calibre/recipes/nin.recipe
2012-09-17 17:42:48 +05:30

102 lines
4.1 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>'
'''
www.nin.co.rs
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Nin(BasicNewsRecipe):
title = 'NIN online'
__author__ = 'Darko Miletic'
description = 'Nedeljne Informativne Novine'
publisher = 'NIN d.o.o. - Ringier d.o.o.'
category = 'news, politics, Serbia'
no_stylesheets = True
oldest_article = 15
encoding = 'utf-8'
needs_subscription = True
remove_empty_feeds = True
auto_cleanup = False
PREFIX = 'http://www.nin.co.rs'
INDEX = PREFIX + '/?change_lang=ls'
use_embedded_content = False
language = 'sr'
publication_type = 'magazine'
masthead_url = 'http://www.nin.co.rs/img/head/logo.jpg'
extra_css = """
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
body{font-family: Verdana, Lucida, sans1, sans-serif}
.article_description{font-family: Verdana, Lucida, sans1, sans-serif}
.artTitle{font-size: x-large; font-weight: bold; color: #900}
.izjava{font-size: x-large; font-weight: bold}
.columnhead{font-size: small; font-weight: bold;}
img{margin-top:0.5em; margin-bottom: 0.7em; display: block}
b{margin-top: 1em}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
preprocess_regexps = [
(re.compile(r'</body>.*?<html>', re.DOTALL|re.IGNORECASE),lambda match: '</body>')
,(re.compile(r'</html>.*?</html>', re.DOTALL|re.IGNORECASE),lambda match: '</html>')
,(re.compile(u'\u0110'), lambda match: u'\u00D0')
]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
br.open(self.INDEX)
br.select_form(name='form1')
br['login_name' ] = self.username
br['login_password'] = self.password
br.submit()
return br
keep_only_tags =[dict(name='td', attrs={'width':'520'})]
remove_tags_before =dict(name='span', attrs={'class':'izjava'})
remove_tags_after =dict(name='html')
remove_tags = [
dict(name=['object','link','iframe','meta','base'])
,dict(attrs={'class':['fb-like','twitter-share-button']})
,dict(attrs={'rel':'nofollow'})
]
remove_attributes=['border','background','height','width','align','valign']
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup(self.INDEX)
for item in soup.findAll('a', href=True):
if item['href'].startswith('/pages/issue.php?id='):
simg = item.find('img')
if simg:
return self.PREFIX + item.img['src']
return cover_url
feeds = [(u'NIN Online', u'http://www.nin.co.rs/misc/rss.php?feed=RSS2.0')]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('div'):
if len(item.contents) == 0:
item.extract()
for item in soup.findAll(['td','tr']):
item.name='div'
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
for tbl in soup.findAll('table'):
img = tbl.find('img')
if img:
img.extract()
tbl.replaceWith(img)
return soup