Code:
import string, re
from calibre import strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Technology Review'
__author__ = 'schuster'
remove_tags_before = dict(id='keywords')
remove_tags_after = dict(id='kommentar')
remove_tags = [dict(attrs={'class':['navi_oben_pvg', 'navi_oben_tarifr', 'navi_oben_itm', 'navi_oben_eve', 'navi_oben_whi', 'navi_oben_abo', 'navi_oben_shop', 'navi_top_logo', 'navi_top_abschnitt', 'first']}),
dict(id=['footer', 'toolsRight', 'articleInline', 'navigation', 'archive', 'side_search', 'blog_sidebar', 'side_tool', 'side_index']),
dict(name=['script', 'noscript', 'style'])]
oldest_article = 4
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'de'
remove_javascript = True
def print_version(self, url):
return url + '?view=print'
feeds = [
(u'Technik News', u'http://www.heise.de/tr/news-atom.xml') ]