[videolecturesnet] Add playlist test

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

diff --git a/youtube_dl/extractor/videolecturesnet.py b/youtube_dl/extractor/videolecturesnet.py
index 160dbb5900f084bf44e8decde68b9d5b1e27ec2a..113a2289bb395a6be5da831a349b1b27c6fb4be2 100644 (file)
--- a/youtube_dl/extractor/videolecturesnet.py
+++ b/youtube_dl/extractor/videolecturesnet.py
@@ -1,7 +1,14 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..compat import (
+    compat_HTTPError,
+    compat_urlparse,
+)
 from ..utils import (
+    ExtractorError,
     parse_duration,
 )
 
@@ -10,7 +17,7 @@ class VideoLecturesNetIE(InfoExtractor):
     _VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/#?]+)/*(?:[#?].*)?$'
     IE_NAME = 'videolectures.net'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
         'info_dict': {
             'id': 'promogram_igor_mekjavic_eng',
@@ -21,13 +28,33 @@ class VideoLecturesNetIE(InfoExtractor):
             'duration': 565,
             'thumbnail': 're:http://.*\.jpg',
         },
-    }
+    }, {
+        'url': 'http://videolectures.net/deeplearning2015_montreal/',
+        'info_dict': {
+            'id': 'deeplearning2015_montreal',
+            'title': 'Deep Learning Summer School, Montreal 2015',
+            'description': 'md5:90121a40cc6926df1bf04dcd8563ed3b',
+        },
+        'playlist_count': 30,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id
-        smil = self._download_smil(smil_url, video_id)
+
+        try:
+            smil = self._download_smil(smil_url, video_id)
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
+                # Probably a playlist
+                webpage = self._download_webpage(url, video_id)
+                entries = [
+                    self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet')
+                    for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)]
+                playlist_title = self._html_search_meta('title', webpage, 'title', fatal=True)
+                playlist_description = self._html_search_meta('description', webpage, 'description')
+                return self.playlist_result(entries, video_id, playlist_title, playlist_description)
 
         info = self._parse_smil(smil, smil_url, video_id)