Merge lp:~stefanor/ibid/url-memory-454768 into lp:~ibid-core/ibid/old-trunk-pack-0.92

[Stefano Rivera]

[Michael Gorven (mgorven)]

On Sunday 18 October 2009 18:55:20 Stefano Rivera wrote:
> +class ContetTypeException(Exception):

Er, is there a reason that's "contet" and not "content"?

[lp:~stefanor/ibid/url-memory-454768]

762. By Stefano Rivera on 2009-10-19

Typo

[Stefano Rivera (stefanor)]

> Er, is there a reason that's "contet" and not "content"?

Twice?! Grrr.

Fixed

[Jonathan Hitchcock (vhata)]

review: Approve

[Michael Gorven (mgorven)]

 review approve

review: Approve

=== modified file 'ibid/plugins/url.py'
--- ibid/plugins/url.py	2009-09-02 06:43:05 +0000
+++ ibid/plugins/url.py	2009-10-19 08:24:13 +0000
@@ -1,7 +1,8 @@
 from datetime import datetime
 from httplib import BadStatusLine
 from urllib import urlencode
-from urllib2 import urlopen, HTTPRedirectHandler, build_opener, HTTPError, HTTPBasicAuthHandler, install_opener
+from urllib2 import urlopen, HTTPRedirectHandler, build_opener, HTTPError, \
+    HTTPBasicAuthHandler, install_opener
 import logging
 import re
 
@@ -44,7 +45,10 @@
         "Posts a URL to delicious.com"
 
         date = datetime.utcnow()
-        title = self._get_title(url)
+        try:
+            title = self._get_title(url)
+        except HTTPError:
+            return
 
         con_re = re.compile(r'!n=|!')
         connection_body = con_re.split(event.sender['connection'])
@@ -74,7 +78,7 @@
             'extended' : event.message['raw'],
             }
 
-        self._set_auth(username,password)
+        self._set_auth(username, password)
         posturl = 'https://api.del.icio.us/v1/posts/add?' + urlencode(data, 'utf-8')
 
         try:
@@ -94,6 +98,8 @@
             etree = get_html_parse_tree(url, None, headers, 'etree')
             title = etree.findtext('head/title')
             return title
+        except HTTPError, e:
+            raise
         except Exception, e:
             log.debug(u"Error determining title for %s: %s", url, unicode(e))
             return url

=== modified file 'ibid/utils.py'
--- ibid/utils.py	2009-10-16 16:31:34 +0000
+++ ibid/utils.py	2009-10-19 08:24:13 +0000
@@ -166,11 +166,19 @@
 
     return unicode(timestamp.strftime(format.encode('utf8')), 'utf8')
 
+class ContentTypeException(Exception):
+    pass
+
 def get_html_parse_tree(url, data=None, headers={}, treetype='beautifulsoup'):
     "Request a URL, parse with html5lib, and return a parse tree from it"
 
     req = urllib2.Request(url, data, headers)
     f = urllib2.urlopen(req)
+
+    if f.info().gettype() not in ('text/html', 'application/xhtml+xml'):
+        f.close()
+        raise ContentTypeException("Content type isn't HTML, but " + f.info().gettype())
+
     data = f.read()
     f.close()