Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Updated Telepolis

Browse Source
This commit is contained in:
Kovid Goyal 2011-05-09 08:42:55 -06:00
parent a558cd0d2a
commit d995b59ce5
1 changed files with 12 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
recipes/telepolis.recipe
View File

@ -1,17 +1,12 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2009, Gerhard Aigner <gerhard.aigner at gmail.com>'
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class TelepolisNews(BasicNewsRecipe): class TelepolisNews(BasicNewsRecipe):
title = u'Telepolis (News+Artikel)' title = u'Telepolis (News+Artikel)'
__author__ = 'Gerhard Aigner' __author__ = 'syntaxis'
publisher = 'Heise Zeitschriften Verlag GmbH & Co KG' publisher = 'Heise Zeitschriften Verlag GmbH & Co KG'
description = 'News from telepolis' description = 'News from Telepolis'
category = 'news' category = 'news'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
@ -20,14 +15,19 @@ class TelepolisNews(BasicNewsRecipe):
encoding = "utf-8" encoding = "utf-8"
language = 'de' language = 'de'
use_embedded_content =False
remove_empty_feeds = True remove_empty_feeds = True
preprocess_regexps = [(re.compile(r'<a[^>]*>', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(r'</a>', re.DOTALL|re.IGNORECASE), lambda match: ''),]
keep_only_tags = [dict(name = 'td',attrs={'class':'bloghead'}),dict(name = 'td',attrs={'class':'blogfliess'})]
remove_tags = [dict(name='img'), dict(name='td',attrs={'class':'blogbottom'}), dict(name='td',attrs={'class':'forum'})] 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')] feeds = [(u'News', u'http://www.heise.de/tp/news-atom.xml')]
@ -39,15 +39,8 @@ class TelepolisNews(BasicNewsRecipe):
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
def get_article_url(self, article):
'''if the linked article is of kind artikel don't take it'''
if (article.link.count('artikel') > 1) :
return None
return article.link
def preprocess_html(self, soup): def preprocess_html(self, soup):
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">' mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
soup.head.insert(0,mtag) soup.head.insert(0,mtag)
return soup return soup