[youtube] Fix extraction.

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

diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py
index ba69739b2b104b60531c0363fd81347a812ebc9c..69a0d01f39c24f9fdcef0d31dd4d9d7a2f082c85 100644 (file)
--- a/youtube_dl/extractor/screencast.py
+++ b/youtube_dl/extractor/screencast.py
@@ -1,18 +1,18 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..compat import (
     compat_parse_qs,
     compat_urllib_request,
 )
+from ..utils import (
+    ExtractorError,
+)
 
 
 class ScreencastIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
     _TESTS = [{
         'url': 'http://www.screencast.com/t/3ZEjQXlT',
         'md5': '917df1c13798a3e96211dd1561fded83',
@@ -21,7 +21,7 @@ class ScreencastIE(InfoExtractor):
             'ext': 'm4v',
             'title': 'Color Measurement with Ocean Optics Spectrometers',
             'description': 'md5:240369cde69d8bed61349a199c5fb153',
-            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+            'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
         }
     }, {
         'url': 'http://www.screencast.com/t/V2uXehPJa1ZI',
@@ -31,7 +31,7 @@ class ScreencastIE(InfoExtractor):
             'ext': 'mov',
             'title': 'The Amadeus Spectrometer',
             'description': 're:^In this video, our friends at.*To learn more about Amadeus, visit',
-            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+            'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
         }
     }, {
         'url': 'http://www.screencast.com/t/aAB3iowa',
@@ -41,14 +41,25 @@ class ScreencastIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Google Earth Export',
             'description': 'Provides a demo of a CommunityViz export to Google Earth, one of the 3D viewing options.',
-            'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
+            'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
         }
-    },
-    ]
+    }, {
+        'url': 'http://www.screencast.com/t/X3ddTrYh',
+        'md5': '669ee55ff9c51988b4ebc0877cc8b159',
+        'info_dict': {
+            'id': 'X3ddTrYh',
+            'ext': 'wmv',
+            'title': 'Toolkit 6 User Group Webinar (2014-03-04) - Default Judgment and First Impression',
+            'description': 'md5:7b9f393bc92af02326a5c5889639eab0',
+            'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
+        }
+    }, {
+        'url': 'http://screencast.com/t/aAB3iowa',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._html_search_regex(
@@ -59,6 +70,12 @@ class ScreencastIE(InfoExtractor):
             flash_vars_s = self._html_search_regex(
                 r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars',
                 default=None)
+            if not flash_vars_s:
+                flash_vars_s = self._html_search_regex(
+                    r'<param name="initParams" value="([^"]+)"', webpage, 'flash vars',
+                    default=None)
+                if flash_vars_s:
+                    flash_vars_s = flash_vars_s.replace(',', '&')
             if flash_vars_s:
                 flash_vars = compat_parse_qs(flash_vars_s)
                 video_url_raw = compat_urllib_request.quote(
@@ -73,13 +90,24 @@ class ScreencastIE(InfoExtractor):
                     r'src=(.*?)(?:$|&)', video_meta,
                     'meta tag video URL', default=None)
 
+        if video_url is None:
+            video_url = self._html_search_regex(
+                r'MediaContentUrl["\']\s*:(["\'])(?P<url>(?:(?!\1).)+)\1',
+                webpage, 'video url', default=None, group='url')
+
+        if video_url is None:
+            video_url = self._html_search_meta(
+                'og:video', webpage, default=None)
+
         if video_url is None:
             raise ExtractorError('Cannot find video')
 
         title = self._og_search_title(webpage, default=None)
         if title is None:
             title = self._html_search_regex(
-                r'class="tabSeperator">></span><span class="tabText">(.*?)<',
+                [r'<b>Title:</b> ([^<]+)</div>',
+                 r'class="tabSeperator">></span><span class="tabText">(.+?)<',
+                 r'<title>([^<]+)</title>'],
                 webpage, 'title')
         thumbnail = self._og_search_thumbnail(webpage)
         description = self._og_search_description(webpage, default=None)