New recipe for Smashing Magazine by Darko Miletic and improved recipe for Die Ziet

src/calibre/web/feeds/recipes/__init__.py

@@ -57,7 +57,7 @@ recipe_modules = ['recipe_' + r for r in (
            'monitor', 'republika', 'beta', 'beta_en', 'glasjavnosti',
            'esquire', 'livemint', 'thedgesingapore', 'darknet', 'rga',
            'intelligencer', 'theoldfoodie', 'hln_be', 'honvedelem',
-           'the_new_republic', 'philly', 'salon', 'tweakers',
+           'the_new_republic', 'philly', 'salon', 'tweakers', 'smashing',
           )]
 
 

src/calibre/web/feeds/recipes/recipe_smashing.py

@@ -0,0 +1,51 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.smashingmagazine.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Tag
+
+class SmashingMagazine(BasicNewsRecipe):
+    title                 = 'Smashing Magazine'
+    __author__            = 'Darko Miletic'
+    description           = 'We smash you with the information that will make your life easier, really'
+    oldest_article        = 20
+    language              = 'en'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    publisher             = 'Smashing Magazine'
+    category              = 'news, web, IT, css, javascript, html'
+    encoding              = 'utf-8'
+    
+    conversion_options = {  
+                             'comments'    : description
+                            ,'tags'        : category
+                            ,'publisher'   : publisher
+                         }
+                         
+    keep_only_tags = [dict(name='div', attrs={'id':'leftcolumn'})]
+    remove_tags_after = dict(name='ul',attrs={'class':'social'})
+    remove_tags = [
+                    dict(name=['link','object'])
+                   ,dict(name='h1',attrs={'class':'logo'})
+                   ,dict(name='div',attrs={'id':'booklogosec'})
+                   ,dict(attrs={'src':'http://media2.smashingmagazine.com/wp-content/uploads/images/the-smashing-book/smbook6.gif'})
+                  ]
+
+    feeds          = [(u'Articles', u'http://rss1.smashingmagazine.com/feed/')]
+
+    def preprocess_html(self, soup):
+        for iter in soup.findAll('div',attrs={'class':'leftframe'}):
+            it = iter.find('h1')
+            if it == None:
+               iter.extract()
+        for item in soup.findAll('img'):
+            oldParent = item.parent
+            if oldParent.name == 'a':
+               oldParent.name = 'div'            
+        return soup

src/calibre/web/feeds/recipes/recipe_zeitde.py

@@ -13,18 +13,17 @@ class ZeitDe(BasicNewsRecipe):
     title = 'Die Zeit Nachrichten'
     description = 'Die Zeit - Online Nachrichten'
     language = 'de'
+    lang = 'de_DE'
 
-    __author__ = 'Kovid Goyal and Martin Pitt'
+    __author__ = 'Martin Pitt and Suajta Raman'
     use_embedded_content   = False
-    timefmt = ' [%d %b %Y]'
     max_articles_per_feed = 40
+    remove_empty_feeds = True
     no_stylesheets = True
-    encoding = 'utf8'
+    encoding = 'utf-8'
 
-    remove_tags = [{'class': 'adwrap'}]
-    keep_only_tags = [{'name': 'div', 'class': 'content'}]
 
-    feeds =  [ ('Kurznachrichten', 'http://newsfeed.zeit.de/index'),
+    feeds =  [
                ('Politik', 'http://newsfeed.zeit.de/politik/index'),
                ('Wirtschaft', 'http://newsfeed.zeit.de/wirtschaft/index'),
                ('Meinung', 'http://newsfeed.zeit.de/meinung/index'),
@@ -33,6 +32,43 @@ class ZeitDe(BasicNewsRecipe):
                ('Wissen', 'http://newsfeed.zeit.de/wissen/index'),
              ]
 
-    def print_version(self,url):
-        return url.replace('http://www.zeit.de/', 'http://mobil.zeit.de/')
+    extra_css = '''
+                .supertitle{color:#990000; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;}
+                .excerpt{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:large;}
+                .title{font-family:Arial,Helvetica,sans-serif;font-size:large}
+                .caption{color:#666666; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;}
+                .copyright{color:#666666; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;}
+                .article{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:x-small}
+                .headline iconportrait_inline{font-family:Arial,Helvetica,sans-serif;font-size:x-small}
+                '''
+    filter_regexps = [r'ad.de.doubleclick.net/']
+    keep_only_tags = [
+                        dict(name='div', attrs={'class':["article"]}) ,
+                         ]
+    remove_tags = [
+                    dict(name='link'), dict(name='iframe'),dict(name='style'),
+                    dict(name='div', attrs={'class':["pagination block","pagenav","inline link"] }),
+                     dict(name='div', attrs={'id':["place_5","place_4"]})
+                  ]
+
+    def get_article_url(self, article):
+
+          url = article.get('guid', None)
+
+          if 'video' in url or 'quiz' in url :
+
+              url = None
+
+          return url
+
+    def preprocess_html(self, soup):
+        soup.html['xml:lang'] = self.lang
+        soup.html['lang']     = self.lang
+        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
+        soup.head.insert(0,mtag)
+
+        return soup
+
+    #def print_version(self,url):
+    #    return url.replace('http://www.zeit.de/', 'http://images.zeit.de/text/').replace('?from=rss', '')