From 746b9b1d63cd6372cd19ac97d787f7bd524e6919 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sat, 21 May 2011 14:19:26 -0600
Subject: [PATCH] Fix #786293 (Updated recipe for Marca website)

---
 recipes/icons/marca.png | Bin 0 -> 293 bytes
 recipes/marca.recipe    |  46 +++++++++++++++++-----------------------
 2 files changed, 19 insertions(+), 27 deletions(-)
 create mode 100644 recipes/icons/marca.png

diff --git a/recipes/icons/marca.png b/recipes/icons/marca.png
new file mode 100644
index 0000000000000000000000000000000000000000..e9231176b66532319eae2266c74d9d1c5ac30c1c
GIT binary patch
literal 293
zcmV+=0owkFP)<h;3K|Lk000e1NJLTq000mG000mO1^@s6AM^iV0002&Nkl<Zc$}q@
zIkLhq5JcZt3dqQ~g{$BsT!GLB;{=?BfQ+0BB8~e8vMr34zr8AzC2P9XS_}~XAOc8#
z^Dwh)K-)qH(~92MY&z#&63h|;T(7X*=6)ymBn~S`5MwEHhsy;vo3S_qNNGq{4CXkW
z7X$Vh12i1sdxEvCrPO&C)q3^!%p24-G));dP5$>|1AyZ(#|<I(SI|HR66EjmDed>t
z;UK+U<GBt%v9p-o#Qly=CveAZx4C73{ubP4U!oolND15RrUvd<r;*&Hy3P^bTgf_Y
r?gEq(wC(a^T0S|fs`3_oryTPIQQej)U60RQ00000NkvXXu0mjf^%Q?!

literal 0
HcmV?d00001

diff --git a/recipes/marca.recipe b/recipes/marca.recipe
index 14543b3c0f..1abd8791b6 100644
--- a/recipes/marca.recipe
+++ b/recipes/marca.recipe
@@ -1,14 +1,11 @@
-#!/usr/bin/env  python
 # -*- coding: utf-8 -*-
-
 __license__   = 'GPL v3'
-__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>'
 '''
 www.marca.com
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
 
 class Marca(BasicNewsRecipe):
     title                 = 'Marca'
@@ -22,35 +19,30 @@ class Marca(BasicNewsRecipe):
     use_embedded_content  = False
     delay                 = 1
     encoding              = 'iso-8859-15'
-    language = 'es'
+    language              = 'es_ES'
+    publication_type      = 'newsportal'
+    masthead_url          = 'http://estaticos.marca.com/deporte/img/v3.0/img_marca-com.png'
+    extra_css             = """
+                                body{font-family: Tahoma,Geneva,sans-serif}
+                                h1,h2,h3,h4,h5,h6{font-family: 'LatoBlack',Tahoma,Geneva,sans-serif}
+                                .cab_articulo h4 {font-family: Georgia,"Times New Roman",Times,serif}
+                                .antetitulo{text-transform: uppercase}
+                            """
 
-    direction             = 'ltr'
+    feeds             = [(u'Portada', u'http://estaticos.marca.com/rss/portada.xml')]
 
-    html2lrf_options = [
-                          '--comment'  , description
-                        , '--category' , category
-                        , '--publisher', publisher
-                        ]
-
-    html2epub_options  = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
-
-    feeds              = [(u'Portada', u'http://rss.marca.com/rss/descarga.htm?data2=425')]
-
-    keep_only_tags = [dict(name='div', attrs={'class':['cab_articulo','col_izq']})]
-
-    remove_tags        = [
-                             dict(name=['object','link','script'])
-                            ,dict(name='div', attrs={'class':['colC','peu']})
-                            ,dict(name='div', attrs={'class':['utilidades estirar','bloque_int_corr estirar']})
+    keep_only_tags    = [dict(name='div', attrs={'class':['cab_articulo','cuerpo_articulo']})]
+    remove_attributes = ['lang']
+    remove_tags       = [
+                             dict(name=['object','link','script','embed','iframe','meta','base'])
+                            ,dict(name='div', attrs={'class':'tabs'})
                          ]
 
-    remove_tags_after = [dict(name='div', attrs={'class':'bloque_int_corr estirar'})]
-
     def preprocess_html(self, soup):
-        soup.html['dir' ] = self.direction
-        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
-        soup.head.insert(0,mcharset)
         for item in soup.findAll(style=True):
             del item['style']
         return soup
 
+    def get_article_url(self, article):
+        return article.get('guid',  None)
+