screencast.com: support missing www

[youtube-dl] / youtube_dl / extractor / udemy.py

diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py
index 2e54dbc1129daacabe5b53ea46a8fd33cb1dd7a8..d1e6f2703e022dac0edc3ef0f16794a6285d2b8f 100644 (file)
--- a/youtube_dl/extractor/udemy.py
+++ b/youtube_dl/extractor/udemy.py
@@ -17,7 +17,6 @@ from ..utils import (
     int_or_none,
     sanitized_Request,
     unescapeHTML,
-    update_url_query,
     urlencode_postdata,
 )
 
@@ -152,8 +151,8 @@ class UdemyIE(InfoExtractor):
         login_form = self._form_hidden_inputs('login-form', login_popup)
 
         login_form.update({
-            'email': username.encode('utf-8'),
-            'password': password.encode('utf-8'),
+            'email': username,
+            'password': password,
         })
 
         request = sanitized_Request(
@@ -194,12 +193,12 @@ class UdemyIE(InfoExtractor):
 
         asset = lecture['asset']
 
-        asset_type = asset.get('assetType') or asset.get('asset_type')
+        asset_type = asset.get('asset_type') or asset.get('assetType')
         if asset_type != 'Video':
             raise ExtractorError(
                 'Lecture %s is not a video' % lecture_id, expected=True)
 
-        stream_url = asset.get('streamUrl') or asset.get('stream_url')
+        stream_url = asset.get('stream_url') or asset.get('streamUrl')
         if stream_url:
             youtube_url = self._search_regex(
                 r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url, 'youtube URL', default=None)
@@ -207,7 +206,7 @@ class UdemyIE(InfoExtractor):
                 return self.url_result(youtube_url, 'Youtube')
 
         video_id = asset['id']
-        thumbnail = asset.get('thumbnailUrl') or asset.get('thumbnail_url')
+        thumbnail = asset.get('thumbnail_url') or asset.get('thumbnailUrl')
         duration = float_or_none(asset.get('data', {}).get('duration'))
 
         formats = []
@@ -306,7 +305,7 @@ class UdemyIE(InfoExtractor):
 
 class UdemyCourseIE(UdemyIE):
     IE_NAME = 'udemy:course'
-    _VALID_URL = r'https?://www\.udemy\.com/(?P<id>[\da-z-]+)'
+    _VALID_URL = r'https?://www\.udemy\.com/(?P<id>[^/?#&]+)'
     _TESTS = []
 
     @classmethod
@@ -322,27 +321,29 @@ class UdemyCourseIE(UdemyIE):
 
         self._enroll_course(url, webpage, course_id)
 
-        course_url = update_url_query(
+        response = self._download_json(
             'https://www.udemy.com/api-2.0/courses/%s/cached-subscriber-curriculum-items' % course_id,
-            {
+            course_id, 'Downloading course curriculum', query={
                 'fields[chapter]': 'title,object_index',
-                'fields[lecture]': 'title',
+                'fields[lecture]': 'title,asset',
                 'page_size': '1000',
             })
 
-        response = self._download_json(
-            course_url, course_id, 'Downloading course curriculum')
-
         entries = []
         chapter, chapter_number = [None] * 2
         for entry in response['results']:
             clazz = entry.get('_class')
             if clazz == 'lecture':
+                asset = entry.get('asset')
+                if isinstance(asset, dict):
+                    asset_type = asset.get('asset_type') or asset.get('assetType')
+                    if asset_type != 'Video':
+                        continue
                 lecture_id = entry.get('id')
                 if lecture_id:
                     entry = {
                         '_type': 'url_transparent',
-                        'url': 'https://www.udemy.com/%s/#/lecture/%s' % (course_path, entry['id']),
+                        'url': 'https://www.udemy.com/%s/learn/v4/t/lecture/%s' % (course_path, entry['id']),
                         'title': entry.get('title'),
                         'ie_key': UdemyIE.ie_key(),
                     }