0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 02:25:11 +00:00

[generic] Improve detection

Allow download of http://goo.gl/7X5tOk
Fixes #1818
This commit is contained in:
Philipp Hagemeister 2013-11-25 03:35:52 +01:00
parent 79d09f47c2
commit 113577e155

View file

@ -209,7 +209,7 @@ def _real_extract(self, url):
mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
if mobj is None: if mobj is None:
# Broaden the search a little bit: JWPlayer JS loader # Broaden the search a little bit: JWPlayer JS loader
mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http[^\'"&]*)', webpage) mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http[^\'"]*)', webpage)
if mobj is None: if mobj is None:
# Try to find twitter cards info # Try to find twitter cards info
mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage) mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
@ -236,18 +236,16 @@ def _real_extract(self, url):
video_id = compat_urllib_parse.unquote(os.path.basename(video_url)) video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
# here's a fun little line of code for you: # here's a fun little line of code for you:
video_extension = os.path.splitext(video_id)[1][1:]
video_id = os.path.splitext(video_id)[0] video_id = os.path.splitext(video_id)[0]
# video uploader is domain name # video uploader is domain name
video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*', video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*',
url, u'video uploader') url, u'video uploader')
return [{ return {
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'uploader': video_uploader, 'uploader': video_uploader,
'upload_date': None, 'upload_date': None,
'title': video_title, 'title': video_title,
'ext': video_extension, }
}]