Hyperlink class now parses out the domain as well

palewire · Jul 17, 2014 · 02b1b25 · 02b1b25
1 parent 7ff3fc3
commit 02b1b25
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 0 deletions.
diff --git a/storytracker/analysis.py b/storytracker/analysis.py
@@ -6,6 +6,10 @@
 from six import BytesIO
 from bs4 import BeautifulSoup
 from .toolbox import UnicodeMixin
+try:
+    from urlparse import urlparse
+except ImportError:
+    from six.moves.urllib.parse import urlparse
 
 
 class ArchivedURL(UnicodeMixin):
@@ -160,6 +164,7 @@ class Hyperlink(UnicodeMixin):
     def __init__(self, href, contents):
         self.href = href
         self.contents = contents
+        self.domain = urlparse(href).netloc
 
     def __unicode__(self):
         return six.text_type(self.href)
diff --git a/test.py b/test.py
@@ -119,6 +119,7 @@ def test_url_hyperlinks(self):
         a = obj.hyperlinks[0]
         a.href
         a.contents
+        a.domain
         a.__unicode__()
         a.__str__()
         a.__repr__()