Upstream/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-13 20:57:14 +01:00
Code Issues Projects Releases Wiki Activity

[udemy] Improve paid course detection

Browse Source
This commit is contained in:
Sergey M․ 2016-03-27 00:09:12 +06:00
parent af4116f4f0
commit b24ab3e341
1 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
youtube_dl/extractor/udemy.py
View File

@ -55,21 +55,26 @@ class UdemyIE(InfoExtractor):
}] }]
def _enroll_course(self, base_url, webpage, course_id): def _enroll_course(self, base_url, webpage, course_id):
def combine_url(base_url, url):
return compat_urlparse.urljoin(base_url, url) if not url.startswith('http') else url
checkout_url = unescapeHTML(self._search_regex( checkout_url = unescapeHTML(self._search_regex(
r'href=(["\'])(?P<url>https?://(?:www\.)?udemy\.com/payment/checkout/.+?)\1', r'href=(["\'])(?P<url>(?:https?://(?:www\.)?udemy\.com)?/payment/checkout/.+?)\1',
webpage, 'checkout url', group='url', default=None)) webpage, 'checkout url', group='url', default=None))
if checkout_url: if checkout_url:
raise ExtractorError( raise ExtractorError(
'Course %s is not free. You have to pay for it before you can download. ' 'Course %s is not free. You have to pay for it before you can download. '
'Use this URL to confirm purchase: %s' % (course_id, checkout_url), expected=True) 'Use this URL to confirm purchase: %s'
% (course_id, combine_url(base_url, checkout_url)),
expected=True)
enroll_url = unescapeHTML(self._search_regex( enroll_url = unescapeHTML(self._search_regex(
r'href=(["\'])(?P<url>(?:https?://(?:www\.)?udemy\.com)?/course/subscribe/.+?)\1', r'href=(["\'])(?P<url>(?:https?://(?:www\.)?udemy\.com)?/course/subscribe/.+?)\1',
webpage, 'enroll url', group='url', default=None)) webpage, 'enroll url', group='url', default=None))
if enroll_url: if enroll_url:
if not enroll_url.startswith('http'): webpage = self._download_webpage(
enroll_url = compat_urlparse.urljoin(base_url, enroll_url) combine_url(base_url, enroll_url),
webpage = self._download_webpage(enroll_url, course_id, 'Enrolling in the course') course_id, 'Enrolling in the course')
if '>You have enrolled in' in webpage: if '>You have enrolled in' in webpage:
self.to_screen('%s: Successfully enrolled in the course' % course_id) self.to_screen('%s: Successfully enrolled in the course' % course_id)