home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Chip 2011 November
/
CHIP_2011_11.iso
/
Programy
/
Narzedzia
/
Calibre
/
calibre-0.8.18.msi
/
file_280
/
telepolis.recipe
< prev
next >
Wrap
Text File
|
2011-09-09
|
2KB
|
47 lines
# -*- coding: utf-8 -*-
from calibre.web.feeds.news import BasicNewsRecipe
class TelepolisNews(BasicNewsRecipe):
title = u'Telepolis (News+Artikel)'
__author__ = 'syntaxis'
publisher = 'Heise Zeitschriften Verlag GmbH & Co KG'
description = 'News from Telepolis'
category = 'news'
oldest_article = 7
max_articles_per_feed = 100
recursion = 0
no_stylesheets = True
encoding = "utf-8"
language = 'de'
remove_empty_feeds = True
keep_only_tags = [dict(name = 'div',attrs={'class':'head'}),dict(name = 'div',attrs={'class':'leftbox'}),dict(name='td',attrs={'class':'strict'})]
remove_tags = [ dict(name='td',attrs={'class':'blogbottom'}),
dict(name='div',attrs={'class':'forum'}), dict(name='div',attrs={'class':'social'}),dict(name='div',attrs={'class':'blog-letter p-news'}),
dict(name='div',attrs={'class':'blog-sub'}),dict(name='div',attrs={'class':'version-div'}),dict(name='div',attrs={'id':'breadcrumb'})
,dict(attrs={'class':'tp-url'}),dict(attrs={'class':'blog-name entry_'}) ]
remove_tags_after = [dict(name='span', attrs={'class':['breadcrumb']})]
feeds = [(u'News', u'http://www.heise.de/tp/news-atom.xml')]
html2lrf_options = [
'--comment' , description
, '--category' , category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
soup.head.insert(0,mtag)
return soup