home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Chip 2011 November
/
CHIP_2011_11.iso
/
Programy
/
Narzedzia
/
Calibre
/
calibre-0.8.18.msi
/
file_280
/
cotidianul.recipe
< prev
next >
Wrap
Text File
|
2011-09-09
|
3KB
|
70 lines
# -*- coding: utf-8 -*-
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = u'2011, Silviu Cotoar\u0103'
'''
cotidianul.ro
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Cotidianul(BasicNewsRecipe):
title = u'Cotidianul'
__author__ = u'Silviu Cotoar\u0103'
description = u''
publisher = u'Cotidianul'
oldest_article = 25
language = 'ro'
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
category = 'Ziare,Stiri'
encoding = 'utf-8'
cover_url = 'http://www.cotidianul.ro/images/cotidianul.png'
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={'class':'titlu'})
, dict(name='div', attrs={'class':'gallery clearfix'})
, dict(name='div', attrs={'align':'justify'})
]
remove_tags = [
dict(name='div', attrs={'class':['space']})
, dict(name='div', attrs={'id':['title_desc']})
]
remove_tags_after = [
dict(name='div', attrs={'class':['space']})
, dict(name='span', attrs={'class':['date']})
]
feeds = [
(u'Feeds', u'http://www.cotidianul.ro/rssfeed/ToateStirile.xml')
]
def preprocess_html(self, soup):
return self.adeify_images(soup)