calibre/resources/recipes/24sata_rs.recipe

69 lines
2.5 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
24sata.rs
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Ser24Sata(BasicNewsRecipe):
title = '24 Sata - Sr'
__author__ = 'Darko Miletic'
description = '24 sata portal vesti iz Srbije'
publisher = 'Ringier d.o.o.'
category = 'news, politics, entertainment, Serbia'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
language = 'sr'
lang = 'sr-Latn-RS'
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif}'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : lang
, 'pretty_print' : True
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
feeds = [(u'Vesti Dana', u'http://www.24sata.rs/rss.php')]
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
attribs = [ 'style','font','valign'
,'colspan','width','height'
,'rowspan','summary','align'
,'cellspacing','cellpadding'
,'frames','rules','border'
]
for item in soup.body.findAll(name=['table','td','tr','th','caption','thead','tfoot','tbody','colgroup','col']):
item.name = 'div'
for attrib in attribs:
if item.has_key(attrib):
del item[attrib]
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
soup.head.insert(0,mlang)
soup.head.insert(1,mcharset)
return self.adeify_images(soup)
def print_version(self, url):
article = url.partition('#')[0]
article_id = article.partition('id=')[2]
return 'http://www.24sata.rs/_print.php?id=' + article_id