Fix #801655 (Updated recipe for Financial times UK edition)

Changelog.yaml

@@ -69,6 +69,7 @@
   improved recipes:
     - Le Temps
     - Perfil
+    - Financial Times UK
 
   new recipes:
     - title: "Daytona Beach Journal"

recipes/financial_times_uk.recipe

@@ -1,15 +1,17 @@
 __license__   = 'GPL v3'
 __copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
 '''
-ft.com
+www.ft.com/uk-edition
 '''
 from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class FinancialTimes(BasicNewsRecipe):
-    title                 = u'Financial Times - UK printed edition'
+    title                 = 'Financial Times - UK printed edition'
     __author__            = 'Darko Miletic'
-    description           = 'Financial world news'
+    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'
     oldest_article        = 2
     language              = 'en_GB'
     max_articles_per_feed = 250
@@ -17,14 +19,24 @@ class FinancialTimes(BasicNewsRecipe):
     use_embedded_content  = False
     needs_subscription    = True
     encoding              = 'utf8'
-    simultaneous_downloads= 1
+    publication_type      = 'newspaper'
-    delay                 = 1
+    cover_url             = strftime('http://specials.ft.com/vtf_pdf/%d%m%y_FRONT1_LON.pdf')
+    masthead_url          = 'http://im.media.ft.com/m/img/masthead_main.jpg'
     LOGIN                 = 'https://registration.ft.com/registration/barrier/login'
     INDEX                 = 'http://www.ft.com/uk-edition'
     PREFIX                = 'http://www.ft.com'
 
+    conversion_options = {
+                          'comment'          : description
+                        , 'tags'             : category
+                        , 'publisher'        : publisher
+                        , 'language'         : language
+                        , 'linearize_tables' : True
+                        }
+
     def get_browser(self):
         br = BasicNewsRecipe.get_browser()
+        br.open(self.INDEX)
         if self.username is not None and self.password is not None:
             br.open(self.LOGIN)
             br.select_form(name='loginForm')
@@ -33,29 +45,34 @@ class FinancialTimes(BasicNewsRecipe):
             br.submit()
         return br
 
-    keep_only_tags    = [ dict(name='div', attrs={'id':'cont'}) ]
+    keep_only_tags = [dict(name='div', attrs={'class':['fullstory fullstoryHeader','fullstory fullstoryBody','ft-story-header','ft-story-body','index-detail']})]
-    remove_tags_after = dict(name='p', attrs={'class':'copyright'})
     remove_tags = [
                       dict(name='div', attrs={'id':'floating-con'})
                      ,dict(name=['meta','iframe','base','object','embed','link'])
+                     ,dict(attrs={'class':['storyTools','story-package','screen-copy','story-package separator','expandable-image']})
                   ]
     remove_attributes = ['width','height','lang']
 
     extra_css = """
-                body{font-family:Arial,Helvetica,sans-serif;}
+                body{font-family: Georgia,Times,"Times New Roman",serif}
-                h2{font-size:large;}
+                h2{font-size:large}
-                .ft-story-header{font-size:xx-small;}
+                .ft-story-header{font-size: x-small}
-                .ft-story-body{font-size:small;}
-                a{color:#003399;}
                 .container{font-size:x-small;}
                 h3{font-size:x-small;color:#003399;}
                 .copyright{font-size: x-small}
+                img{margin-top: 0.8em; display: block}
+                .lastUpdated{font-family: Arial,Helvetica,sans-serif; font-size: x-small}
+                .byline,.ft-story-body,.ft-story-header{font-family: Arial,Helvetica,sans-serif}
                 """
 
     def get_artlinks(self, elem):
         articles = []
         for item in elem.findAll('a',href=True):
-            url   = self.PREFIX + item['href']
+            rawlink = item['href']
+            if rawlink.startswith('http://'):
+               url = rawlink
+            else:
+               url   = self.PREFIX + rawlink
             title = self.tag_to_string(item)
             date = strftime(self.timefmt)
             articles.append({
@@ -65,7 +82,7 @@ class FinancialTimes(BasicNewsRecipe):
                              ,'description':''
                             })
         return articles
-                
+
     def parse_index(self):
         feeds = []
         soup = self.index_to_soup(self.INDEX)
@@ -80,11 +97,34 @@ class FinancialTimes(BasicNewsRecipe):
            strest.insert(0,st)
         for item in strest:
             ftitle   = self.tag_to_string(item)
-            self.report_progress(0, _('Fetching feed')+' %s...'%(ftitle))            
+            self.report_progress(0, _('Fetching feed')+' %s...'%(ftitle))
             feedarts = self.get_artlinks(item.parent.ul)
             feeds.append((ftitle,feedarts))
         return feeds
 
     def preprocess_html(self, soup):
-        return self.adeify_images(soup)
+        items = ['promo-box','promo-title',
-
+                 'promo-headline','promo-image',
+                 'promo-intro','promo-link','subhead']
+        for item in items:
+            for it in soup.findAll(item):
+                it.name = 'div'
+                it.attrs = []
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll('a'):
+            limg = item.find('img')
+            if item.string is not None:
+               str = item.string
+               item.replaceWith(str)
+            else:
+               if limg:
+                  item.name = 'div'
+                  item.attrs = []
+               else:
+                   str = self.tag_to_string(item)
+                   item.replaceWith(str)
+        for item in soup.findAll('img'):
+            if not item.has_key('alt'):
+               item['alt'] = 'image'
+        return soup