mirror of
https://github.com/blackjack4494/yt-dlc.git
synced 2024-12-23 00:07:49 +00:00
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
This commit is contained in:
parent
f631c3311a
commit
3f40217704
1 changed files with 10 additions and 12 deletions
|
@ -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 @@ class InstagramIE(InfoExtractor):
|
|||
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'<title>(.+?)</title>',
|
||||
webpage, u'title', flags=re.DOTALL)
|
||||
title = re.sub(u'(?: *\(Videos?\))? \u2022 Instagram$', '', html_title).strip()
|
||||
uploader_id = self._html_search_regex(
|
||||
r'<div class="media-user" id="media_user">.*?<h2><a href="[^"]*">([^<]*)</a></h2>',
|
||||
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,
|
||||
}]
|
||||
|
|
Loading…
Reference in a new issue