New recipes for Dagens Nyheter and Svenska Dagbladet by Darko Miletic

This commit is contained in:
Kovid Goyal 2009-10-20 17:41:35 -06:00
parent 83247f8e3e
commit ed17c42def
4 changed files with 102 additions and 0 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 628 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 427 B

View File

@ -0,0 +1,49 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
dn.se
'''
from calibre.web.feeds.news import BasicNewsRecipe
class DN_se(BasicNewsRecipe):
title = 'Dagens Nyheter'
__author__ = 'Darko Miletic'
description = 'News from Sveden'
publisher = 'Dagens Nyheter'
category = 'news, politics, Sveden'
oldest_article = 2
delay = 1
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'sv'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
feeds = [
(u'Nyheter', u'http://www.dn.se/m/rss/toppnyheter')
,(u'Ekonomi', u'http://www.dn.se/ekonomi-rss' )
,(u'Sport' , u'http://www.dn.se/sport-rss' )
,(u'Debatt' , u'http://www.dn.se/debatt-rss' )
,(u'Ledare' , u'http://www.dn.se/ledare-rss' )
,(u'Kultur' , u'http://www.dn.se/kultur-rss' )
]
keep_only_tags = [dict(name='div', attrs={'id':'article'})]
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div',attrs={'id':'byline'})
remove_tags = [
dict(name=['object','link','base'])
,dict(name='div',attrs={'id':'hook'})
]

View File

@ -0,0 +1,53 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
svd.se
'''
from calibre.web.feeds.news import BasicNewsRecipe
class SVD_se(BasicNewsRecipe):
title = 'Svenska Dagbladet'
__author__ = 'Darko Miletic'
description = 'News from Sveden'
publisher = 'Svenska Dagbladet'
category = 'news, politics, Sveden'
oldest_article = 2
delay = 1
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'sv'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
feeds = [
(u'Toppnyheter' , u'http://www.svd.se/?service=rss' )
,(u'Inrikes' , u'http://www.svd.se/nyheter/inrikes/?service=rss' )
,(u'Utrikes' , u'http://www.svd.se/nyheter/utrikes/?service=rss' )
,(u'Politik' , u'http://www.svd.se/nyheter/politik/?service=rss' )
,(u'Idagsidan ' , u'http://www.svd.se/nyheter/idagsidan/?service=rss' )
,(u'Vetenskap' , u'http://www.svd.se/nyheter/vetenskap/?service=rss' )
,(u'Sport' , u'http://www.svd.se/sportspel/nyheter/?service=rss' )
,(u'Opinion' , u'http://www.svd.se/opinion/startsidan/?service=rss')
,(u'Kultur' , u'http://www.svd.se/kulturnoje/nyheter/?service=rss')
]
keep_only_tags = [dict(name='div', attrs={'id':'articlecontent'})]
remove_tags_after = dict(name='div',attrs={'class':'articlebody normal'})
remove_tags = [
dict(name=['object','link','base'])
,dict(name='div',attrs={'class':['articlead','factcolumn']})
,dict(name='ul', attrs={'class':'toolbar articletop clearfix'})
,dict(name='p', attrs={'class':'more'})
]