From 152738b691092e3ea3ecaac9374ca47d4da7dbc0 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sun, 29 Nov 2009 13:25:11 -0700
Subject: [PATCH] Fix #4032 (NYT wont complete)

---
 resources/recipes/irish_independent.recipe | 6 +++---
 resources/recipes/nytimes.recipe           | 2 +-
 resources/recipes/nytimes_sub.recipe       | 5 ++++-
 src/calibre/ebooks/oeb/base.py             | 3 ++-
 4 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/resources/recipes/irish_independent.recipe b/resources/recipes/irish_independent.recipe
index 268b25b381..e4a98e999d 100644
--- a/resources/recipes/irish_independent.recipe
+++ b/resources/recipes/irish_independent.recipe
@@ -1,6 +1,6 @@
 __license__   = 'GPL v3'
 __copyright__ = '2009 Neil Grogan'
-# 
+#
 # Irish Independent Recipe
 #
 
@@ -10,7 +10,7 @@ class IrishIndependent(BasicNewsRecipe):
     title          = u'Irish Independent'
     description = 'Irish and World news from Irelands Bestselling Daily Broadsheet'
     __author__	= 'Neil Grogan'
-    language = 'en_UK'
+    language = 'en_GB'
     oldest_article = 7
     max_articles_per_feed = 100
     remove_tags_before = dict(id='article')
@@ -37,7 +37,7 @@ class IrishIndependent(BasicNewsRecipe):
     (u'Letters', u'http://www.independent.ie/opinion/letters/rss'),
     (u'Weather', u'http://www.independent.ie/weather/rss')
     ]
-    
+
 # If text only articles are desired
 #def print_version(self, url):
 #    return '%s?service=Print' % url
diff --git a/resources/recipes/nytimes.recipe b/resources/recipes/nytimes.recipe
index 89d5656741..26ecf895ef 100644
--- a/resources/recipes/nytimes.recipe
+++ b/resources/recipes/nytimes.recipe
@@ -14,7 +14,7 @@ class NYTimes(BasicNewsRecipe):
 
     title       = 'New York Times Top Stories'
     __author__  = 'GRiker'
-    language = _('English')
+    language = 'en'
     description = 'Top Stories from the New York Times'
 
     # List of sections typically included in Top Stories.  Use a keyword from the
diff --git a/resources/recipes/nytimes_sub.recipe b/resources/recipes/nytimes_sub.recipe
index a2c805c299..a6e903f6dd 100644
--- a/resources/recipes/nytimes_sub.recipe
+++ b/resources/recipes/nytimes_sub.recipe
@@ -22,7 +22,10 @@ class NYTimes(BasicNewsRecipe):
     remove_tags_before = dict(id='article')
     remove_tags_after  = dict(id='article')
     remove_tags = [dict(attrs={'class':['articleTools', 'post-tools', 'side_tool', 'nextArticleLink clearfix']}),
-                   dict(id=['footer', 'toolsRight', 'articleInline', 'navigation', 'archive', 'side_search', 'blog_sidebar', 'side_tool', 'side_index']),
+                   dict(id=['footer', 'toolsRight', 'articleInline',
+                       'navigation', 'archive', 'side_search', 'blog_sidebar',
+                       'side_tool', 'side_index',
+                       'relatedArticles', 'relatedTopics', 'adxSponLink']),
                    dict(name=['script', 'noscript', 'style'])]
     encoding = 'cp1252'
     no_stylesheets = True
diff --git a/src/calibre/ebooks/oeb/base.py b/src/calibre/ebooks/oeb/base.py
index 77cef0d22c..05d4cbb256 100644
--- a/src/calibre/ebooks/oeb/base.py
+++ b/src/calibre/ebooks/oeb/base.py
@@ -849,7 +849,8 @@ class Manifest(object):
                 try:
                     data = etree.fromstring(data)
                 except:
-                    data=data.replace(':=', '=').replace(':>', '>')
+                    data = data.replace(':=', '=').replace(':>', '>')
+                    data = data.replace('<http:/>', '')
                     try:
                         data = etree.fromstring(data)
                     except etree.XMLSyntaxError: