Add an extractor for NBC news (closes #1320)
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Tue, 27 Aug 2013 10:38:30 +0000 (12:38 +0200)
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Tue, 27 Aug 2013 10:38:57 +0000 (12:38 +0200)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/nbc.py [new file with mode: 0644]

index ea2af0d0e67ece4f4b7eb80ead7b2b4b32502cc3..27bbcc0f7df65a5e4578e73935be6ab0a0fadce8 100644 (file)
@@ -54,6 +54,7 @@ from .muzu import MuzuTVIE
 from .myspass import MySpassIE
 from .myvideo import MyVideoIE
 from .nba import NBAIE
+from .nbc import NBCNewsIE
 from .ooyala import OoyalaIE
 from .pbs import PBSIE
 from .photobucket import PhotobucketIE
diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py
new file mode 100644 (file)
index 0000000..3bc9dae
--- /dev/null
@@ -0,0 +1,33 @@
+import re
+import xml.etree.ElementTree
+
+from .common import InfoExtractor
+from ..utils import find_xpath_attr, compat_str
+
+
+class NBCNewsIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://www.nbcnews.com/video/nbc-news/52753292',
+        u'file': u'52753292.flv',
+        u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179',
+        u'info_dict': {
+            u'title': u'Crew emerges after four-month Mars food study',
+            u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        info_xml = self._download_webpage('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
+        info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')).find('video')
+
+        return {'id': video_id,
+                'title': info.find('headline').text,
+                'ext': 'flv',
+                'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
+                'description': compat_str(info.find('caption').text),
+                'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
+                }