Imported Upstream version 2016.08.17

[youtubedl] / youtube_dl / extractor / pyvideo.py

diff --git a/youtube_dl/extractor/pyvideo.py b/youtube_dl/extractor/pyvideo.py
index 0bc0859b466e533419d5647d7f0250988d2f36db..cc0416cb81eb23ed87d1dae0cdf2573a6df8936a 100644 (file)
--- a/youtube_dl/extractor/pyvideo.py
+++ b/youtube_dl/extractor/pyvideo.py
@@ -7,19 +7,19 @@ from .common import InfoExtractor
 
 
 class PyvideoIE(InfoExtractor):
 
 
 class PyvideoIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
+    _VALID_URL = r'https?://(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'

 
     _TESTS = [
         {
             'url': 'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',
 
     _TESTS = [
         {
             'url': 'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',

-            'md5': 'de317418c8bc76b1fd8633e4f32acbc6',
+            'md5': '520915673e53a5c5d487c36e0c4d85b5',

             'info_dict': {
                 'id': '24_4WWkSmNo',
             'info_dict': {
                 'id': '24_4WWkSmNo',

-                'ext': 'mp4',
+                'ext': 'webm',

                 'title': 'Become a logging expert in 30 minutes',
                 'description': 'md5:9665350d466c67fb5b1598de379021f7',
                 'upload_date': '20130320',
                 'title': 'Become a logging expert in 30 minutes',
                 'description': 'md5:9665350d466c67fb5b1598de379021f7',
                 'upload_date': '20130320',

-                'uploader': 'NextDayVideo',
+                'uploader': 'Next Day Video',

                 'uploader_id': 'NextDayVideo',
             },
             'add_ie': ['Youtube'],
                 'uploader_id': 'NextDayVideo',
             },
             'add_ie': ['Youtube'],


@@ -46,7 +46,7 @@ class PyvideoIE(InfoExtractor):
             return self.url_result(m_youtube.group(1), 'Youtube')
 
         title = self._html_search_regex(
             return self.url_result(m_youtube.group(1), 'Youtube')
 
         title = self._html_search_regex(

-            r'<div class="section">.*?<h3(?:\s+class="[^"]*")?>([^>]+?)</h3>',
+            r'<div class="section">\s*<h3(?:\s+class="[^"]*"[^>]*)?>([^>]+?)</h3>',

             webpage, 'title', flags=re.DOTALL)
         video_url = self._search_regex(
             [r'<source src="(.*?)"', r'<dt>Download</dt>.*?<a href="(.+?)"'],
             webpage, 'title', flags=re.DOTALL)
         video_url = self._search_regex(
             [r'<source src="(.*?)"', r'<dt>Download</dt>.*?<a href="(.+?)"'],