calibre/recipes/japan_times.recipe
2011-10-21 22:19:01 +05:30

72 lines
2.8 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
'''
japantimes.co.jp
'''
from calibre.web.feeds.news import BasicNewsRecipe
class JapanTimes(BasicNewsRecipe):
title = 'The Japan Times'
__author__ = 'Darko Miletic'
description = "Daily news and features on Japan from the most widely read English-language newspaper in Japan. Coverage includes national news, business news, sports news, commentary and features on living in Japan, entertainment, the arts, education and more."
language = 'en_JP'
category = 'news, politics, japan'
publisher = 'The Japan Times'
oldest_article = 5
max_articles_per_feed = 150
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
publication_type = 'newspaper'
masthead_url = 'http://search.japantimes.co.jp/images/header_title.gif'
extra_css = 'body{font-family: Geneva,Arial,Helvetica,sans-serif}'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
, 'linearize_tables' : True
}
keep_only_tags = [dict(name='div', attrs={'id':'printresult'})]
remove_tags = [
dict(name=['iframe','meta','link','embed','object','base'])
,dict(attrs={'id':'searchfooter'})
]
feeds = [(u'The Japan Times', u'http://feeds.feedburner.com/japantimes')]
remove_attributes = ['border']
def get_article_url(self, article):
rurl = BasicNewsRecipe.get_article_url(self, article)
return rurl.partition('?')[0]
def print_version(self, url):
if '/rss/' in url:
return url.replace('.jp/rss/','.jp/print/')
if '/text/' in url:
return url.replace('.jp/text/','.jp/print/')
return url
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
for item in soup.findAll('photo'):
item.name = 'div'
for item in soup.head.findAll('paragraph'):
item.extract()
for item in soup.findAll('wwfilename'):
item.extract()
for item in soup.findAll('jtcategory'):
item.extract()
for item in soup.findAll('nomooter'):
item.extract()
for item in soup.body.findAll('paragraph'):
item.name = 'p'
return soup