Updated recipes for Clarin and Pagina 12. Fix #4199 (Updated recipes in spanish)

resources/recipes/clarin.recipe

@@ -1,4 +1,3 @@
-#!/usr/bin/env  python
 
 __license__   = 'GPL v3'
 __copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
@@ -8,7 +7,6 @@ clarin.com
 
 from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
 
 class Clarin(BasicNewsRecipe):
     title                 = 'Clarin'
@@ -21,21 +19,16 @@ class Clarin(BasicNewsRecipe):
     use_embedded_content  = False
     no_stylesheets        = True
     cover_url             = strftime('http://www.clarin.com/diario/%Y/%m/%d/portada.jpg')
-    remove_javascript     = True
     encoding              = 'cp1252'
     language              = 'es'
-
-    lang                  = 'es-AR'
-    direction             = 'ltr'
     extra_css             = ' .Txt{ font-family: sans-serif } .Volan{ font-family: sans-serif; font-size: x-small} .Pie{ font-family: sans-serif; font-size: x-small} .Copete{font-family: sans-serif; font-size: large} .Hora{font-family: sans-serif; font-size: large} .Autor{font-family: sans-serif; font-size: small} '
 
-    html2lrf_options = [
+    conversion_options = {
-                          '--comment', description
+                          'comment'  : description
-                        , '--category', category
+                        , 'tags'     : category
-                        , '--publisher', publisher
+                        , 'publisher': publisher
-                        ]
+                        , 'language' : language
-
+                        }
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\npretty_print=True\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
 
     remove_tags = [
                      dict(name='a'   , attrs={'class':'Imp'   })
@@ -60,14 +53,4 @@ class Clarin(BasicNewsRecipe):
         lurl = u'http://www.servicios.clarin.com/notas/jsp/clarin/v9/notas/imprimir.jsp?pagid=' + lmain
         return lurl
 
-    def preprocess_html(self, soup):
-        soup.html['lang'] = self.lang
-        soup.html['dir' ] = self.direction
-        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
-        soup.head.insert(0,mlang)
-        soup.head.insert(1,mcharset)
-        for item in soup.findAll(style=True):
-            del item['style']
-        return soup
 

resources/recipes/pagina12.recipe

@@ -1,4 +1,3 @@
-#!/usr/bin/env  python
 
 __license__   = 'GPL v3'
 __copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
@@ -6,7 +5,6 @@ __copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
 pagina12.com.ar
 '''
 
-from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Pagina12(BasicNewsRecipe):
@@ -19,36 +17,33 @@ class Pagina12(BasicNewsRecipe):
     max_articles_per_feed = 100
     no_stylesheets        = True
     encoding              = 'cp1252'
-    cover_url             = strftime('http://www.pagina12.com.ar/fotos/%Y%m%d/diario/tapagn.jpg')
-    remove_javascript     = True
     use_embedded_content  = False
     language              = 'es'
 
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_tags = [dict(name='div', attrs={'id':['volver','logo','logo_suple','fin','permalink']})]
 
 
-    html2lrf_options = [
+    feeds = [
-                          '--comment', description
+              (u'Edicion impresa', u'http://www.pagina12.com.ar/diario/rss/principal.xml'   )
-                        , '--category', category
+             ,(u'Espectaculos'   , u'http://www.pagina12.com.ar/diario/rss/espectaculos.xml')
-                        , '--publisher', publisher
+             ,(u'Radar'          , u'http://www.pagina12.com.ar/diario/rss/radar.xml'       )
+             ,(u'Radar libros'   , u'http://www.pagina12.com.ar/diario/rss/libros.xml'      )
+             ,(u'Cash'           , u'http://www.pagina12.com.ar/diario/rss/cash.xml'        )
+             ,(u'Turismo'        , u'http://www.pagina12.com.ar/diario/rss/turismo.xml'     )
+             ,(u'Libero'         , u'http://www.pagina12.com.ar/diario/rss/libero.xml'      )
+             ,(u'NO'             , u'http://www.pagina12.com.ar/diario/rss/no.xml'          )
+             ,(u'Las/12'         , u'http://www.pagina12.com.ar/diario/rss/las12.xml'       )
+             ,(u'Soy'            , u'http://www.pagina12.com.ar/diario/rss/soy.xml'         )
+             ,(u'M2'             , u'http://www.pagina12.com.ar/diario/rss/futuro.xml'      )
             ]
 
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
-
-
-    remove_tags = [
-                     dict(name='div', attrs={'id':'volver'})
-                    ,dict(name='div', attrs={'id':'logo'  })
-                  ]
-
-
-    feeds = [(u'Pagina/12', u'http://www.pagina12.com.ar/diario/rss/principal.xml')]
-
     def print_version(self, url):
         return url.replace('http://www.pagina12.com.ar/','http://www.pagina12.com.ar/imprimir/')
 
-    def preprocess_html(self, soup):
-        mtag = '<meta http-equiv="Content-Language" content="es-AR"/>'
-        soup.head.insert(0,mtag)
-        for item in soup.findAll(style=True):
-            del item['style']
-        return soup