Quote:
Originally Posted by GPThomson
|
Here goes first:
Code:
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
demorgen.be
'''
from calibre.web.feeds.news import BasicNewsRecipe
class dmg(BasicNewsRecipe):
title = u'DeMorgen.be'
__author__ = u'Darko Miletic'
description = u'news from Belgium'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
keep_only_tags = [dict(name='div' , attrs={'class':'art_box2'})]
feeds = [
(u'Nieuws' , u'http://www.demorgen.be/nieuws/rss.xml' )
,(u'De Gedachte' , u'http://www.demorgen.be/degedachte/rss.xml' )
,(u'Financiele morgen' , u'http://www.demorgen.be/financielemorgen/rss.xml')
,(u'Financiele morgen' , u'http://www.demorgen.be/financielemorgen/rss.xml')
,(u'Sport' , u'http://www.demorgen.be/sport/rss.xml' )
,(u'Bis' , u'http://www.demorgen.be/bis/rss.xml' )
,(u'Magazine' , u'http://www.demorgen.be/magazine/rss.xml' )
,(u'De stand der dingen', u'http://www.demorgen.be/standderdingen/rss.xml' )
]
Quote:
Originally Posted by GPThomson
|
This one was a bit harder to do:
Code:
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
standaard.be
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Destandaard(BasicNewsRecipe):
title = u'De Standaard'
__author__ = u'Darko Miletic'
description = u'news from Belgium'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
keep_only_tags = [dict(name='div' , attrs={'id':'_parts_midContainer_div'})]
remove_tags_after = dict(name='h3', attrs={'title':'Binnenland'})
remove_tags = [
dict(name='h3' , attrs={'title':'Binnenland' })
,dict(name='p' , attrs={'class':'by' })
,dict(name='div' , attrs={'class':'articlesright'})
,dict(name='a' , attrs={'class':'help' })
,dict(name='a' , attrs={'class':'archive' })
,dict(name='a' , attrs={'class':'print' })
,dict(name='a' , attrs={'class':'email' })
]
feeds = [
(u'De Standaard Online', u'http://feeds.feedburner.com/dso-front')
]