From 517a3e397575cd34fc77046a79e8d3f29d025ee5 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sun, 20 Mar 2011 11:18:18 -0600
Subject: [PATCH] Fix Washington Post

---
 recipes/wash_post.recipe | 68 ++++++++++++++++++----------------------
 1 file changed, 30 insertions(+), 38 deletions(-)

diff --git a/recipes/wash_post.recipe b/recipes/wash_post.recipe
index fb6d5bc598..3af89d502e 100644
--- a/recipes/wash_post.recipe
+++ b/recipes/wash_post.recipe
@@ -1,4 +1,3 @@
-import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 
@@ -6,55 +5,48 @@ class WashingtonPost(BasicNewsRecipe):
 
     title = 'Washington Post'
     description = 'US political news'
-    __author__ = 'Kovid Goyal and Sujata Raman'
+    __author__ = 'Kovid Goyal'
     use_embedded_content   = False
     max_articles_per_feed = 20
     language = 'en'
+    encoding = 'utf-8'
 
 
     remove_javascript = True
     no_stylesheets = True
 
-    extra_css       = '''
-                        #articleCopyright { font-family:Arial,helvetica,sans-serif ; font-weight:bold ; font-size:x-small ;}
-                        p { font-family:"Times New Roman",times,serif ; font-weight:normal ; font-size:small ;}
-                        body{font-family:arial,helvetica,sans-serif}
-                            '''
-
-    feeds = [   ('Today\'s Highlights', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/03/24/LI2005032400102.xml'),
-                ('Politics', 'http://www.washingtonpost.com/wp-dyn/rss/politics/index.xml'),
-                ('Nation', 'http://www.washingtonpost.com/wp-dyn/rss/nation/index.xml'),
-                ('World', 'http://www.washingtonpost.com/wp-dyn/rss/world/index.xml'),
-                ('Business', 'http://www.washingtonpost.com/wp-dyn/rss/business/index.xml'),
-                ('Technology', 'http://www.washingtonpost.com/wp-dyn/rss/technology/index.xml'),
-                ('Health', 'http://www.washingtonpost.com/wp-dyn/rss/health/index.xml'),
-                ('Education', 'http://www.washingtonpost.com/wp-dyn/rss/education/index.xml'),
-                ('Style',
-                     'http://www.washingtonpost.com/wp-dyn/rss/print/style/index.xml'),
-                ('NFL Sports',
-                     'http://www.washingtonpost.com/wp-dyn/rss/sports/index/nfl/index.xml'),
-                ('Redskins', 'http://www.washingtonpost.com/wp-dyn/rss/sports/redskins/index.xml'),
-                ('Editorials', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/05/30/LI2005053000331.xml'),
+    feeds = [
+            ('Politics', 'http://www.washingtonpost.com/rss/politics'),
+            ('Nation', 'http://www.washingtonpost.com/rss/national'),
+            ('World', 'http://www.washingtonpost.com/rss/world'),
+            ('Business', 'http://www.washingtonpost.com/rss/business'),
+            ('Lifestyle', 'http://www.washingtonpost.com/rss/lifestyle'),
+            ('Sports', 'http://www.washingtonpost.com/rss/sports'),
+            ('Redskins', 'http://www.washingtonpost.com/rss/sports/redskins'),
+            ('Opinions', 'http://www.washingtonpost.com/rss/opinions'),
+            ('Entertainment', 'http://www.washingtonpost.com/rss/entertainment'),
+            ('Local', 'http://www.washingtonpost.com/rss/local'),
+            ('Investigations',
+                'http://www.washingtonpost.com/rss/investigations'),
     ]
 
-    remove_tags = [{'id':['pfmnav', 'ArticleCommentsWrapper']}]
+    remove_tags = [
+            {'class':lambda x: x and 'article-toolbar' in x},
+            {'class':lambda x: x and 'quick-comments' in x},
+            {'class':lambda x: x and 'tweet' in x},
+            {'class':lambda x: x and 'article-related' in x},
+            {'class':lambda x: x and 'hidden' in x.split()},
+            {'class':lambda x: x and 'also-read' in x.split()},
+            {'class':lambda x: x and 'partners-content' in x.split()},
+            {'class':['module share', 'module ads', 'comment-vars', 'hidden',
+                'share-icons-wrap', 'comments']},
+            {'id':['right-rail']},
 
+            ]
+    keep_only_tags = dict(id=['content', 'article'])
 
-    def get_article_url(self, article):
-        return article.get('guid', article.get('link', None))
 
     def print_version(self, url):
-        return url.rpartition('.')[0] + '_pf.html'
+        url = url.rpartition('?')[0]
+        return url.replace('_story.html', '_singlePage.html')
 
-    def postprocess_html(self, soup, first):
-        for div in soup.findAll(name='div', style=re.compile('margin')):
-            div['style'] = ''
-        return soup
-
-    def preprocess_html(self, soup):
-        for tag in soup.findAll('font'):
-            if tag.has_key('size'):
-                if tag['size'] == '+2':
-                    if tag.b:
-                        return soup
-        return None