Merge remote-tracking branch 'malept/tds-extended-interviews'

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

diff --git a/youtube_dl/extractor/pyvideo.py b/youtube_dl/extractor/pyvideo.py
index 5c47993e7844ee4c46f2e3a3db7d40e7670b5fc7..33054591b755b383eb0d216623b99d308073c64d 100644 (file)
--- a/youtube_dl/extractor/pyvideo.py
+++ b/youtube_dl/extractor/pyvideo.py
@@ -1,25 +1,51 @@
 import re
+import os
 
 from .common import InfoExtractor
-from ..utils import determine_ext
 
 
 class PyvideoIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?pyvideo\.org/video/(\d+)/(.*)'
-    _TEST = {
+    _VALID_URL = r'(?:http://)?(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
+    _TESTS = [{
         u'url': u'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',
-        u'file': u'Become a logging expert in 30 minutes-24_4WWkSmNo.mp4',
-        u'md5': u'bf08cae24e1601027f98ae1262c299ad',
+        u'file': u'24_4WWkSmNo.mp4',
+        u'md5': u'de317418c8bc76b1fd8633e4f32acbc6',
         u'info_dict': {
-            u"title": u"Become a logging expert in 30 minutes"
-        }
-    }
+            u"title": u"Become a logging expert in 30 minutes",
+            u"description": u"md5:9665350d466c67fb5b1598de379021f7",
+            u"upload_date": u"20130320",
+            u"uploader": u"NextDayVideo",
+            u"uploader_id": u"NextDayVideo",
+        },
+        u'add_ie': ['Youtube'],
+    },
+    {
+        u'url': u'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v',
+        u'md5': u'5fe1c7e0a8aa5570330784c847ff6d12',
+        u'info_dict': {
+            u'id': u'2542',
+            u'ext': u'm4v',
+            u'title': u'Gloriajw-SpotifyWithErikBernhardsson182',
+        },
+    },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(2)
+        video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage)
 
         if m_youtube is not None:
             return self.url_result(m_youtube.group(1), 'Youtube')
+
+        title = self._html_search_regex(r'<div class="section">.*?<h3>([^>]+?)</h3>',
+            webpage, u'title', flags=re.DOTALL)
+        video_url = self._search_regex([r'<source src="(.*?)"',
+            r'<dt>Download</dt>.*?<a href="(.+?)"'],
+            webpage, u'video url', flags=re.DOTALL)
+        return {
+            'id': video_id,
+            'title': os.path.splitext(title)[0],
+            'url': video_url,
+        }