aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2016-03-27 00:09:12 +0600
committerSergey M․ <dstftw@gmail.com>2016-03-27 00:09:12 +0600
commitb24ab3e341b9082774785332a1aa6405764f7202 (patch)
treef359fa0676de6f51885c0f7dbbca5c08a7c1caed /youtube_dl/extractor
parentaf4116f4f04a3fc8150fdb4a220ef31a0a2dd044 (diff)
downloadyoutube-dl-b24ab3e341b9082774785332a1aa6405764f7202.tar.xz
[udemy] Improve paid course detection
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/udemy.py15
1 files changed, 10 insertions, 5 deletions
diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py
index 5a5e9fa9e..71bea5363 100644
--- a/youtube_dl/extractor/udemy.py
+++ b/youtube_dl/extractor/udemy.py
@@ -55,21 +55,26 @@ class UdemyIE(InfoExtractor):
}]
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(
- 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))
if checkout_url:
raise ExtractorError(
'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(
r'href=(["\'])(?P<url>(?:https?://(?:www\.)?udemy\.com)?/course/subscribe/.+?)\1',
webpage, 'enroll url', group='url', default=None))
if enroll_url:
- if not enroll_url.startswith('http'):
- enroll_url = compat_urlparse.urljoin(base_url, enroll_url)
- webpage = self._download_webpage(enroll_url, course_id, 'Enrolling in the course')
+ webpage = self._download_webpage(
+ combine_url(base_url, enroll_url),
+ course_id, 'Enrolling in the course')
if '>You have enrolled in' in webpage:
self.to_screen('%s: Successfully enrolled in the course' % course_id)