calibre/recipes/focus_pl.recipe
2011-12-18 08:33:31 +05:30

84 lines
3.4 KiB
Plaintext

import re
from calibre.web.feeds.news import BasicNewsRecipe
class FocusRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = u'intromatyk <intromatyk@gmail.com>'
language = 'pl'
version = 1
title = u'Focus'
publisher = u'Gruner + Jahr Polska'
category = u'News'
description = u'Newspaper'
category='magazine'
cover_url=''
remove_empty_feeds= True
no_stylesheets=True
oldest_article = 7
max_articles_per_feed = 100000
recursions = 0
no_stylesheets = True
remove_javascript = True
encoding = 'utf-8'
# Seems to work best, but YMMV
simultaneous_downloads = 5
r = re.compile('.*(?P<url>http:\/\/(www.focus.pl)|(rss.feedsportal.com\/c)\/.*\.html?).*')
keep_only_tags =[]
keep_only_tags.append(dict(name = 'div', attrs = {'id' : 'cll'}))
remove_tags =[]
remove_tags.append(dict(name = 'div', attrs = {'class' : 'ulm noprint'}))
remove_tags.append(dict(name = 'div', attrs = {'class' : 'txb'}))
remove_tags.append(dict(name = 'div', attrs = {'class' : 'h2'}))
remove_tags.append(dict(name = 'ul', attrs = {'class' : 'txu'}))
remove_tags.append(dict(name = 'div', attrs = {'class' : 'ulc'}))
extra_css = '''
body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
h1{text-align: left;}
h2{font-size: medium; font-weight: bold;}
p.lead {font-weight: bold; text-align: left;}
.authordate {font-size: small; color: #696969;}
.fot{font-size: x-small; color: #666666;}
'''
feeds = [
('Nauka', 'http://focus.pl.feedsportal.com/c/32992/f/532693/index.rss'),
('Historia', 'http://focus.pl.feedsportal.com/c/32992/f/532694/index.rss'),
('Cywilizacja', 'http://focus.pl.feedsportal.com/c/32992/f/532695/index.rss'),
('Sport', 'http://focus.pl.feedsportal.com/c/32992/f/532696/index.rss'),
('Technika', 'http://focus.pl.feedsportal.com/c/32992/f/532697/index.rss'),
('Przyroda', 'http://focus.pl.feedsportal.com/c/32992/f/532698/index.rss'),
('Technologie', 'http://focus.pl.feedsportal.com/c/32992/f/532699/index.rss'),
]
def skip_ad_pages(self, soup):
if ('advertisement' in soup.find('title').string.lower()):
href = soup.find('a').get('href')
return self.index_to_soup(href, raw=True)
else:
return None
def get_cover_url(self):
soup=self.index_to_soup('http://www.focus.pl/magazyn/')
tag=soup.find(name='div', attrs={'class':'clr fl'})
if tag:
self.cover_url='http://www.focus.pl/' + tag.a['href']
return getattr(self, 'cover_url', self.cover_url)
def print_version(self, url):
if url.count ('focus.pl.feedsportal.com'):
u = url.find('focus0Bpl')
u = 'http://www.focus.pl/' + url[u + 11:]
u = u.replace('0C', '/')
u = u.replace('A', '')
u = u.replace ('0E','-')
u = u.replace('/nc/1//story01.htm', '/do-druku/1')
else:
u = url.replace('/nc/1','/do-druku/1')
return u