Fix #802232 (Updated recipe for Financial times rss)

recipes/financial_times.recipe

@@ -1,32 +1,42 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
 '''
-ft.com
+www.ft.com
 '''
 
+import datetime
+from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
 
-class FinancialTimes(BasicNewsRecipe):
+class FinancialTimes_rss(BasicNewsRecipe):
-    title                 = u'Financial Times'
+    title                 = 'Financial Times'
-    __author__            = 'Darko Miletic and Sujata Raman'
+    __author__            = 'Darko Miletic'
-    description           = ('Financial world news. Available after 5AM '
+    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."
-                                'GMT, daily.')
+    publisher             = 'The Financial Times Ltd.'
+    category              = 'news, finances, politics, World'
     oldest_article        = 2
     language              = 'en'
-
+    max_articles_per_feed = 250
-    max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
     needs_subscription    = True
-    simultaneous_downloads= 1
+    encoding              = 'utf8'
-    delay                 = 1
+    publication_type      = 'newspaper'
-
+    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'
+
+    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')
@@ -35,31 +45,63 @@ 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 = '''
+    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}
+                """
+
     feeds = [
                (u'UK'         , u'http://www.ft.com/rss/home/uk'        )
               ,(u'US'         , u'http://www.ft.com/rss/home/us'        )
-              ,(u'Europe'     , u'http://www.ft.com/rss/home/europe'    )
               ,(u'Asia'       , u'http://www.ft.com/rss/home/asia'      )
               ,(u'Middle East', u'http://www.ft.com/rss/home/middleeast')
             ]
 
     def preprocess_html(self, soup):
-        content_type = soup.find('meta', {'http-equiv':'Content-Type'})
+        items = ['promo-box','promo-title',
-        if content_type:
+                 'promo-headline','promo-image',
-            content_type['content'] = 'text/html; charset=utf-8'
+                 '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
+
+    def get_cover_url(self):
+        cdate = datetime.date.today()
+        if cdate.isoweekday() == 7:
+           cdate -= datetime.timedelta(days=1)
+        return cdate.strftime('http://specials.ft.com/vtf_pdf/%d%m%y_FRONT1_USA.pdf')
+