github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

[udemy] Update User-Agent and detect captcha (closes #14713, closes #15839, closes #18126)

Browse source
This commit is contained in:
Sergey M․ 2019-02-17 00:58:13 +07:00
parent ba2e3730d1
commit ae65c93a26
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 14 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
youtube_dl/extractor/udemy.py
View file

@ -123,10 +123,22 @@ class UdemyIE(InfoExtractor):
def _download_webpage_handle(self, *args, **kwargs): def _download_webpage_handle(self, *args, **kwargs):
headers = kwargs.get('headers', {}).copy() headers = kwargs.get('headers', {}).copy()
headers['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4' headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36'
kwargs['headers'] = headers kwargs['headers'] = headers
return super(UdemyIE, self)._download_webpage_handle( ret = super(UdemyIE, self)._download_webpage_handle(
*args, **compat_kwargs(kwargs)) *args, **compat_kwargs(kwargs))
if not ret:
return ret
webpage, _ = ret
if any(p in webpage for p in (
'>Please verify you are a human',
'Access to this page has been denied because we believe you are using automation tools to browse the website',
'"_pxCaptcha"')):
raise ExtractorError(
'Udemy asks you to solve a CAPTCHA. Login with browser, '
'solve CAPTCHA, then export cookies and pass cookie file to '
'youtube-dl with --cookies.', expected=True)
return ret
def _download_json(self, url_or_request, *args, **kwargs): def _download_json(self, url_or_request, *args, **kwargs):
headers = { headers = {