Hi,
my old first attempt to get scinexx was of course quite wrong,
but nobody complaint about that up to now anyways.
However, to finish this, here's my actual version. Maybe somebody who knows s'thing about python might have a short look at it, to make things more smooth...
LG Londo
Code:
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1265145870(BasicNewsRecipe):
title = u'Scinexx.de'
language = 'de'
__author__ = 'Recipe by JSuer'
cover_url = 'http://www.g-o.de/grafiken/web_scinexx/head2.gif'
oldest_article = 14
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'ISO-8859-1'
# encoding = 'utf-8'
feeds = [(u'Scinexx.de', u'http://feeds.feedburner.com/scinexx')]
remove_tags = [{'class':['text1fett']}]
remove_tags = [{'href':['javascript:window.print()']}]
extra_css = '''
.text2normal{font-family:Verdana,Geneva,Kalimati,sans-serif; font-size:x-small;}
.text1normalblau{font-family:Verdana,Geneva,Kalimati,sans-serif; font-size:small;}
.text1fett{font-color:grey; font-size:small;}
.titel1{font-family:Georgia,"Times New Roman",Times,serif; font-size:large;}
.titel2{font-family:Georgia,"Times New Roman",Times,serif; }
.titel3{font-family:Georgia,"Times New Roman",Times,serif; font-size:larger;}
h1{font-size:large;}
'''
def print_version(self, url):
id_start = url.rfind('2010') - 6
id_end = id_start + 5
id = url[id_start : id_end]
result = 'http://www.scinexx.de/inc/artikel_drucken.php?id=' + id + '&a_flag=1'
return result