mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
50 lines
1.3 KiB
Python
50 lines
1.3 KiB
Python
#!/usr/bin/env python2
|
|
# -*- coding: utf-8 -*-
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = u'Łukasz Grąbczewski 2012-2013'
|
|
__version__ = '1.2'
|
|
|
|
'''
|
|
zw.com.pl
|
|
'''
|
|
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class zyciewarszawy(BasicNewsRecipe):
|
|
__author__ = u'Łukasz Grączewski'
|
|
title = u'Życie Warszawy'
|
|
description = u'Wiadomości z Warszawy'
|
|
language = 'pl'
|
|
publisher = 'Presspublica'
|
|
publication_type = 'newspaper'
|
|
masthead_url = 'http://www.zw.com.pl/static/img/logo_zw.gif'
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
use_embedded_content = False
|
|
remove_empty_feeds = True
|
|
|
|
oldest_article = 1.5 #last 36h
|
|
max_articles_per_feed = 100
|
|
|
|
feeds = [(u'Najnowsze', u'http://www.zw.com.pl/rss/1.html')]
|
|
|
|
keep_only_tags = []
|
|
keep_only_tags.append(dict(name = 'div', attrs = {'id' : 'storyp'}))
|
|
|
|
remove_tags = []
|
|
remove_tags.append(dict(attrs = {'class' : 'author'}))
|
|
remove_tags.append(dict(attrs = {'class' : 'more'}))
|
|
remove_tags.append(dict(attrs = {'class' : 'clr'}))
|
|
remove_tags.append(dict(attrs = {'id' : 'adk_0'}))
|
|
remove_tags.append(dict(attrs = {'id' : 'adsense_0'}))
|
|
remove_tags.append(dict(attrs = {'id' : 'share_bottom'}))
|
|
remove_tags.append(dict(attrs = {'id' : 'copyright_law'}))
|
|
|
|
preprocess_regexps = [(re.compile(r',3.jpg'), lambda m: ',2.jpg')]
|
|
|
|
def print_version(self, url):
|
|
url += "?print=tak"
|
|
return url
|