mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
66 lines
2.4 KiB
Python
66 lines
2.4 KiB
Python
#!/usr/bin/env python2
|
|
# -*- coding: utf-8 -*-
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = u'2011, Silviu Cotoar\u0103'
|
|
'''
|
|
pcworld.ro
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class Pcworld(BasicNewsRecipe):
|
|
title = u'PC World'
|
|
__author__ = u'Silviu Cotoar\u0103'
|
|
description = u'IT'
|
|
publisher = u'PC World'
|
|
oldest_article = 25
|
|
language = 'ro'
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
category = 'Ziare,Stiri,IT'
|
|
encoding = 'utf-8'
|
|
cover_url = 'http://www.pcworld.ro/img/ui/header-logo.gif'
|
|
|
|
conversion_options = {
|
|
'comments': description, 'tags': category, 'language': language, 'publisher': publisher
|
|
}
|
|
|
|
extra_css = '''
|
|
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
|
|
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
|
.byline {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
|
|
.date {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
|
|
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
|
.copyright {font-family:Arial,Helvetica,sans-serif;font-size:xx-small;text-align:center}
|
|
.story{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
|
.entry-asset asset hentry{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
|
.pagebody{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
|
.maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
|
.story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
|
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
|
|
'''
|
|
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'id': 'content_page'}), dict(
|
|
name='div', attrs={'class': 'box_center content_body'})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name='h3', attrs={'class': ['breadcrumb']}), dict(
|
|
name='div', attrs={'class': ['box_center voteaza']})
|
|
]
|
|
|
|
remove_tags_after = [
|
|
dict(name='div', attrs={'class': ['box_center voteaza']})
|
|
]
|
|
|
|
feeds = [
|
|
(u'Feeds', u'http://www.pcworld.ro/contents/pcworld.rss')
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
return self.adeify_images(soup)
|