diff options
| author | remitamine <remitamine@gmail.com> | 2015-09-24 21:55:44 +0100 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2015-09-25 04:36:15 +0600 |
| commit | 857421024daf810e92036149cc02bcf1c337da5c (patch) | |
| tree | 77aa7d72579b0d641a490d43315795f1c7675a6d /youtube_dl/extractor/iconosquare.py | |
| parent | 80faa7a152415f4cd7264055745e37935c667e72 (diff) | |
| download | youtube-dl-857421024daf810e92036149cc02bcf1c337da5c.tar.xz | |
[iconosquare] fix info extraction
Diffstat (limited to 'youtube_dl/extractor/iconosquare.py')
| -rw-r--r-- | youtube_dl/extractor/iconosquare.py | 12 |
1 files changed, 7 insertions, 5 deletions
diff --git a/youtube_dl/extractor/iconosquare.py b/youtube_dl/extractor/iconosquare.py index 70e4c0d41..4fff8c0b3 100644 --- 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 ..utils import int_or_none +from ..utils import ( + int_or_none, + get_element_by_id, +) class IconosquareIE(InfoExtractor): @@ -12,7 +15,7 @@ class IconosquareIE(InfoExtractor): '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', @@ -29,8 +32,7 @@ class IconosquareIE(InfoExtractor): 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 = [{ @@ -42,7 +44,7 @@ class IconosquareIE(InfoExtractor): 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')) |