Fix #6794 (Updated recipes for Infobae and NSPM)

resources/recipes/infobae.recipe

@@ -1,12 +1,8 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
 '''
 infobae.com
 '''
-import re
-import urllib, urlparse
 
 from calibre.web.feeds.news import BasicNewsRecipe
 
@@ -21,33 +17,22 @@ class Infobae(BasicNewsRecipe):
     no_stylesheets        = True
     use_embedded_content  = False
     language              = 'es'
-    lang = 'es-AR'
-
     encoding              = 'cp1252'
-    cover_url             = 'http://www.infobae.com/imgs/header/header.gif'
+    masthead_url          = 'http://www.infobae.com/imgs/header/header.gif'
     remove_javascript     = True
-    preprocess_regexps = [(re.compile(
+    remove_empty_feeds    = True
-        r'<meta name="Description" content="[^"]+">'), lambda m:'')]
-
-
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
-
     extra_css             = '''
-                    .col-center{font-family:Arial,Helvetica,sans-serif;}
+                              body{font-family:Arial,Helvetica,sans-serif;}
-                    h1{font-family:Arial,Helvetica,sans-serif; color:#0D4261;}
+                              .popUpTitulo{color:#0D4261; font-size: xx-large}
-                    .fuenteIntNota{font-family:Arial,Helvetica,sans-serif; color:#1D1D1D; font-size:x-small;}
                             '''
     
-    keep_only_tags = [dict(name='div', attrs={'class':['content']})]
+    conversion_options = {
-
+                          'comment'          : description
-
+                        , 'tags'             : category
-    remove_tags = [
+                        , 'publisher'        : publisher
-               dict(name='div', attrs={'class':['options','col-right','controles', 'bannerLibre','tiulo-masleidas','masleidas-h']}),
+                        , 'language'         : language
-               dict(name='a', attrs={'name' : 'comentario',}),
+                        , 'linearize_tables' : True
-               dict(name='iframe'),
+                        }
-               dict(name='img', alt = "Ver galerias de imagenes"),
-
-                                 ]
     
 
     feeds = [
@@ -57,39 +42,14 @@ class Infobae(BasicNewsRecipe):
              ,(u'Deportes'  , u'http://www.infobae.com/adjuntos/html/RSS/deportes.xml'  )
             ]
 
-#    def print_version(self, url):
+    def print_version(self, url):
-#        main, sep, article_part = url.partition('contenidos/')
+        article_part = url.rpartition('/')[2]
-#        article_id, rsep, rrest = article_part.partition('-')
+        article_id= article_part.partition('-')[0]
-#        return u'http://www.infobae.com/notas/nota_imprimir.php?Idx=' + article_id
+        return 'http://www.infobae.com/notas/nota_imprimir.php?Idx=' + article_id
-
-    def get_article_url(self, article):
-        ans = article.get('link').encode('utf-8')
-        parts = list(urlparse.urlparse(ans))
-        parts[2] = urllib.quote(parts[2])
-        ans = urlparse.urlunparse(parts)
-        return ans.decode('utf-8')
-
-
-    def preprocess_html(self, soup):
-
-        for tag in soup.head.findAll('strong'):
-            tag.extract()
-        for tag in soup.findAll('meta'):
-            del tag['content']
-            tag.extract()
-
-        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">\n<meta http-equiv="Content-Language" content="es-AR"/>\n'
-        soup.head.insert(0,mtag)
-        for item in soup.findAll(style=True):
-            del item['style']
-
-        return soup
 
     def postprocess_html(self, soup, first):
-
         for tag in soup.findAll(name='strong'):
              tag.name = 'b'
-
         return soup
 
 

resources/recipes/nspm.recipe

@@ -6,6 +6,7 @@ nspm.rs
 
 import re
 from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Tag, NavigableString
 
 class Nspm(BasicNewsRecipe):
     title                 = 'Nova srpska politicka misao'
@@ -21,6 +22,7 @@ class Nspm(BasicNewsRecipe):
     encoding              = 'utf-8'
     language              = 'sr'
     delay                 = 2
+    remove_empty_feeds    = True
     publication_type      = 'magazine'
     masthead_url          = 'http://www.nspm.rs/templates/jsn_epic_pro/images/logol.jpg'
     extra_css             = """ @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
@@ -45,6 +47,7 @@ class Nspm(BasicNewsRecipe):
                            dict(name=['link','object','embed','script','meta','base','iframe'])
                           ,dict(attrs={'class':'buttonheading'})
                          ]
+    remove_tags_before = dict(attrs={'class':'contentheading'})
     remove_tags_after  = dict(attrs={'class':'article_separator'})
     remove_attributes  = ['width','height']
 
@@ -67,4 +70,8 @@ class Nspm(BasicNewsRecipe):
     def preprocess_html(self, soup):
         for item in soup.body.findAll(style=True):
             del item['style']
+        for item in soup.body.findAll('h1'):
+            nh = NavigableString(item.a.string)
+            item.a.extract()
+            item.insert(0,nh)
         return self.adeify_images(soup)