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

Noticias R7 by Diniz Bortolotto

Browse Source
This commit is contained in:
Kovid Goyal 2011-06-16 01:13:00 -06:00
parent 2704b4ff26
commit d925732543
1 changed files with 40 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
recipes/noticias_r7.recipe Normal file
View File

@ -0,0 +1,40 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class PortalR7(BasicNewsRecipe):
title = 'Noticias R7'
__author__ = 'Diniz Bortolotto'
description = 'Noticias Portal R7'
oldest_article = 2
max_articles_per_feed = 20
encoding = 'utf8'
publisher = 'Rede Record'
category = 'news, Brazil'
language = 'pt_BR'
publication_type = 'newsportal'
use_embedded_content = False
no_stylesheets = True
remove_javascript = True
remove_attributes = ['style']
feeds = [
(u'Brasil', u'http://www.r7.com/data/rss/brasil.xml'),
(u'Economia', u'http://www.r7.com/data/rss/economia.xml'),
(u'Internacional', u'http://www.r7.com/data/rss/internacional.xml'),
(u'Tecnologia e Ci\xeancia', u'http://www.r7.com/data/rss/tecnologiaCiencia.xml')
]
reverse_article_order = True
keep_only_tags = [dict(name='div', attrs={'class':'materia'})]
remove_tags = [
dict(id=['espalhe', 'report-erro']),
dict(name='ul', attrs={'class':'controles'}),
dict(name='ul', attrs={'class':'relacionados'}),
dict(name='div', attrs={'class':'materia_banner'}),
dict(name='div', attrs={'class':'materia_controles'})
]
preprocess_regexps = [
(re.compile(r'<div class="materia">.*<div class="materia_cabecalho">',re.DOTALL|re.IGNORECASE),
lambda match: '<div class="materia"><div class="materia_cabecalho">')
]