debian/control: Remove trailing whitespace at EOF.

[youtubedl] / youtube_dl / extractor / lynda.py

diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py
index f4dcfd93fa760878566568636d9c2b864b6c7556..f5c7abc13eb431605355c080ade55da197fc04e3 100644 (file)
--- a/youtube_dl/extractor/lynda.py
+++ b/youtube_dl/extractor/lynda.py
@@ -73,7 +73,7 @@ class LyndaBaseIE(InfoExtractor):
 
         # Already logged in
         if any(re.search(p, signin_page) for p in (
 
         # Already logged in
         if any(re.search(p, signin_page) for p in (

-                'isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')):
+                r'isLoggedIn\s*:\s*true', r'logout\.aspx', r'>Log out<')):

             return
 
         # Step 2: submit email
             return
 
         # Step 2: submit email


@@ -94,7 +94,15 @@ class LyndaBaseIE(InfoExtractor):
 class LyndaIE(LyndaBaseIE):
     IE_NAME = 'lynda'
     IE_DESC = 'lynda.com videos'
 class LyndaIE(LyndaBaseIE):
     IE_NAME = 'lynda'
     IE_DESC = 'lynda.com videos'

-    _VALID_URL = r'https?://(?:www\.)?lynda\.com/(?:[^/]+/[^/]+/(?P<course_id>\d+)|player/embed)/(?P<id>\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?(?:lynda\.com|educourse\.ga)/
+                        (?:
+                            (?:[^/]+/){2,3}(?P<course_id>\d+)|
+                            player/embed
+                        )/
+                        (?P<id>\d+)
+                    '''

 
     _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
 
 
     _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
 


@@ -110,6 +118,12 @@ class LyndaIE(LyndaBaseIE):
     }, {
         'url': 'https://www.lynda.com/player/embed/133770?tr=foo=1;bar=g;fizz=rt&fs=0',
         'only_matching': True,
     }, {
         'url': 'https://www.lynda.com/player/embed/133770?tr=foo=1;bar=g;fizz=rt&fs=0',
         'only_matching': True,

+    }, {
+        'url': 'https://educourse.ga/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Willkommen-Grundlagen-guten-Gestaltung/393570/393572-4.html',
+        'only_matching': True,

     }]
 
     def _raise_unavailable(self, video_id):
     }]
 
     def _raise_unavailable(self, video_id):


@@ -241,8 +255,9 @@ class LyndaIE(LyndaBaseIE):
     def _get_subtitles(self, video_id):
         url = 'https://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
         subs = self._download_json(url, None, False)
     def _get_subtitles(self, video_id):
         url = 'https://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
         subs = self._download_json(url, None, False)

-        if subs:
-            return {'en': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]}
+        fixed_subs = self._fix_subtitles(subs)
+        if fixed_subs:
+            return {'en': [{'ext': 'srt', 'data': fixed_subs}]}

         else:
             return {}
 
         else:
             return {}
 


@@ -253,16 +268,39 @@ class LyndaCourseIE(LyndaBaseIE):
 
     # Course link equals to welcome/introduction video link of same course
     # We will recognize it as course link
 
     # Course link equals to welcome/introduction video link of same course
     # We will recognize it as course link

-    _VALID_URL = r'https?://(?:www|m)\.lynda\.com/(?P<coursepath>[^/]+/[^/]+/(?P<courseid>\d+))-\d\.html'
+    _VALID_URL = r'https?://(?:www|m)\.(?:lynda\.com|educourse\.ga)/(?P<coursepath>(?:[^/]+/){2,3}(?P<courseid>\d+))-2\.html'
+
+    _TESTS = [{
+        'url': 'https://www.lynda.com/Graphic-Design-tutorials/Grundlagen-guten-Gestaltung/393570-2.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Grundlagen-guten-Gestaltung/393570-2.html',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         course_path = mobj.group('coursepath')
         course_id = mobj.group('courseid')
 
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         course_path = mobj.group('coursepath')
         course_id = mobj.group('courseid')
 

+        item_template = 'https://www.lynda.com/%s/%%s-4.html' % course_path
+

         course = self._download_json(
             'https://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
         course = self._download_json(
             'https://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,

-            course_id, 'Downloading course JSON')
+            course_id, 'Downloading course JSON', fatal=False)
+
+        if not course:
+            webpage = self._download_webpage(url, course_id)
+            entries = [
+                self.url_result(
+                    item_template % video_id, ie=LyndaIE.ie_key(),
+                    video_id=video_id)
+                for video_id in re.findall(
+                    r'data-video-id=["\'](\d+)', webpage)]
+            return self.playlist_result(
+                entries, course_id,
+                self._og_search_title(webpage, fatal=False),
+                self._og_search_description(webpage))

 
         if course.get('Status') == 'NotFound':
             raise ExtractorError(
 
         if course.get('Status') == 'NotFound':
             raise ExtractorError(


@@ -283,7 +321,7 @@ class LyndaCourseIE(LyndaBaseIE):
                 if video_id:
                     entries.append({
                         '_type': 'url_transparent',
                 if video_id:
                     entries.append({
                         '_type': 'url_transparent',

-                        'url': 'https://www.lynda.com/%s/%s-4.html' % (course_path, video_id),
+                        'url': item_template % video_id,

                         'ie_key': LyndaIE.ie_key(),
                         'chapter': chapter.get('Title'),
                         'chapter_number': int_or_none(chapter.get('ChapterIndex')),
                         'ie_key': LyndaIE.ie_key(),
                         'chapter': chapter.get('Title'),
                         'chapter_number': int_or_none(chapter.get('ChapterIndex')),