Add an extractor for southparkstudios.com (closes #1434)
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Sun, 15 Sep 2013 21:30:58 +0000 (23:30 +0200)
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Sun, 15 Sep 2013 21:30:58 +0000 (23:30 +0200)
It uses the MTV system

youtube_dl/extractor/__init__.py
youtube_dl/extractor/southparkstudios.py [new file with mode: 0644]

index 19d57c2e9f77bcbb02381acf965f6855139b1504..246f1e8b56c85d08731c001fd9b0fb57b2d99b4f 100644 (file)
@@ -83,6 +83,7 @@ from .slashdot import SlashdotIE
 from .slideshare import SlideshareIE
 from .sohu import SohuIE
 from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
+from .southparkstudios import SouthParkStudiosIE
 from .spiegel import SpiegelIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .statigram import StatigramIE
diff --git a/youtube_dl/extractor/southparkstudios.py b/youtube_dl/extractor/southparkstudios.py
new file mode 100644 (file)
index 0000000..a5dc754
--- /dev/null
@@ -0,0 +1,34 @@
+import re
+
+from .mtv import MTVIE, _media_xml_tag
+
+
+class SouthParkStudiosIE(MTVIE):
+    IE_NAME = u'southparkstudios.com'
+    _VALID_URL = r'https?://www\.southparkstudios\.com/clips/(?P<id>\d+)'
+
+    _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
+
+    _TEST = {
+        u'url': u'http://www.southparkstudios.com/clips/104437/bat-daded#tab=featured',
+        u'file': u'a7bff6c2-ed00-11e0-aca6-0026b9414f30.mp4',
+        u'info_dict': {
+            u'title': u'Bat Daded',
+            u'description': u'Randy disqualifies South Park by getting into a fight with Bat Dad.',
+        },
+    }
+
+    # Overwrite MTVIE properties we don't want
+    _TESTS = []
+
+    def _get_thumbnail_url(self, uri, itemdoc):
+        search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
+        return itemdoc.find(search_path).attrib['url']
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        mgid = self._search_regex(r'swfobject.embedSWF\(".*?(mgid:.*?)"',
+                                  webpage, u'mgid')
+        return self._get_videos_info(mgid)