youtube-dl

commit 3fa95508373bb5813099c2e4ccad95638a506916
parent 117adb0f0f14766189b3e2f635462990637d1274
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Thu, 11 Jul 2013 12:02:16 +0200

Merge remote-tracking branch 'yasoob/master'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/ehow.py
 | 
44
++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 45 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -13,6 +13,7 @@ from .dailymotion import DailymotionIE
 from .depositfiles import DepositFilesIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
+from .ehow import EhowIE
 from .eighttracks import EightTracksIE
 from .escapist import EscapistIE
 from .facebook import FacebookIE
diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py
@@ -0,0 +1,44 @@
+import re
+from ..utils import compat_urllib_parse
+from .common import InfoExtractor
+
+
+class EhowIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?ehow\.com/([^/]+)'
+    _TEST = {
+        u'url': u'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
+        u'file': u'12245069.flv',
+        u'md5': u'9809b4e3f115ae2088440bcb4efbf371',
+        u'info_dict': {
+            u"title": u"Hardwood Flooring Basics",
+            u"description": u"Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...",
+   			u"uploader": u"Erick Nathan"
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1).split("_")[1]
+        webpage = self._download_webpage(url, video_id)
+        video_url = self._search_regex(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)',
+            webpage, u'video URL')
+        final_url = compat_urllib_parse.unquote(video_url)        
+        thumbnail_url = self._search_regex(r'<meta property="og:image" content="(.+?)" />',
+            webpage, u'thumbnail URL')
+        uploader = self._search_regex(r'<meta name="uploader" content="(.+?)" />',
+            webpage, u'uploader')
+        title = self._search_regex(r'<meta property="og:title" content="(.+?)" />',
+            webpage, u'Video title').replace(' | eHow','')
+        description = self._search_regex(r'<meta property="og:description" content="(.+?)" />',
+            webpage, u'video description')
+        ext = final_url.split('.')[-1]
+        return [{
+            'id':          video_id,
+            'url':         final_url,
+            'ext':         ext,
+            'title':       title,
+            'thumbnail':   thumbnail_url,
+            'description': description,
+            'uploader':    uploader,
+        }]
+