Updated Spiegel Online International. Fixes #806603 (Updated recipe for Spiegel International in english)

recipes/spiegel_int.recipe

@@ -1,94 +1,67 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
 '''
 spiegel.de
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
 
-
 class Spiegel_int(BasicNewsRecipe):
     title                 = 'Spiegel Online International'
     __author__            = 'Darko Miletic and Sujata Raman'
-    description           = "News and POV from Europe's largest newsmagazine"
+    description           = "Daily news, analysis and opinion from Europe's leading newsmagazine and Germany's top news Web site"
     oldest_article        = 7
     max_articles_per_feed = 100
-    language = 'en'
-
+    language              = 'en_DE'
     no_stylesheets        = True
     use_embedded_content  = False
+    encoding              = 'cp1252'
     publisher             = 'SPIEGEL ONLINE GmbH'
     category              = 'news, politics, Germany'
-    lang                  = 'en'
-    recursions = 1
-    match_regexps = [r'http://www.spiegel.de/.*-[1-9],00.html']
+    masthead_url          = 'http://www.spiegel.de/static/sys/v9/spiegelonline_logo.png'
+    publication_type      = 'magazine'
+
     conversion_options = {
-                             'comments'    : description
-                            ,'tags'        : category
-                            ,'language'    : lang
-                            ,'publisher'   : publisher
-                            ,'pretty_print': True
+                             'comments' : description
+                            ,'tags'     : category
+                            ,'language' : language
+                            ,'publisher': publisher
                          }
 
     extra_css = '''
-                   #spArticleColumn{font-family:verdana,arial,helvetica,geneva,sans-serif ; }
+                   #spArticleContent{font-family: Verdana,Arial,Helvetica,Geneva,sans-serif}
                    h1{color:#666666; font-weight:bold;}
                    h2{color:#990000;}
                    h3{color:#990000;}
                    h4 {color:#990000;}
                    a{color:#990000;}
                    .spAuthor{font-style:italic;}
-                   #spIntroTeaser{font-weight:bold;}
+                   #spIntroTeaser{font-weight:bold}
                    .spCredit{color:#666666; font-size:x-small;}
                    .spShortDate{font-size:x-small;}
                    .spArticleImageBox {font-size:x-small;}
                    .spPhotoGallery{font-size:x-small; color:#990000 ;}
                 '''
 
-    keep_only_tags = [
-                        dict(name ='div', attrs={'id': ['spArticleImageBox spAssetAlignleft','spArticleColumn']}),
-                    ]
+    keep_only_tags    = [dict(attrs={'id':'spArticleContent'})]
+    remove_tags_after = dict(attrs={'id':'spArticleBody'})
+    remove_tags       = [dict(name=['meta','base','iframe','embed','object'])]
+    remove_attributes = ['clear']
+    feeds             = [(u'Spiegel Online', u'http://www.spiegel.de/international/index.rss')]
 
-    remove_tags = [
-                    dict(name='div', attrs={'id':['spSocialBookmark','spArticleFunctions','spMultiPagerHeadlines',]}),
-                    dict(name='div', attrs={'class':['spCommercial spM520','spArticleCredit','spPicZoom']}),
-                    ]
-
-    feeds          = [(u'Spiegel Online', u'http://www.spiegel.de/schlagzeilen/rss/0,5291,676,00.xml')]
-
-    def postprocess_html(self, soup,first):
-
-         for tag in soup.findAll(name='div',attrs={'id':"spMultiPagerControl"}):
-                tag.extract()
-
-         p =  soup.find(name = 'p', attrs={'id':'spIntroTeaser'})
-
-         if p.string is not None:
-            t = p.string.rpartition(':')[0]
-
-            if 'Part'in t:
-                if soup.h1 is not None:
-                     soup.h1.extract()
-                if soup.h2 is not None:
-                 soup.h2.extract()
-                 functag = soup.find(name= 'div', attrs={'id':"spArticleFunctions"})
-                 if functag is not None:
-                     functag.extract()
-                 auttag = soup.find(name= 'p', attrs={'class':"spAuthor"})
-                 if auttag is not None:
-                     auttag.extract()
-
-                 pictag = soup.find(name= 'div', attrs={'id':"spArticleTopAsset"})
-                 if pictag is not None:
-                     pictag.extract()
-
-
-         return soup
-
-   # def print_version(self, url):
-   #     main, sep, rest = url.rpartition(',')
-   #     rmain, rsep, rrest = main.rpartition(',')
-   #     return rmain + ',druck-' + rrest + ',' + rest
+    def print_version(self, url):
+        main, sep, rest = url.rpartition(',')
+        rmain, rsep, rrest = main.rpartition(',')
+        return rmain + ',druck-' + rrest + ',' + rest
 
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll('a'):
+            if item.string is not None:
+               str = item.string
+               item.replaceWith(str)
+            else:
+               str = self.tag_to_string(item)
+               item.replaceWith(str)
+        return soup