float_or_none,
int_or_none,
sanitized_Request,
+ unescapeHTML,
)
_VALID_URL = r'https?://www\.udemy\.com/(?:[^#]+#/lecture/|lecture/view/?\?lectureId=)(?P<id>\d+)'
_LOGIN_URL = 'https://www.udemy.com/join/login-popup/?displayType=ajax&showSkipButton=1'
_ORIGIN_URL = 'https://www.udemy.com'
- _SUCCESSFULLY_ENROLLED = '>You have enrolled in this course!<'
- _ALREADY_ENROLLED = '>You are already taking this course.<'
_NETRC_MACHINE = 'udemy'
_TESTS = [{
'skip': 'Requires udemy account credentials',
}]
- def _enroll_course(self, webpage, course_id):
- enroll_url = self._search_regex(
- r'href=(["\'])(?P<url>https?://(?:www\.)?udemy\.com/course/subscribe/.+?)\1',
- webpage, 'enroll url', group='url',
- default='https://www.udemy.com/course/subscribe/?courseId=%s' % course_id)
- webpage = self._download_webpage(enroll_url, course_id, 'Enrolling in the course')
- if self._SUCCESSFULLY_ENROLLED in webpage:
- self.to_screen('%s: Successfully enrolled in' % course_id)
- elif self._ALREADY_ENROLLED in webpage:
- self.to_screen('%s: Already enrolled in' % course_id)
+ def _enroll_course(self, base_url, webpage, course_id):
+ checkout_url = unescapeHTML(self._search_regex(
+ 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)
+
+ 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')
+ if '>You have enrolled in' in webpage:
+ self.to_screen('%s: Successfully enrolled in the course' % course_id)
def _download_lecture(self, course_id, lecture_id):
return self._download_json(
'fields[asset]': 'asset_type,stream_url,thumbnail_url,download_urls,data',
'instructorPreviewMode': 'False',
})),
- lecture_id, 'Downloading lecture JSON', fatal=False)
+ lecture_id, 'Downloading lecture JSON')
def _handle_error(self, response):
if not isinstance(response, dict):
error_str += ' - %s' % error_data.get('formErrors')
raise ExtractorError(error_str, expected=True)
- def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', *args, **kwargs):
+ def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'):
headers = {
'X-Udemy-Snail-Case': 'true',
'X-Requested-With': 'XMLHttpRequest',
else:
url_or_request = sanitized_Request(url_or_request, headers=headers)
- response = super(UdemyIE, self)._download_json(url_or_request, video_id, note, *args, **kwargs)
+ response = super(UdemyIE, self)._download_json(url_or_request, video_id, note)
self._handle_error(response)
return response
webpage = self._download_webpage(url, lecture_id)
course_id = self._search_regex(
- r'data-course-id=["\'](\d+)', webpage, 'course id')
+ (r'data-course-id=["\'](\d+)', r'"id"\s*:\s*(\d+)'),
+ webpage, 'course id')
try:
lecture = self._download_lecture(course_id, lecture_id)
except ExtractorError as e:
# Error could possibly mean we are not enrolled in the course
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
- self._enroll_course(webpage, course_id)
- lecture_id = self._download_lecture(course_id, lecture_id)
+ self._enroll_course(url, webpage, course_id)
+ lecture = self._download_lecture(course_id, lecture_id)
else:
raise
course_id = response['id']
course_title = response.get('title')
- self._enroll_course(webpage, course_id)
+ self._enroll_course(url, webpage, course_id)
response = self._download_json(
'https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id,
course_id, 'Downloading course curriculum')
- entries = [
- self.url_result(
- 'https://www.udemy.com/%s/#/lecture/%s' % (course_path, asset['id']), 'Udemy')
- for asset in response if asset.get('assetType') or asset.get('asset_type') == 'Video'
- ]
+ entries = []
+ chapter, chapter_number = None, None
+ for asset in response:
+ asset_type = asset.get('assetType') or asset.get('asset_type')
+ if asset_type == 'Video':
+ asset_id = asset.get('id')
+ if asset_id:
+ entry = {
+ '_type': 'url_transparent',
+ 'url': 'https://www.udemy.com/%s/#/lecture/%s' % (course_path, asset['id']),
+ 'ie_key': UdemyIE.ie_key(),
+ }
+ if chapter_number:
+ entry['chapter_number'] = chapter_number
+ if chapter:
+ entry['chapter'] = chapter
+ entries.append(entry)
+ elif asset.get('type') == 'chapter':
+ chapter_number = asset.get('index') or asset.get('object_index')
+ chapter = asset.get('title')
return self.playlist_result(entries, course_id, course_title)
projects / youtube-dl / blobdiff