calibre/resources/recipes/nspm.recipe

73 lines
3.0 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
nspm.rs
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Nspm(BasicNewsRecipe):
title = 'Nova srpska politicka misao'
__author__ = 'Darko Miletic'
description = 'Casopis za politicku teoriju i drustvena istrazivanja'
publisher = 'NSPM'
category = 'news, politics, Serbia'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
INDEX = 'http://www.nspm.rs/?alphabet=l'
encoding = 'utf-8'
language = 'sr'
publication_type = 'magazine'
masthead_url = 'http://www.nspm.rs/templates/jsn_epic_pro/images/logol.jpg'
extra_css = ' @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: "Times New Roman", serif1, serif} .article_description{font-family: Arial, sans1, sans-serif} img{margin-top:0.5em; margin-bottom: 0.7em} .author{color: #990000; font-weight: bold} .author,.createdate{font-size: 0.9em} img{margin-top:0.5em; margin-bottom: 0.7em} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
remove_tags = [
dict(name=['link','object','embed','script','meta'])
,dict(name='td', attrs={'class':'buttonheading'})
]
keep_only_tags = [
dict(attrs={'class':['contentpagetitle','author','createdate']})
,dict(name='p')
]
remove_attributes = ['width','height']
def get_browser(self):
br = BasicNewsRecipe.get_browser()
br.open(self.INDEX)
return br
feeds = [(u'Nova srpska politicka misao', u'http://www.nspm.rs/feed/rss.html')]
def print_version(self, url):
return url.replace('.html','/stampa.html')
def preprocess_html(self, soup):
for item in soup.body.findAll(style=True):
del item['style']
att = soup.find('a',attrs={'class':'contentpagetitle'})
if att:
att.name = 'h1';
del att['href']
att2 = soup.find('td')
if att2:
att2.name = 'p';
del att['valign']
for pt in soup.findAll('img'):
brtag = Tag(soup,'br')
brtag2 = Tag(soup,'br')
pt.append(brtag)
pt.append(brtag2)
return soup