mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-12-25 06:17:21 -05:00
65 lines
2.7 KiB
Plaintext
65 lines
2.7 KiB
Plaintext
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
http://www.businessweek.com/magazine/news/articles/business_news.htm
|
|
'''
|
|
|
|
from calibre import strftime
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class BWmagazine(BasicNewsRecipe):
|
|
title = 'BusinessWeek Magazine'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Stay up to date with BusinessWeek magazine articles. Read news on international business, personal finances & the economy in the BusinessWeek online magazine.'
|
|
publisher = 'Bloomberg L.P.'
|
|
category = 'news, International Business News, current news in international business,international business articles, personal business, business week magazine, business week magazine articles, business week magazine online, business week online magazine'
|
|
oldest_article = 10
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
encoding = 'utf-8'
|
|
use_embedded_content = False
|
|
language = 'en'
|
|
INDEX = 'http://www.businessweek.com/magazine/news/articles/business_news.htm'
|
|
cover_url = 'http://images.businessweek.com/mz/covers/current_120x160.jpg'
|
|
|
|
|
|
conversion_options = {
|
|
'comment' : description
|
|
, 'tags' : category
|
|
, 'publisher' : publisher
|
|
, 'language' : language
|
|
}
|
|
|
|
|
|
def parse_index(self):
|
|
articles = []
|
|
soup = self.index_to_soup(self.INDEX)
|
|
ditem = soup.find('div',attrs={'id':'column2'})
|
|
if ditem:
|
|
for item in ditem.findAll('h3'):
|
|
title_prefix = ''
|
|
description = ''
|
|
feed_link = item.find('a')
|
|
if feed_link and feed_link.has_key('href'):
|
|
url = 'http://www.businessweek.com/magazine/' + feed_link['href'].partition('../../')[2]
|
|
title = title_prefix + self.tag_to_string(feed_link)
|
|
date = strftime(self.timefmt)
|
|
articles.append({
|
|
'title' :title
|
|
,'date' :date
|
|
,'url' :url
|
|
,'description':description
|
|
})
|
|
return [(soup.head.title.string, articles)]
|
|
|
|
keep_only_tags = dict(name='div', attrs={'id':'storyBody'})
|
|
|
|
def print_version(self, url):
|
|
rurl = url.rpartition('?')[0]
|
|
if rurl == '':
|
|
rurl = url
|
|
return rurl.replace('.com/magazine/','.com/print/magazine/')
|
|
|
|
|