China Daily by Darko Miletic

This commit is contained in:
Kovid Goyal 2010-04-26 08:55:13 -06:00
parent ba65c3b3e2
commit ea3939fea6
2 changed files with 48 additions and 0 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 491 B

View File

@ -0,0 +1,48 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.chinadaily.com.cn
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Pagina12(BasicNewsRecipe):
title = 'China Daily'
__author__ = 'Darko Miletic'
description = 'Chinadaily.com.cn is the largest English portal in China, providing news, business information, BBS, learning materials.'
publisher = 'China Daily Information Co.'
category = 'news, politics, China'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'en_CN'
remove_empty_feeds = True
publication_type = 'newsportal'
masthead_url = 'http://www.chinadaily.com.cn/15421.files/chinadailylogo_e_20100301.jpg'
extra_css = ' body{font-family: Arial,Helvetica,sans-serif } '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [dict(name=['object','embed','iframe','table'])]
keep_only_tags = [dict(attrs={'id':['Title_e','Content']})]
feeds = [
(u'China' , u'http://www.chinadaily.com.cn/rss/china_rss.xml' )
,(u'Business', u'http://www.chinadaily.com.cn/rss/bizchina_rss.xml')
,(u'World' , u'http://www.chinadaily.com.cn/rss/world_rss.xml' )
,(u'Sports' , u'http://www.chinadaily.com.cn/rss/sports_rss.xml' )
,(u'Opinions', u'http://www.chinadaily.com.cn/rss/opinion_rss.xml' )
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup