calibre/recipes/national_geographic_pl.recipe
2012-04-18 09:33:44 +05:30

86 lines
3.3 KiB
Plaintext

# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = 'Marcin Urban 2011'
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class recipeMagic(BasicNewsRecipe):
title = 'National Geographic PL'
__author__ = 'Marcin Urban 2011'
__modified_by__ = 'fenuks'
description = 'legenda wśród magazynów z historią sięgającą 120 lat'
#cover_url = 'http://www.guj.pl/var/guj/storage/images/media/nasze_magazyny/national_geographic/logo/ng_logo/2606-1-pol-PL/ng_logo.jpg'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
#delay = 1
use_embedded_content = False
encoding = 'utf8'
publisher = 'G+J Gruner+Jahr Polska'
category = 'news, PL,'
language = 'pl'
publication_type = 'newsportal'
extra_css = ''' body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
h1{text-align: center;}
h2{font-size: medium; font-weight: bold;}
.authordate {font-size: small; color: #696969;}
p.lead {font-weight: bold; text-align: center;}
.fot{font-size: x-small; color: #666666;} '''
preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
,'linearize_tables': True
}
remove_tags = [
dict(name='div', attrs={'class':'add_inf'}),
dict(name='div', attrs={'class':'add_f'}),
]
remove_attributes = ['width','height']
feeds=[]
def find_articles(self, url):
articles = []
soup=self.index_to_soup(url)
tag=soup.find(attrs={'class':'arl'})
art=tag.ul.findAll('li')
for i in art:
title=i.a['title']
url=i.a['href']
#date=soup.find(id='footer').ul.li.string[41:-1]
desc=i.div.p.string
articles.append({'title' : title,
'url' : url,
'date' : '',
'description' : desc
})
return articles
def parse_index(self):
feeds = []
feeds.append((u"Aktualności", self.find_articles('http://www.national-geographic.pl/aktualnosci/')))
feeds.append((u"Artykuły", self.find_articles('http://www.national-geographic.pl/artykuly/')))
return feeds
def print_version(self, url):
if 'artykuly' in url:
return url.replace('artykuly/pokaz', 'drukuj-artykul')
elif 'aktualnosci' in url:
return url.replace('aktualnosci/pokaz', 'drukuj-artykul')
else:
return url
def get_cover_url(self):
soup = self.index_to_soup('http://www.national-geographic.pl/biezace-wydania/')
tag=soup.find(attrs={'class':'txt jus'})
self.cover_url=tag.img['src']
return getattr(self, 'cover_url', self.cover_url)