From 7445edba1b6976f10604a68806cdf0c431206487 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Wed, 28 Sep 2011 09:16:25 -0600
Subject: [PATCH] Fix Chicago Tribune multipage articles

---
 recipes/chicago_tribune.recipe | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/recipes/chicago_tribune.recipe b/recipes/chicago_tribune.recipe
index 8fa006b5da..6842dcff2a 100644
--- a/recipes/chicago_tribune.recipe
+++ b/recipes/chicago_tribune.recipe
@@ -8,21 +8,25 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class ChicagoTribune(BasicNewsRecipe):
 
     title       = 'Chicago Tribune'
-    __author__  = 'Kovid Goyal and Sujata Raman'
+    __author__  = 'Kovid Goyal and Sujata Raman, a.peter'
     description = 'Politics, local and business news from Chicago'
-    language = 'en'
+    language    = 'en'
+    version     = 2
 
-    use_embedded_content    = False
-    no_stylesheets        = True
-    remove_javascript = True
+    use_embedded_content = False
+    no_stylesheets       = True
+    remove_javascript    = True
+    recursions           = 1
 
     keep_only_tags = [dict(name='div', attrs={'class':["story","entry-asset asset hentry"]}),
                       dict(name='div', attrs={'id':["pagebody","story","maincontentcontainer"]}),
                            ]
-    remove_tags_after = [    {'class':['photo_article',]} ]
+    remove_tags_after = [{'class':['photo_article',]}]
 
-    remove_tags = [{'id':["moduleArticleTools","content-bottom","rail","articleRelates module","toolSet","relatedrailcontent","div-wrapper","beta","atp-comments","footer"]},
-                   {'class':["clearfix","relatedTitle","articleRelates module","asset-footer","tools","comments","featurePromo","featurePromo fp-topjobs brownBackground","clearfix fullSpan brownBackground","curvedContent"]},
+    match_regexps = [r'page=[0-9]+']
+
+    remove_tags = [{'id':["moduleArticleTools","content-bottom","rail","articleRelates module","toolSet","relatedrailcontent","div-wrapper","beta","atp-comments","footer",'gallery-subcontent','subFooter']},
+                   {'class':["clearfix","relatedTitle","articleRelates module","asset-footer","tools","comments","featurePromo","featurePromo fp-topjobs brownBackground","clearfix fullSpan brownBackground","curvedContent",'nextgen-share-tools','outbrainTools', 'google-ad-story-bottom']},
                    dict(name='font',attrs={'id':["cr-other-headlines"]})]
     extra_css = '''
                     h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
@@ -37,7 +41,7 @@ class ChicagoTribune(BasicNewsRecipe):
                     .maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                     .story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                     body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
-		'''
+                '''
     feeds = [
              ('Latest news', 'http://feeds.chicagotribune.com/chicagotribune/news/'),
              ('Local news', 'http://feeds.chicagotribune.com/chicagotribune/news/local/'),
@@ -76,8 +80,12 @@ class ChicagoTribune(BasicNewsRecipe):
         print article.get('feedburner_origlink', article.get('guid', article.get('link')))
         return article.get('feedburner_origlink', article.get('guid', article.get('link')))
 
-
     def postprocess_html(self, soup, first_fetch):
+        # Remove the navigation bar. It was kept until now to be able to follow
+        # the links to further pages. But now we don't need them anymore.
+        for nav in soup.findAll(attrs={'class':['toppaginate','article-nav clearfix']}):
+            nav.extract()
+
         for t in soup.findAll(['table', 'tr', 'td']):
             t.name = 'div'
 
@@ -88,4 +96,3 @@ class ChicagoTribune(BasicNewsRecipe):
 
         return soup
 
-