calibre/resources/recipes/new_scientist.recipe
2010-06-24 12:07:33 -06:00

72 lines
3.6 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2010, AprilHare, Darko Miletic <darko.miletic at gmail.com>'
'''
newscientist.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class NewScientist(BasicNewsRecipe):
title = 'New Scientist - Online News'
__author__ = 'Darko Miletic'
description = 'Science news and science articles from New Scientist.'
language = 'en'
publisher = 'New Scientist'
category = 'science news, science articles, science jobs, drugs, cancer, depression, computer software'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
cover_url = 'http://www.newscientist.com/currentcover.jpg'
masthead_url = 'http://www.newscientist.com/img/misc/ns_logo.jpg'
encoding = 'utf-8'
extra_css = ' body{font-family: Arial,sans-serif} img{margin-bottom: 0.8em} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
preprocess_regexps = [(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')]
keep_only_tags = [dict(name='div', attrs={'id':['pgtop','maincol','blgmaincol','nsblgposts','hldgalcols']})]
remove_tags = [
dict(name='div' , attrs={'class':['hldBd','adline','pnl','infotext' ]})
,dict(name='div' , attrs={'id' :['compnl','artIssueInfo','artTools','comments','blgsocial']})
,dict(name='p' , attrs={'class':['marker','infotext' ]})
,dict(name='meta' , attrs={'name' :'description' })
,dict(name='a' , attrs={'rel' :'tag' })
]
remove_tags_after = dict(attrs={'class':['nbpcopy','comments']})
remove_attributes = ['height','width']
feeds = [
(u'Latest Headlines' , u'http://feeds.newscientist.com/science-news' )
,(u'Magazine' , u'http://www.newscientist.com/feed/magazine' )
,(u'Health' , u'http://www.newscientist.com/feed/view?id=2&type=channel' )
,(u'Life' , u'http://www.newscientist.com/feed/view?id=3&type=channel' )
,(u'Space' , u'http://www.newscientist.com/feed/view?id=6&type=channel' )
,(u'Physics and Mathematics' , u'http://www.newscientist.com/feed/view?id=4&type=channel' )
,(u'Environment' , u'http://www.newscientist.com/feed/view?id=1&type=channel' )
,(u'Science in Society' , u'http://www.newscientist.com/feed/view?id=5&type=channel' )
,(u'Tech' , u'http://www.newscientist.com/feed/view?id=7&type=channel' )
]
def get_article_url(self, article):
return article.get('guid', None)
def print_version(self, url):
return url + '?full=true&print=true'
def preprocess_html(self, soup):
for tg in soup.findAll('a'):
if tg.string == 'Home':
tg.parent.extract()
return self.adeify_images(soup)
return self.adeify_images(soup)