Updated faz.net

This commit is contained in:
Kovid Goyal 2011-05-27 09:50:47 -06:00
parent 44f1d19cda
commit e097f907fe

View File

@ -1,35 +1,63 @@
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
__license__ = 'GPL v3'
__copyright__ = '2008-2011, Kovid Goyal <kovid at kovidgoyal.net>, Darko Miletic <darko at gmail.com>'
'''
Profile to download FAZ.NET
'''
title = u'Faz.net'
__author__ = 'schuster'
oldest_article = 1
from calibre.web.feeds.news import BasicNewsRecipe
class FazNet(BasicNewsRecipe):
title = 'FAZ.NET'
__author__ = 'Kovid Goyal, Darko Miletic'
description = 'Frankfurter Allgemeine Zeitung'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'de'
remove_javascript = True
cover_url = 'http://www.faz.net/f30/Images/Logos/logo.gif'
publisher = 'Frankfurter Allgemeine Zeitung GmbH'
category = 'news, politics, Germany'
use_embedded_content = False
language = 'de'
remove_tags = [dict(attrs={'class':['LinkBoxModulSmall', 'ModulLesermeinungenFooter', 'ModulArtikelServices', 'SocialMediaUnten', 'ArrowLinkRight', 'ModulVerlagsInfo', 'AdData', 'FazFooter', 'Date']}),
dict(id=['FAZNavHeader', 'FAZNavMain', 'RightColumn', 'FazFooter', 'BreadCrumbs', 'FAZNavSubMain', 'FAZImgEvent']),
dict(name=['jksrdt'])]
max_articles_per_feed = 30
no_stylesheets = True
encoding = 'utf-8'
remove_javascript = True
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
feeds = [(u'Politik', u'http://www.faz.net/s/RubA24ECD630CAE40E483841DB7D16F4211/Tpl~Epartner~SRss_.xml'),
(u'Wirtschaft', u'http://www.faz.net/s/RubC9401175958F4DE28E143E68888825F6/Tpl~Epartner~SRss_.xml'),
(u'Feuilleton', u'http://www.faz.net/s/RubCC21B04EE95145B3AC877C874FB1B611/Tpl~Epartner~SRss_.xml'),
(u'Sport', u'http://www.faz.net/s/Rub9F27A221597D4C39A82856B0FE79F051/Tpl~Epartner~SRss_.xml'),
(u'Gesellschaft', u'http://www.faz.net/s/Rub02DBAA63F9EB43CEB421272A670A685C/Tpl~Epartner~SRss_.xml'),
(u'Finanzen', u'http://www.faz.net/s/Rub4B891837ECD14082816D9E088A2D7CB4/Tpl~Epartner~SRss_.xml'),
(u'Wissen', u'http://www.faz.net/s/Rub7F4BEE0E0C39429A8565089709B70C44/Tpl~Epartner~SRss_.xml'),
(u'Reise', u'http://www.faz.net/s/RubE2FB5CA667054BDEA70FB3BC45F8D91C/Tpl~Epartner~SRss_.xml'),
(u'Technik & Motor', u'http://www.faz.net/s/Rub01E4D53776494844A85FDF23F5707AD8/Tpl~Epartner~SRss_.xml'),
(u'Beruf & Chance', u'http://www.faz.net/s/RubB1E10A8367E8446897468EDAA6EA0504/Tpl~Epartner~SRss_.xml'),
(u'Kunstmarkt', u'http://www.faz.net/s/RubBC09F7BF72A2405A96718ECBFB68FBFE/Tpl~Epartner~SRss_.xml'),
(u'Immobilien ', u'http://www.faz.net/s/RubFED172A9E10F46B3A5F01B02098C0C8D/Tpl~Epartner~SRss_.xml'),
(u'Rhein-Main Zeitung', u'http://www.faz.net/s/RubABE881A6669742C2A5EBCB5D50D7EBEE/Tpl~Epartner~SRss_.xml'),
(u'Atomdebatte ', u'http://www.faz.net/s/Rub469C43057F8C437CACC2DE9ED41B7950/Tpl~Epartner~SRss_.xml')
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':'Article'})]
remove_tags = [
dict(name=['object','link','embed','base'])
,dict(name='div',
attrs={'class':['LinkBoxModulSmall','ModulVerlagsInfo',
'ArtikelServices', 'ModulLesermeinungenFooter',
'ModulArtikelServices', 'BoxTool Aufklappen_Grau',
'SocialMediaUnten', ]}),
dict(id=['KurzLinkMenu', 'ArtikelServicesMenu']),
]
feeds = [
('FAZ.NET Aktuell', 'http://www.faz.net/s/RubF3CE08B362D244869BE7984590CB6AC1/Tpl~Epartner~SRss_.xml'),
('Politik', 'http://www.faz.net/s/RubA24ECD630CAE40E483841DB7D16F4211/Tpl~Epartner~SRss_.xml'),
('Wirtschaft', 'http://www.faz.net/s/RubC9401175958F4DE28E143E68888825F6/Tpl~Epartner~SRss_.xml'),
('Feuilleton', 'http://www.faz.net/s/RubCC21B04EE95145B3AC877C874FB1B611/Tpl~Epartner~SRss_.xml'),
('Sport', 'http://www.faz.net/s/Rub9F27A221597D4C39A82856B0FE79F051/Tpl~Epartner~SRss_.xml'),
('Gesellschaft', 'http://www.faz.net/s/Rub02DBAA63F9EB43CEB421272A670A685C/Tpl~Epartner~SRss_.xml'),
('Finanzen', 'http://www.faz.net/s/Rub4B891837ECD14082816D9E088A2D7CB4/Tpl~Epartner~SRss_.xml'),
('Wissen', 'http://www.faz.net/s/Rub7F4BEE0E0C39429A8565089709B70C44/Tpl~Epartner~SRss_.xml'),
('Reise', 'http://www.faz.net/s/RubE2FB5CA667054BDEA70FB3BC45F8D91C/Tpl~Epartner~SRss_.xml'),
('Technik & Motor', 'http://www.faz.net/s/Rub01E4D53776494844A85FDF23F5707AD8/Tpl~Epartner~SRss_.xml'),
('Beruf & Chance', 'http://www.faz.net/s/RubB1E10A8367E8446897468EDAA6EA0504/Tpl~Epartner~SRss_.xml')
]
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'
soup.head.insert(0,mtag)
del soup.body['onload']
for item in soup.findAll(style=True):
del item['style']
return soup