_search_regex(
r'<title>(.+?)(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)</title>', r'<title>(.+?)</title>',
webpage, 'title') webpage, 'title')
timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time')) timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time'))