[FIX] link_tracker: page title encoding

When tracking a page with special characters
in the title (e.g. `Ä`), the title
of the page in the tracked links was
badly encoded, because the
encoding was not handled correctly
when parsing the given website page.

opw-679993

1 files changed, 3 insertions, 2 deletions

diff --git a/addons/link_tracker/models/link_tracker.py b/addons/link_tracker/models/link_tracker.py
index f387a7e6e7f..4de629fc517 100644
--- a/addons/link_tracker/models/link_tracker.py
+++ b/addons/link_tracker/models/link_tracker.py
@@ -4,13 +4,14 @@ import random
 import re
 import string
 
-from lxml.html import parse
+from lxml import html
 from urllib2 import urlopen
 from urlparse import urljoin
 from urlparse import urlparse
 from werkzeug import url_encode
 
 from openerp import models, fields, api, _
+from openerp.tools import ustr
 
 URL_REGEX = r'(\bhref=[\'"](?!mailto:)([^\'"]+)[\'"])'
 
@@ -108,7 +109,7 @@ class link_tracker(models.Model):
     def _get_title_from_url(self, url):
         try:
             page = urlopen(url, timeout=5)
-            p = parse(page)
+            p = html.fromstring(ustr(page.read()).encode('utf-8'), parser=html.HTMLParser(encoding='utf-8'))
             title = p.find('.//title').text
         except:
             title = url