From ef0036ce4fd8f7774237df56c52547629839ab58 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Tue, 4 Oct 2011 10:51:12 -0600 Subject: [PATCH] Fix FAZ.net --- recipes/faznet.recipe | 51 +++++++++++-------------------------------- 1 file changed, 13 insertions(+), 38 deletions(-) diff --git a/recipes/faznet.recipe b/recipes/faznet.recipe index 742c6f4431..720993cfbb 100644 --- a/recipes/faznet.recipe +++ b/recipes/faznet.recipe @@ -19,45 +19,20 @@ class FazNet(BasicNewsRecipe): no_stylesheets = True encoding = 'utf-8' remove_javascript = True - - html2lrf_options = [ - '--comment', description - , '--category', category - , '--publisher', publisher - ] - - 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']), - ] + auto_cleanup = True + auto_cleanup_keep_tags = '//div[@class="FAZArtikelEinleitung"]' 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') + ('FAZ.NET Aktuell', 'http://www.faz.net/aktuell/?rssview=1'), + ('Politik', 'http://www.faz.net/aktuell/politik/?rssview=1'), + ('Wirtschaft', 'http://www.faz.net/aktuell/wirtschaft/?rssview=1'), + ('Feuilleton', 'http://www.faz.net/aktuell/feuilleton/?rssview=1'), + ('Sport', 'http://www.faz.net/aktuell/sport/?rssview=1'), + ('Gesellschaft', 'http://www.faz.net/aktuell/gesellschaft/?rssview=1'), + ('Finanzen', 'http://www.faz.net/aktuell/finanzen/?rssview=1'), + ('Technik & Motor', 'http://www.faz.net/aktuell/technik-motor/?rssview=1'), + ('Wissen', 'http://www.faz.net/aktuell/wissen/?rssview=1'), + ('Reise', 'http://www.faz.net/aktuell/reise/?rssview=1'), + ('Beruf & Chance', 'http://www.faz.net/aktuell/beruf-chance/?rssview=1') ] - def preprocess_html(self, soup): - mtag = '' - soup.head.insert(0,mtag) - del soup.body['onload'] - for item in soup.findAll(style=True): - del item['style'] - return soup