From f9e79e10ddd070fe2c271a1f70dd09ffabcd5500 Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Wed, 4 Aug 2010 22:19:59 -0600
Subject: [PATCH] Folha de Sao Paulo by Saverio Palmieri Neto

---
 resources/recipes/folhadesaopaulo.recipe | 74 ++++++++++++++++++++++++
 1 file changed, 74 insertions(+)
 create mode 100644 resources/recipes/folhadesaopaulo.recipe

diff --git a/resources/recipes/folhadesaopaulo.recipe b/resources/recipes/folhadesaopaulo.recipe
new file mode 100644
index 0000000000..262a265020
--- /dev/null
+++ b/resources/recipes/folhadesaopaulo.recipe
@@ -0,0 +1,74 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Saverio Palmieri Neto <saverio.palmieri at gmail.com>'
+'''
+folha.uol.com.br
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class FolhaOnline(BasicNewsRecipe):
+    title                 = 'Folha de Sao Paulo'
+    __author__            = 'Saverio Palmieri Neto'
+    description           = 'Brazilian news from Folha de Sao Paulo Online'
+    publisher             = 'Folha de Sao Paulo'
+    category              = 'Brasil, news'
+    oldest_article        = 2
+    max_articles_per_feed = 1000
+    summary_length        = 2048
+    no_stylesheets        = True
+    use_embedded_content  = False
+    timefmt               = ' [%d %b %Y (%a)]'
+    encoding              = 'cp1252'
+    cover_url             = 'http://lh5.ggpht.com/_hEb7sFmuBvk/TFoiKLRS5dI/AAAAAAAAADM/kcVKggZwKnw/capa_folha.jpg'
+    cover_margins         = (5,5,'white')
+    remove_javascript     = True
+
+    keep_only_tags = [dict(name='div', attrs={'id':'articleNew'})]
+
+    remove_tags = [
+                     dict(name='script')
+					,dict(name='div',
+						attrs={'id':[
+							'articleButton'
+							,'bookmarklets'
+							,'ad-180x150-1'
+							,'contextualAdsArticle'
+							,'articleEnd'
+							,'articleComments'
+							]})
+					,dict(name='div',
+						attrs={'class':[
+							'openBox adslibraryArticle'
+							]})
+                    ,dict(name='a')
+                    ,dict(name='iframe')
+                    ,dict(name='link')
+                  ]
+
+
+    feeds = [
+	(u'Em cima da hora', u'http://feeds.folha.uol.com.br/emcimadahora/rss091.xml')
+	,(u'Ambiente', u'http://feeds.folha.uol.com.br/ambiente/rss091.xml')
+	,(u'Bichos', u'http://feeds.folha.uol.com.br/bichos/rss091.xml')
+	,(u'Poder', u'http://feeds.folha.uol.com.br/poder/rss091.xml')
+	,(u'Ciencia', u'http://feeds.folha.uol.com.br/ciencia/rss091.xml')
+	,(u'Cotidiano', u'http://feeds.folha.uol.com.br/cotidiado/rss091.xml')
+	,(u'Saber', u'http://feeds.folha.uol.com.br/saber/rss091.xml')
+	,(u'Equilíbrio e Saúde', u'http://feeds.folha.uol.com.br/equilibrioesaude/rss091.xml')
+	,(u'Esporte', u'http://feeds.folha.uol.com.br/esporte/rss091.xml')
+	,(u'Ilustrada', u'http://feeds.folha.uol.com.br/ilustrada/rss091.xml')
+	,(u'Ilustríssima', u'http://feeds.folha.uol.com.br/ilustrissima/rss091.xml')
+	,(u'Mercado', u'http://feeds.folha.uol.com.br/mercado/rss091.xml')
+	,(u'Mundo', u'http://feeds.folha.uol.com.br/mundo/rss091.xml')
+	,(u'Tec', u'http://feeds.folha.uol.com.br/tec/rss091.xml')
+	,(u'Turismo', u'http://feeds.folha.uol.com.br/turismo/rss091.xml')
+            ]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+
+    language = 'pt'