import re
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+)
+from ..utils import (
ExtractorError,
+ int_or_none,
+ sanitized_Request,
)
class UdemyIE(InfoExtractor):
IE_NAME = 'udemy'
_VALID_URL = r'https?://www\.udemy\.com/(?:[^#]+#/lecture/|lecture/view/?\?lectureId=)(?P<id>\d+)'
- _LOGIN_URL = 'https://www.udemy.com/join/login-submit/'
+ _LOGIN_URL = 'https://www.udemy.com/join/login-popup/?displayType=ajax&showSkipButton=1'
+ _ORIGIN_URL = 'https://www.udemy.com'
_NETRC_MACHINE = 'udemy'
_TESTS = [{
error_str += ' - %s' % error_data.get('formErrors')
raise ExtractorError(error_str, expected=True)
- def _download_json(self, url, video_id, note='Downloading JSON metadata'):
- response = super(UdemyIE, self)._download_json(url, video_id, note)
+ def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'):
+ headers = {
+ 'X-Udemy-Snail-Case': 'true',
+ 'X-Requested-With': 'XMLHttpRequest',
+ }
+ for cookie in self._downloader.cookiejar:
+ if cookie.name == 'client_id':
+ headers['X-Udemy-Client-Id'] = cookie.value
+ elif cookie.name == 'access_token':
+ headers['X-Udemy-Bearer-Token'] = cookie.value
+
+ if isinstance(url_or_request, compat_urllib_request.Request):
+ for header, value in headers.items():
+ url_or_request.add_header(header, value)
+ else:
+ url_or_request = sanitized_Request(url_or_request, headers=headers)
+
+ response = super(UdemyIE, self)._download_json(url_or_request, video_id, note)
self._handle_error(response)
return response
def _login(self):
(username, password) = self._get_login_info()
if username is None:
- raise ExtractorError(
- 'Udemy account is required, use --username and --password options to provide account credentials.',
- expected=True)
+ self.raise_login_required('Udemy account is required')
login_popup = self._download_webpage(
- 'https://www.udemy.com/join/login-popup?displayType=ajax&showSkipButton=1', None,
- 'Downloading login popup')
+ self._LOGIN_URL, None, 'Downloading login popup')
+
+ def is_logged(webpage):
+ return any(p in webpage for p in ['href="https://www.udemy.com/user/logout/', '>Logout<'])
- if login_popup == '<div class="run-command close-popup redirect" data-url="https://www.udemy.com/"></div>':
+ # already logged in
+ if is_logged(login_popup):
return
- csrf = self._html_search_regex(r'<input type="hidden" name="csrf" value="(.+?)"', login_popup, 'csrf token')
+ login_form = self._form_hidden_inputs('login-form', login_popup)
- login_form = {
- 'email': username,
- 'password': password,
- 'csrf': csrf,
- 'displayType': 'json',
- 'isSubmitted': '1',
- }
- request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
- response = self._download_json(request, None, 'Logging in as %s' % username)
+ login_form.update({
+ 'email': username.encode('utf-8'),
+ 'password': password.encode('utf-8'),
+ })
- if 'returnUrl' not in response:
+ request = sanitized_Request(
+ self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+ request.add_header('Referer', self._ORIGIN_URL)
+ request.add_header('Origin', self._ORIGIN_URL)
+
+ response = self._download_webpage(
+ request, None, 'Logging in as %s' % username)
+
+ if not is_logged(response):
+ error = self._html_search_regex(
+ r'(?s)<div[^>]+class="form-errors[^"]*">(.+?)</div>',
+ response, 'error message', default=None)
+ if error:
+ raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- lecture_id = mobj.group('id')
+ lecture_id = self._match_id(url)
lecture = self._download_json(
- 'https://www.udemy.com/api-1.1/lectures/%s' % lecture_id, lecture_id, 'Downloading lecture JSON')
+ 'https://www.udemy.com/api-1.1/lectures/%s' % lecture_id,
+ lecture_id, 'Downloading lecture JSON')
- if lecture['assetType'] != 'Video':
- raise ExtractorError('Lecture %s is not a video' % lecture_id, expected=True)
+ asset_type = lecture.get('assetType') or lecture.get('asset_type')
+ if asset_type != 'Video':
+ raise ExtractorError(
+ 'Lecture %s is not a video' % lecture_id, expected=True)
asset = lecture['asset']
- stream_url = asset['streamUrl']
+ stream_url = asset.get('streamUrl') or asset.get('stream_url')
mobj = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url)
if mobj:
return self.url_result(mobj.group(1), 'Youtube')
video_id = asset['id']
- thumbnail = asset['thumbnailUrl']
- duration = asset['data']['duration']
-
- download_url = asset['downloadUrl']
-
- formats = [
- {
- 'url': download_url['Video480p'][0],
- 'format_id': '360p',
- },
- {
- 'url': download_url['Video'][0],
- 'format_id': '720p',
- },
- ]
+ thumbnail = asset.get('thumbnailUrl') or asset.get('thumbnail_url')
+ duration = int_or_none(asset.get('data', {}).get('duration'))
+
+ download_url = asset.get('downloadUrl') or asset.get('download_url')
+
+ video = download_url.get('Video') or download_url.get('video')
+ video_480p = download_url.get('Video480p') or download_url.get('video_480p')
+
+ formats = [{
+ 'url': video_480p[0],
+ 'format_id': 'download-360p',
+ }, {
+ 'url': video[0],
+ 'format_id': 'download-720p',
+ }]
+
+ # Some videos also contain formats in asset['data']['outputs'] (e.g.
+ # https://www.udemy.com/ios9-swift/learn/#/lecture/3383208)
+ outputs = asset.get('data', {}).get('outputs')
+ if isinstance(outputs, dict):
+ for format_id, f in outputs.items():
+ video_url = f.get('url')
+ if video_url:
+ formats.append({
+ 'url': video_url,
+ 'format_id': '%sp' % (f.get('labe1l') or format_id),
+ 'width': int_or_none(f.get('width')),
+ 'height': int_or_none(f.get('height')),
+ 'vbr': int_or_none(f.get('video_bitrate_in_kbps')),
+ 'vcodec': f.get('video_codec'),
+ 'fps': int_or_none(f.get('frame_rate')),
+ 'abr': int_or_none(f.get('audio_bitrate_in_kbps')),
+ 'acodec': f.get('audio_codec'),
+ 'asr': int_or_none(f.get('audio_sample_rate')),
+ 'tbr': int_or_none(f.get('total_bitrate_in_kbps')),
+ 'filesize': int_or_none(f.get('file_size_in_bytes')),
+ })
+
+ self._sort_formats(formats)
title = lecture['title']
- description = lecture['description']
+ description = lecture.get('description')
return {
'id': video_id,
course_path = mobj.group('coursepath')
response = self._download_json(
- 'https://www.udemy.com/api-1.1/courses/%s' % course_path, course_path, 'Downloading course JSON')
+ 'https://www.udemy.com/api-1.1/courses/%s' % course_path,
+ course_path, 'Downloading course JSON')
course_id = int(response['id'])
course_title = response['title']
webpage = self._download_webpage(
- 'https://www.udemy.com/course/subscribe/?courseId=%s' % course_id, course_id, 'Enrolling in the course')
+ 'https://www.udemy.com/course/subscribe/?courseId=%s' % course_id,
+ 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)
- response = self._download_json('https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id,
- course_id, 'Downloading course curriculum')
+ 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') == 'Video'
+ 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'
]
return self.playlist_result(entries, course_id, course_title)
projects / youtube-dl / blobdiff