Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improved telepolis

Browse Source
This commit is contained in:
Kovid Goyal 2010-11-21 19:18:33 -07:00
parent fc524ee7d4
commit 27d52c02eb
1 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
resources/recipes/telepolis.recipe
View File

@ -3,12 +3,12 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Gerhard Aigner <gerhard.aigner at gmail.com>' __copyright__ = '2009, Gerhard Aigner <gerhard.aigner at gmail.com>'
''' http://www.derstandard.at - Austrian Newspaper '''
import re 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)' title = u'Telepolis (News+Artikel)'
__author__ = 'Gerhard Aigner' __author__ = 'Gerhard Aigner'
publisher = 'Heise Zeitschriften Verlag GmbH & Co KG' publisher = 'Heise Zeitschriften Verlag GmbH & Co KG'
description = 'News from telepolis' description = 'News from telepolis'
@ -20,16 +20,16 @@ class TelepolisNews(BasicNewsRecipe):
encoding = "utf-8" encoding = "utf-8"
language = 'de_AT' language = 'de_AT'
use_embedded_content = False use_embedded_content =False
remove_empty_feeds = True remove_empty_feeds = True
preprocess_regexps = [(re.compile(r'<a[^>]*>', re.DOTALL|re.IGNORECASE), lambda match: ''), preprocess_regexps = [(re.compile(r'<a[^>]*>', re.DOTALL|re.IGNORECASE), lambda match: ''),
(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 = 'table',attrs={'class':'blogtable'})] 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'})] remove_tags = [dict(name='img'), dict(name='td',attrs={'class':'blogbottom'}), dict(name='td',attrs={'class':'forum'})]
feeds = [(u'News', u'http://www.heise.de/tp/news.rdf')] feeds = [(u'News', u'http://www.heise.de/tp/news-atom.xml')]
html2lrf_options = [ html2lrf_options = [
'--comment' , description '--comment' , description
@ -41,7 +41,7 @@ class TelepolisNews(BasicNewsRecipe):
def get_article_url(self, article): def get_article_url(self, article):
'''if the linked article is of kind artikel don't take it''' '''if the linked article is of kind artikel don't take it'''
if (article.link.count('artikel') > 0) : if (article.link.count('artikel') > 1) :
return None return None
return article.link return article.link
@ -49,3 +49,5 @@ class TelepolisNews(BasicNewsRecipe):
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