Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update O Globo

Browse Source
This commit is contained in:
Kovid Goyal 2012-06-23 09:46:02 +05:30
parent 5dc832354c
commit dc2fc23d3c
2 changed files with 23 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
recipes/bbc_brasil.recipe
View File

@ -147,7 +147,7 @@ class BBCBrasilRecipe(BasicNewsRecipe):
# Author of this recipe.
__author__ = 'claviola'
__author__ = 'Carlos Laviola'
# Specify English as the language of the RSS feeds (ISO-639 code).
language = 'en_GB'

52
recipes/o_globo.recipe
View File

@ -1,4 +1,4 @@
#!/usr/bin/env python
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
@ -10,11 +10,11 @@ from calibre.web.feeds.news import BasicNewsRecipe
class OGlobo(BasicNewsRecipe):
title = 'O Globo'
__author__ = 'Darko Miletic and Sujata Raman'
__author__ = 'Darko Miletic and Carlos Laviola'
description = 'News from Brasil'
publisher = 'O Globo'
category = 'news, politics, Brasil'
oldest_article = 2
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
@ -35,47 +35,39 @@ class OGlobo(BasicNewsRecipe):
body{font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
h3{font-size:large; color:#082963; font-weight:bold;}
#ident{color:#0179B4; font-size:xx-small;}
p{color:#000000;font-weight:normal;}
p{color:#000000;font-weight:normal;}
.commentario p{color:#007BB5; font-style:italic;}
'''
keep_only_tags = [dict(name='div', attrs={'id':'ltintb'}),
dict(name='a', attrs={'class':['img imgLoader','img ftr imgLoader']}),]
remove_tags = [
dict(name='script')
,dict(name='object')
,dict(name='form')
,dict(name='div', attrs={'id':['linksPatGoogle','rdpm','cor','com','env','rcm_st','coment',]})
,dict(name='div', attrs={'class':'box-zap-anu2'})
,dict(name='a', attrs={'class':'assine'})
,dict(name='link')
,dict(name='div', attrs={'id':'header'})
,dict(name='p', attrs={'id':'info-date-press'})
]
feeds = [
(u'Todos os canais', u'http://oglobo.globo.com/rss/plantao.xml')
,(u'Ciencia', u'http://oglobo.globo.com/rss/plantaociencia.xml')
,(u'Educacao', u'http://oglobo.globo.com/rss/plantaoeducacao.xml')
,(u'Opiniao', u'http://oglobo.globo.com/rss/plantaoopiniao.xml')
,(u'Sao Paulo', u'http://oglobo.globo.com/rss/plantaosaopaulo.xml')
,(u'Viagem', u'http://oglobo.globo.com/rss/plantaoviagem.xml')
,(u'Cultura', u'http://oglobo.globo.com/rss/plantaocultura.xml')
,(u'Esportes', u'http://oglobo.globo.com/rss/plantaoesportes.xml')
,(u'Mundo', u'http://oglobo.globo.com/rss/plantaomundo.xml')
,(u'Pais', u'http://oglobo.globo.com/rss/plantaopais.xml')
,(u'Rio', u'http://oglobo.globo.com/rss/plantaorio.xml')
,(u'Saude', u'http://oglobo.globo.com/rss/plantaosaude.xml')
,(u'Viver Melhor', u'http://oglobo.globo.com/rss/plantaovivermelhor.xml')
,(u'Economia', u'http://oglobo.globo.com/rss/plantaoeconomia.xml')
,(u'Tecnologia', u'http://oglobo.globo.com/rss/plantaotecnologia.xml')
(u'Todos os canais', u'http://oglobo.globo.com/rss.xml?completo=true')
,(u'Ciencia', u'http://oglobo.globo.com/rss.xml?secao=ciencia&completo=true')
,(u'Educacao', u'http://oglobo.globo.com/rss.xml?secao=educacao&completo=true')
,(u'Opiniao', u'http://oglobo.globo.com/rss.xml?secao=opiniao&completo=true')
,(u'Cultura', u'http://oglobo.globo.com/rss.xml?secao=cultura&completo=true')
,(u'Esportes', u'http://oglobo.globo.com/rss.xml?secao=esportes&completo=true')
,(u'Mundo', u'http://oglobo.globo.com/rss.xml?secao=mundo&completo=true')
,(u'Pais', u'http://oglobo.globo.com/rss.xml?secao=pais&completo=true')
,(u'Rio', u'http://oglobo.globo.com/rss.xml?secao=rio&completo=true')
,(u'Saude', u'http://oglobo.globo.com/rss.xml?secao=saude&completo=true')
,(u'Economia', u'http://oglobo.globo.com/rss.xml?secao=economia&completo=true')
,(u'Tecnologia', u'http://oglobo.globo.com/rss.xml?secao=tecnologia&completo=true')
]
def print_version(self, url):
return url + '?service=print'
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup
language = 'pt'
language = 'pt_BR'