X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvideolecturesnet.py;h=649ac9433f3ec93458d3fe445b752cebccb5f333;hb=e3e166d8cfa2be039b320d0c733b8233e95d3dcf;hp=eadff8d180034f407cea190a9e5f51aea72f3c8a;hpb=0c996b9f488bfaa74d79e94739af80a0be38e125;p=youtube-dl

diff --git a/youtube_dl/extractor/videolecturesnet.py b/youtube_dl/extractor/videolecturesnet.py
index eadff8d18..649ac9433 100644
--- a/youtube_dl/extractor/videolecturesnet.py
+++ b/youtube_dl/extractor/videolecturesnet.py
@@ -3,15 +3,21 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
-from ..utils import parse_duration
+from ..compat import (
+    compat_HTTPError,
+    compat_urlparse,
+)
+from ..utils import (
+    ExtractorError,
+    parse_duration,
+)
 
 
 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',
@@ -22,23 +28,48 @@ class VideoLecturesNetIE(InfoExtractor):
             'duration': 565,
             'thumbnail': 're:http://.*\.jpg',
         },
-    }
+    }, {
+        # video with invalid direct format links (HTTP 403)
+        'url': 'http://videolectures.net/russir2010_filippova_nlp/',
+        'info_dict': {
+            'id': 'russir2010_filippova_nlp',
+            'ext': 'flv',
+            'title': 'NLP at Google',
+            'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3',
+            'duration': 5352,
+            'thumbnail': 're:http://.*\.jpg',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }, {
+        '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, fatal=False)
-
-        # Probably a playlist
-        if smil is False:
-            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)
+
+        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)