Fix #1169590 (Updated recipe for Financial Times, UK and US edition)

recipes/financial_times_uk.recipe

@@ -1,7 +1,7 @@
 __license__   = 'GPL v3'
-__copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2010-2013, Darko Miletic <darko.miletic at gmail.com>'
 '''
-www.ft.com/uk-edition
+www.ft.com/intl/uk-edition
 '''
 
 import datetime
@@ -29,7 +29,7 @@ class FinancialTimes(BasicNewsRecipe):
     masthead_url          = 'http://im.media.ft.com/m/img/masthead_main.jpg'
     LOGIN                 = 'https://registration.ft.com/registration/barrier/login'
     LOGIN2                = 'http://media.ft.com/h/subs3.html'
-    INDEX                 = 'http://www.ft.com/uk-edition'
+    INDEX                 = 'http://www.ft.com/intl/uk-edition'
     PREFIX                = 'http://www.ft.com'
 
     conversion_options = {

recipes/financial_times_us.recipe

@@ -1,20 +1,21 @@
 __license__   = 'GPL v3'
-__copyright__ = '2013, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2010-2013, Darko Miletic <darko.miletic at gmail.com>'
 '''
-http://www.ft.com/intl/us-edition
+www.ft.com/intl/international-edition
 '''
 
 import datetime
 from calibre.ptempfile import PersistentTemporaryFile
 from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
+from collections import OrderedDict
 
 class FinancialTimes(BasicNewsRecipe):
-    title                 = 'Financial Times (US) printed edition'
+    title                 = 'Financial Times (International) printed edition'
     __author__            = 'Darko Miletic'
     description           = "The Financial Times (FT) is one of the world's leading business news and information organisations, recognised internationally for its authority, integrity and accuracy."
     publisher             = 'The Financial Times Ltd.'
-    category              = 'news, finances, politics, UK, World'
+    category              = 'news, finances, politics, World'
     oldest_article        = 2
     language              = 'en'
     max_articles_per_feed = 250
@@ -28,7 +29,7 @@ class FinancialTimes(BasicNewsRecipe):
     masthead_url          = 'http://im.media.ft.com/m/img/masthead_main.jpg'
     LOGIN                 = 'https://registration.ft.com/registration/barrier/login'
     LOGIN2                = 'http://media.ft.com/h/subs3.html'
-    INDEX                 = 'http://www.ft.com/intl/us-edition'
+    INDEX                 = 'http://www.ft.com/intl/international-edition'
     PREFIX                = 'http://www.ft.com'
 
     conversion_options = {
@@ -105,29 +106,30 @@ class FinancialTimes(BasicNewsRecipe):
         return articles
 
     def parse_index(self):
-        feeds = []
+        feeds = OrderedDict()
         soup = self.index_to_soup(self.INDEX)
-        dates= self.tag_to_string(soup.find('div', attrs={'class':'btm-links'}).find('div'))
+        #dates= self.tag_to_string(soup.find('div', attrs={'class':'btm-links'}).find('div'))
-        self.timefmt = ' [%s]'%dates
+        #self.timefmt = ' [%s]'%dates
-        wide = soup.find('div',attrs={'class':'wide'})
+        section_title = 'Untitled'
-        if not wide:
+
-           return feeds
+        for column in soup.findAll('div', attrs = {'class':'feedBoxes clearfix'}):
-        allsections = wide.findAll(attrs={'class':lambda x: x and 'footwell' in x.split()})
+            for section in column. findAll('div', attrs = {'class':'feedBox'}):
-        if not allsections:
+                sectiontitle=self.tag_to_string(section.find('h4'))
-           return feeds
+                if '...' not in sectiontitle: section_title=sectiontitle
-        count = 0
+                for article in section.ul.findAll('li'):
-        for item in allsections:
+                    articles = []
-            count = count + 1
+                    title=self.tag_to_string(article.a)
-            if self.test and count > 2:
+                    url=article.a['href']
-               return feeds
+                    articles.append({'title':title, 'url':url, 'description':'', 'date':''})
-            fitem = item.h3
+
-            if not fitem:
+                    if articles:
-               fitem = item.h4
+                        if section_title not in feeds:
-            ftitle = self.tag_to_string(fitem)   
+                            feeds[section_title] = []
-            self.report_progress(0, _('Fetching feed')+' %s...'%(ftitle))
+                        feeds[section_title] += articles
-            feedarts = self.get_artlinks(item.ul)
+
-            feeds.append((ftitle,feedarts))
+
-        return feeds
+        ans = [(key, val) for key, val in feeds.iteritems()]
+        return ans
 
     def preprocess_html(self, soup):
         items = ['promo-box','promo-title',
@@ -177,6 +179,3 @@ class FinancialTimes(BasicNewsRecipe):
         tfile.close()
         self.temp_files.append(tfile)
         return tfile.name
-
-    def cleanup(self):
-        self.browser.open('https://registration.ft.com/registration/login/logout?location=')