From 5cc6465941057f1a3e2820f37f0750cd48774d26 Mon Sep 17 00:00:00 2001
From: Tom Scholl <thomasscholl@gmail.com>
Date: Mon, 4 Apr 2011 16:35:09 +0000
Subject: [PATCH 1/2] Added fast no image version of the daily mail recipe

---
 recipes/daily_mail_fast.recipe | 52 ++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)
 create mode 100644 recipes/daily_mail_fast.recipe

diff --git a/recipes/daily_mail_fast.recipe b/recipes/daily_mail_fast.recipe
new file mode 100644
index 0000000000..9ddb6f77f8
--- /dev/null
+++ b/recipes/daily_mail_fast.recipe
@@ -0,0 +1,52 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class TheDailyMail(BasicNewsRecipe):
+    title          = u'The Daily Mail (fast)'
+    oldest_article = 2
+    language = 'en_GB'
+
+    author = 'RufusA and Sujata Raman'
+    description = 'Faster and smaller version of the Daily Mail that does not download pictures'
+    simultaneous_downloads= 1
+    max_articles_per_feed = 50
+
+    extra_css = '''#js-article-text{font-family:Arial,Helvetica,sans-serif;}
+                    h1{font-size:x-large; font-weight:bold;}
+                    a.author{color:#003580;}
+                    .js-article-text{font-size:50%;}
+                    .imageCaption{font-size:x-small; font-weight:bold}
+
+
+                '''
+
+    remove_tags = [ dict(name='div', attrs={'class':['article-icon-links-container','print-or-mail-links cleared',
+                                                     'social-links cleared','explore-links','relatedItems','intellicrumbs box','travel','moduleHalf']}),
+                    dict(name='div', attrs={'id':['link-unit-wrapper','pushdown-ad','reader-comments','googleAds',]}),
+                    dict(name='h3', attrs={'class':['social-links-title']}),
+                     dict(name='span', attrs={'class':['clickToEnlargeTop']}),
+                     dict(name=['img']),
+                    ]
+    #remove_tags_before  = dict(name='div', attrs={'id':'content'})
+    keep_only_tags = [dict(name='div', attrs={'id':'js-article-text'})]
+
+    no_stylesheets = True
+
+    feeds          = [
+	(u'Home', u'http://www.dailymail.co.uk/home/index.rss'),
+	(u'News', u'http://www.dailymail.co.uk/news/index.rss'),
+	(u'Sport', u'http://www.dailymail.co.uk/sport/index.rss'),
+	(u'TV and Showbiz', u'http://www.dailymail.co.uk/tvshowbiz/index.rss'),
+	(u'Femail', u'http://www.dailymail.co.uk/femail/index.rss'),
+	(u'Health', u'http://www.dailymail.co.uk/health/index.rss'),
+	(u'Science and Technology', u'http://www.dailymail.co.uk/sciencetech/index.rss'),
+	(u'Money', u'http://www.dailymail.co.uk/money/index.rss'),
+	(u'Property', u'http://www.dailymail.co.uk/property/index.rss'),
+	(u'Motoring', u'http://www.dailymail.co.uk/motoring/index.rss'),
+	(u'Travel', u'http://www.dailymail.co.uk/travel/index.rss')
+        ]
+
+    #def print_version(self, url):
+    #    main = url.partition('?')[0]
+    #    return main + '?printingPage=true'
+
+

From 43b57cb343edcf9f6d17f0b7013ec0c8e2b67d51 Mon Sep 17 00:00:00 2001
From: Tom Scholl <thomasscholl@gmail.com>
Date: Thu, 7 Apr 2011 22:16:12 +0000
Subject: [PATCH 2/2] More detailed sections for guardian recipe

---
 recipes/guardian.recipe | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/recipes/guardian.recipe b/recipes/guardian.recipe
index 6211997b06..c5021cb91d 100644
--- a/recipes/guardian.recipe
+++ b/recipes/guardian.recipe
@@ -28,7 +28,7 @@ class Guardian(BasicNewsRecipe):
     # List of section titles to ignore
     # For example: ['Sport']
     ignore_sections = []
-
+    
     timefmt = ' [%a, %d %b %Y]'
     keep_only_tags = [
                       dict(name='div', attrs={'id':["content","article_header","main-article-info",]}),
@@ -87,8 +87,14 @@ class Guardian(BasicNewsRecipe):
         idx = soup.find('div', id='book-index')
         for s in idx.findAll('strong', attrs={'class':'book'}):
             a = s.find('a', href=True)
-            yield (self.tag_to_string(a), a['href'])
-
+            section_title = self.tag_to_string(a)
+            if not section_title in self.ignore_sections:
+                prefix = ''
+                if section_title != 'Main section':
+                    prefix = section_title + ': '
+                for subsection in s.parent.findAll('a', attrs={'class':'book-section'}):
+                    yield (prefix + self.tag_to_string(subsection), subsection['href'])
+    
     def find_articles(self, url):
         soup = self.index_to_soup(url)
         div = soup.find('div', attrs={'class':'book-index'})
@@ -109,15 +115,12 @@ class Guardian(BasicNewsRecipe):
                         'title': title, 'url':url, 'description':desc,
                         'date' : strftime('%a, %d %b'),
                         }
-
+    
     def parse_index(self):
         try:
             feeds = []
             for title, href in self.find_sections():
-                if not title in self.ignore_sections:
-                    feeds.append((title, list(self.find_articles(href))))
+                feeds.append((title, list(self.find_articles(href))))
             return feeds
         except:
             raise NotImplementedError
-
-