[firstpost] Add extractor (Fixes #2324)
authorPhilipp Hagemeister <phihag@phihag.de>
Wed, 5 Feb 2014 20:22:53 +0000 (21:22 +0100)
committerPhilipp Hagemeister <phihag@phihag.de>
Wed, 5 Feb 2014 20:23:21 +0000 (21:23 +0100)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/firstpost.py [new file with mode: 0644]

index 803c37169951614051bf40c2339eb0facf26bcb7..30b993b45024484e388137cdd9f3f9da5a2fd1af 100644 (file)
@@ -60,6 +60,7 @@ from .exfm import ExfmIE
 from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
+from .firstpost import FirstpostIE
 from .fktv import (
     FKTVIE,
     FKTVPosteckeIE,
diff --git a/youtube_dl/extractor/firstpost.py b/youtube_dl/extractor/firstpost.py
new file mode 100644 (file)
index 0000000..7e3d1af
--- /dev/null
@@ -0,0 +1,38 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class FirstpostIE(InfoExtractor):
+    IE_NAME = 'Firstpost.com'
+    _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
+
+    _TEST = {
+        'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html',
+        'md5': 'ee9114957692f01fb1263ed87039112a',
+        'info_dict': {
+            'id': '1025403',
+            'ext': 'mp4',
+            'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
+            'description': 'Its flight deck is over twice the size of a football field, its power unit can light up the entire Kochi city and the cabling is enough to cover the distance between here to Delhi.',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        video_url = self._html_search_regex(
+            r'<div.*?name="div_video".*?flashvars="([^"]+)">',
+            webpage, 'video URL')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }