[youtube] Fix extraction.

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

diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py
index 89a7f6adefb55652f09e25ced2f163341309c717..2a4faecefbc271f1f88dfe38d2fe284e0bbd9158 100644 (file)
--- a/youtube_dl/extractor/udemy.py
+++ b/youtube_dl/extractor/udemy.py
@@ -29,7 +29,7 @@ class UdemyIE(InfoExtractor):
     IE_NAME = 'udemy'
     _VALID_URL = r'''(?x)
                     https?://
-                        www\.udemy\.com/
+                        (?:[^/]+\.)?udemy\.com/
                         (?:
                             [^#]+\#/lecture/|
                             lecture/view/?\?lectureId=|
@@ -64,6 +64,9 @@ class UdemyIE(InfoExtractor):
         # only outputs rendition
         'url': 'https://www.udemy.com/how-you-can-help-your-local-community-5-amazing-examples/learn/v4/t/lecture/3225750?start=0',
         'only_matching': True,
+    }, {
+        'url': 'https://wipro.udemy.com/java-tutorial/#/lecture/172757',
+        'only_matching': True,
     }]
 
     def _extract_course_info(self, webpage, video_id):
@@ -73,7 +76,10 @@ class UdemyIE(InfoExtractor):
                 webpage, 'course', default='{}')),
             video_id, fatal=False) or {}
         course_id = course.get('id') or self._search_regex(
-            r'data-course-id=["\'](\d+)', webpage, 'course id')
+            [
+                r'data-course-id=["\'](\d+)',
+                r'"courseId"\s*:\s*(\d+)'
+            ], webpage, 'course id')
         return course_id, course.get('title')
 
     def _enroll_course(self, base_url, webpage, course_id):
@@ -372,7 +378,7 @@ class UdemyIE(InfoExtractor):
                     }, res))
 
             # react rendition since 2017.04.15 (see
-            # https://github.com/rg3/youtube-dl/issues/12744)
+            # https://github.com/ytdl-org/youtube-dl/issues/12744)
             data = self._parse_json(
                 self._search_regex(
                     r'videojs-setup-data=(["\'])(?P<data>{.+?})\1', view_html,
@@ -415,8 +421,14 @@ class UdemyIE(InfoExtractor):
 
 class UdemyCourseIE(UdemyIE):
     IE_NAME = 'udemy:course'
-    _VALID_URL = r'https?://(?:www\.)?udemy\.com/(?P<id>[^/?#&]+)'
-    _TESTS = []
+    _VALID_URL = r'https?://(?:[^/]+\.)?udemy\.com/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.udemy.com/java-tutorial/',
+        'only_matching': True,
+    }, {
+        'url': 'https://wipro.udemy.com/java-tutorial/',
+        'only_matching': True,
+    }]
 
     @classmethod
     def suitable(cls, url):