From 3f4021770488cd5f11d5d640769407475895efaf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Thu, 18 Jul 2013 13:12:27 +0200 Subject: [PATCH] InstagramIE: fix the extraction of the uploader_id and the title The page title is now 'Instagram', so we build it. Also extract the description --- youtube_dl/extractor/instagram.py | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index f9ac8d5b4..ddc42882a 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -10,7 +10,8 @@ class InstagramIE(InfoExtractor): u'md5': u'0d2da106a9d2631273e192b372806516', u'info_dict': { u"uploader_id": u"naomipq", - u"title": u"Video by naomipq" + u"title": u"Video by naomipq", + u'description': u'md5:1f17f0ab29bd6fe2bfad705f58de3cb8', } } @@ -18,20 +19,17 @@ def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group(1) webpage = self._download_webpage(url, video_id) - html_title = self._html_search_regex( - r'(.+?)', - webpage, u'title', flags=re.DOTALL) - title = re.sub(u'(?: *\(Videos?\))? \u2022 Instagram$', '', html_title).strip() - uploader_id = self._html_search_regex( - r'
.*?

([^<]*)

', - webpage, u'uploader id', fatal=False, flags=re.DOTALL) - ext = 'mp4' + uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"', + webpage, u'uploader id', fatal=False) + desc = self._search_regex(r'"caption":"(.*?)"', webpage, u'description', + fatal=False) return [{ 'id': video_id, 'url': self._og_search_video_url(webpage), - 'ext': ext, - 'title': title, + 'ext': 'mp4', + 'title': u'Video by %s' % uploader_id, 'thumbnail': self._og_search_thumbnail(webpage), - 'uploader_id' : uploader_id + 'uploader_id' : uploader_id, + 'description': desc, }]