]> git.bitcoin.ninja Git - youtube-dl/commitdiff
added an IE for Ehow videos
authorM.Yasoob Khalid <yasoob.khld@gmail.com>
Thu, 11 Jul 2013 09:25:14 +0000 (14:25 +0500)
committerM.Yasoob Khalid <yasoob.khld@gmail.com>
Thu, 11 Jul 2013 09:25:14 +0000 (14:25 +0500)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/ehow.py [new file with mode: 0644]

index e111df6f73205374e84a1c880b1083049757f8fd..d2a71a6f10d9aa6125348d722064ccf7fc89ce92 100644 (file)
@@ -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
new file mode 100644 (file)
index 0000000..1844d8b
--- /dev/null
@@ -0,0 +1,42 @@
+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.break.com/video/when-girls-act-like-guys-2468056',
+        u'file': u'2468056.mp4',
+        u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b',
+        u'info_dict': {
+            u"title": u"When Girls Act Like D-Bags"
+        }
+    }
+
+    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,
+        }]
+