diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-02-10 20:24:12 +0100 | 
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-02-10 20:24:12 +0100 | 
| commit | 0de668af512f87315dd9e15717ce6c97050e3606 (patch) | |
| tree | a8d656cbff489d24eeb139df037eaeac600ac9e0 | |
| parent | 2a584ea90a52b8a0a34c9bc23e123a0133d777c8 (diff) | |
[instagram] Modernize
| -rw-r--r-- | youtube_dl/extractor/instagram.py | 40 | 
1 files changed, 22 insertions, 18 deletions
| diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 660573d02..63141af27 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -1,35 +1,39 @@ +from __future__ import unicode_literals +  import re  from .common import InfoExtractor +  class InstagramIE(InfoExtractor): -    _VALID_URL = r'(?:http://)?instagram\.com/p/(.*?)/' +    _VALID_URL = r'http://instagram\.com/p/(?P<id>.*?)/'      _TEST = { -        u'url': u'http://instagram.com/p/aye83DjauH/?foo=bar#abc', -        u'file': u'aye83DjauH.mp4', -        u'md5': u'0d2da106a9d2631273e192b372806516', -        u'info_dict': { -            u"uploader_id": u"naomipq",  -            u"title": u"Video by naomipq", -            u'description': u'md5:1f17f0ab29bd6fe2bfad705f58de3cb8', +        'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc', +        'md5': '0d2da106a9d2631273e192b372806516', +        'info_dict': { +            'id': 'aye83DjauH', +            'ext': 'mp4', +            'uploader_id': 'naomipq', +            'title': 'Video by naomipq', +            'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',          }      }      def _real_extract(self, url):          mobj = re.match(self._VALID_URL, url) -        video_id = mobj.group(1) +        video_id = mobj.group('id')          webpage = self._download_webpage(url, video_id)          uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"', -            webpage, u'uploader id', fatal=False) -        desc = self._search_regex(r'"caption":"(.*?)"', webpage, u'description', +            webpage, 'uploader id', fatal=False) +        desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description',              fatal=False) -        return [{ -            'id':        video_id, -            'url':       self._og_search_video_url(webpage, secure=False), -            'ext':       'mp4', -            'title':     u'Video by %s' % uploader_id, +        return { +            'id': video_id, +            'url': self._og_search_video_url(webpage, secure=False), +            'ext': 'mp4', +            'title': 'Video by %s' % uploader_id,              'thumbnail': self._og_search_thumbnail(webpage), -            'uploader_id' : uploader_id, +            'uploader_id': uploader_id,              'description': desc, -        }] +        } | 
