Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #786293 (Updated recipe for Marca website)

Browse Source
This commit is contained in:
Kovid Goyal 2011-05-21 14:19:26 -06:00
parent d4f79884a4
commit 746b9b1d63
2 changed files with 19 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
recipes/icons/marca.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 293 B

44
recipes/marca.recipe
View File

@ -1,14 +1,11 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3' __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 www.marca.com
''' '''
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Marca(BasicNewsRecipe): class Marca(BasicNewsRecipe):
title = 'Marca' title = 'Marca'
@ -22,35 +19,30 @@ class Marca(BasicNewsRecipe):
use_embedded_content = False use_embedded_content = False
delay = 1 delay = 1
encoding = 'iso-8859-15' 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']})]
keep_only_tags = [dict(name='div', attrs={'class':['cab_articulo','cuerpo_articulo']})]
remove_attributes = ['lang']
remove_tags = [ remove_tags = [
dict(name=['object','link','script']) dict(name=['object','link','script','embed','iframe','meta','base'])
,dict(name='div', attrs={'class':['colC','peu']}) ,dict(name='div', attrs={'class':'tabs'})
,dict(name='div', attrs={'class':['utilidades estirar','bloque_int_corr estirar']})
] ]
remove_tags_after = [dict(name='div', attrs={'class':'bloque_int_corr estirar'})]
def preprocess_html(self, soup): 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): for item in soup.findAll(style=True):
del item['style'] del item['style']
return soup return soup
def get_article_url(self, article):
return article.get('guid', None)