From f666c4f61dd034a83b1dc86392a8b8132cd7520e Mon Sep 17 00:00:00 2001
From: j <0x006A@0x2620.org>
Date: Sat, 16 Jun 2007 16:10:34 +0000
Subject: [PATCH] lets try utf-8

---
 scrapeit/imdb.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/scrapeit/imdb.py b/scrapeit/imdb.py
index 7d9a376..5f83ad7 100644
--- a/scrapeit/imdb.py
+++ b/scrapeit/imdb.py
@@ -98,11 +98,12 @@ class IMDb:
     
   def getPage(self, forcereload = False):
     if forcereload or not self.pageSource:
-      self.pageSource = read_url(self.pageUrl)
+      self.pageSource = read_url_utf8(self.pageUrl)
     return self.pageSource
 
   def parse_raw_value(self, key, value):
     if key in ('runtime', 'language', 'genre', 'country', 'tagline', 'plot_outline'):
+      value = unicode(value, 'utf-8')
       value = stripTags(value).strip()    
     if key == 'runtime':
       parsed_value = _getTerm(value, '(.*?) min')