Update Capital.de

recipes/capital_de.recipe

@@ -1,61 +1,81 @@
+#!/usr/bin/env python2
+# vim:fileencoding=utf-8
+from __future__ import unicode_literals, division, absolute_import, print_function
+
+'''
+capital.de
+'''
+
+import re
 from calibre.web.feeds.news import BasicNewsRecipe
+
 class AdvancedUserRecipe1305470859(BasicNewsRecipe):
-    title                 = u'Capital.de'
+    title       = 'Capital.de'
-    language              = 'de'
+    __author__  = 'schuster'
-    __author__            = 'schuster'
+    description = 'RSS-Feed von Capital.de'
-    oldest_article        =7
+    publisher   = 'Gruner+Jahr GmbH & Co KG'
+    language    = 'de'
+
+    oldest_article        = 14
     max_articles_per_feed = 35
     no_stylesheets        = True
     remove_javascript     = True
     use_embedded_content  = False
-    masthead_url = 'http://www.wirtschaftsmedien-shop.de/media/stores/wirtschaftsmedien/capital/teaser_large_abo.jpg'
-    cover_url = 'http://d1kb9jvg6ylufe.cloudfront.net/WebsiteCMS/de/unternehmen/linktipps/mainColumn/08/image/DE_Capital_bis20mm_SW.jpg'
 
-    extra_css = '''
+    conversion_options = {'smarten_punctuation' : True,
-                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                          'publisher'           : publisher}
-                    h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
-                    img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
-                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
-                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
-	'''
-    def print_version(self, url):
-        return url.replace ('nv=rss#utm_source=rss2&utm_medium=rss_feed&utm_campaign=/', 'mode=print')
-    remove_tags_bevor = [dict(name='td', attrs={'class':'textcell'})]
-    remove_tags_after = [dict(name='div', attrs={'class':'artikelsplit'})]
 
-    feeds = [   (u'Wirtschaftsmagazin', u'http://www.capital.de/rss/'),
+    cover_source = 'http://shop.capital.de/abos/capital/'
-	(u'Unternehmen', u'http://www.capital.de/rss/unternehmen'),
+    masthead_url = 'http://www.capital.de/files/capital/layout/logo.png'
-	(u'Finanz & Geldanlage', u'http://www.capital.de/rss/finanzen/geldanlage')]
 
-    def append_page(self, soup, appendtag, position):
+    feeds = [
-        pager = soup.find('div',attrs={'class':'artikelsplit'})
+        ('Capital.de', 'http://www.capital.de/partner-feeds/rss.xml')
-        if pager:
+    ]
-           nexturl = self.INDEX + pager.a['href']
-           soup2 = self.index_to_soup(nexturl)
-           texttag = soup2.find('div', attrs={'class':'printable'})
-           for it in texttag.findAll(style=True):
-               del it['style']
-           newpos = len(texttag.contents)
-           self.append_page(soup2,texttag,newpos)
-           texttag.extract()
-           appendtag.insert(position,texttag)
 
+    keep_only_tags = [
+        dict(name='div', attrs={'class':'grid_8 alpha omega layout_full block'})
+    ]
+
+    remove_tags = [
+        dict(name='div', attrs={'class':'article_header'}),
+        dict(name='br', attrs={'class':'clear'})
+    ]
+
+    remove_attributes = ['height', 'width']
+
+    extra_css = 'h1 {font-size: 1.6em; text-align: left} \
+                 h2 {font-size: 1em; text-align: left} \
+                 .copyright {font-size: 0.6em} \
+                 .caption {font-size: 0.6em}'
+
+    def get_cover_url(self):
+        soup = self.index_to_soup(self.cover_source)
+        img_span = soup.find('span', {'class':re.compile('coverimage')})
+        self.cover_url = img_span.find('img', src=True)['src']
+        return self.cover_url
 
     def preprocess_html(self, soup):
+        # remove all articles without relevant content
+        tags = soup.findAll('li', {'class':'tag-chain-item'})
+        for li in tags:
+            if 'BILDERSTRECKE' in self.tag_to_string(li).upper():
+                self.abort_article()
+        # remove list of tags
+        tags = soup.find('ul', {'class':'tag-chain'})
+        if tags:
+            tags.extract()
+        # remove all style attributes
         for item in soup.findAll(style=True):
             del item['style']
-        for item in soup.findAll('div', attrs={'class':'artikelsplit'}):
+        # remove all local hyperlinks
-            item.extract()
+        for a in soup.findAll('a', {'href':True}):
-        self.append_page(soup, soup.body, 3)
+            if a['href'] and 'http' not in a['href']:
-        pager = soup.find('div',attrs={'class':'artikelsplit'})
+                del a['href']
-        if pager:
+        # remove picture(s) of author(s)
-           pager.extract()
+        for div in soup.findAll('div', {'class':'ce_text block'}):
-        return self.adeify_images(soup)
+            if div.find('hr'):
-
+                for hr in div.findAll('hr'):
-
+                    hr.extract()
-
+                for img in div.findAll('img'):
-    remove_tags = [dict(attrs={'class':['navSeitenAlle', 'kommentieren', 'teaserheader', 'teasercontent', 'info', 'zwischenhead', 'artikelsplit']}),
+                    img.extract()
-                dict(id=['topNav', 'mainNav', 'subNav', 'socialmedia', 'footerRahmen', 'gatrixx_marktinformationen', 'pager', 'weitere']),
+        return soup
-                dict(span=['ratingtext', 'Gesamtranking', 'h3','']),
-	dict(rel=['canonical'])]
-