mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
104 lines
5.1 KiB
Plaintext
104 lines
5.1 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2008-2010, AprilHare, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
newscientist.com
|
|
'''
|
|
|
|
import re
|
|
import urllib
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class NewScientist(BasicNewsRecipe):
|
|
title = 'New Scientist - Online News w. subscription'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Science news and science articles from New Scientist.'
|
|
language = 'en'
|
|
publisher = 'Reed Business Information Ltd.'
|
|
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'
|
|
needs_subscription = 'optional'
|
|
extra_css = """
|
|
body{font-family: Arial,sans-serif}
|
|
img{margin-bottom: 0.8em; display: block}
|
|
.quotebx{font-size: x-large; font-weight: bold; margin-right: 2em; margin-left: 2em}
|
|
"""
|
|
|
|
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']})]
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser()
|
|
br.open('http://www.newscientist.com/')
|
|
if self.username is not None and self.password is not None:
|
|
br.open('https://www.newscientist.com/user/login')
|
|
data = urllib.urlencode({ 'source':'form'
|
|
,'redirectURL':''
|
|
,'loginId':self.username
|
|
,'password':self.password
|
|
})
|
|
br.open('https://www.newscientist.com/user/login',data)
|
|
return br
|
|
|
|
remove_tags = [
|
|
dict(name='div' , attrs={'class':['hldBd','adline','pnl','infotext' ]})
|
|
,dict(name='div' , attrs={'id' :['compnl','artIssueInfo','artTools','comments','blgsocial','sharebtns']})
|
|
,dict(name='p' , attrs={'class':['marker','infotext' ]})
|
|
,dict(name='meta' , attrs={'name' :'description' })
|
|
,dict(name='a' , attrs={'rel' :'tag' })
|
|
,dict(name='ul' , attrs={'class':'markerlist' })
|
|
,dict(name=['link','base','meta','iframe','object','embed'])
|
|
]
|
|
remove_tags_after = dict(attrs={'class':['nbpcopy','comments']})
|
|
remove_attributes = ['height','width','lang','onclick']
|
|
|
|
feeds = [
|
|
(u'Latest Headlines' , u'http://feeds.newscientist.com/science-news' )
|
|
,(u'Magazine' , u'http://feeds.newscientist.com/magazine' )
|
|
,(u'Health' , u'http://feeds.newscientist.com/health' )
|
|
,(u'Life' , u'http://feeds.newscientist.com/life' )
|
|
,(u'Space' , u'http://feeds.newscientist.com/space' )
|
|
,(u'Physics and Mathematics' , u'http://feeds.newscientist.com/physics-math' )
|
|
,(u'Environment' , u'http://feeds.newscientist.com/environment' )
|
|
,(u'Science in Society' , u'http://feeds.newscientist.com/science-in-society' )
|
|
,(u'Tech' , u'http://feeds.newscientist.com/tech' )
|
|
]
|
|
|
|
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):
|
|
if soup.html.has_key('id'):
|
|
del soup.html['id']
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
for item in soup.findAll(['quote','quotetext']):
|
|
item.name='p'
|
|
for item in soup.findAll(['xref','figref']):
|
|
tstr = item.string
|
|
item.replaceWith(tstr)
|
|
for tg in soup.findAll('a'):
|
|
if tg.string == 'Home':
|
|
tg.parent.extract()
|
|
else:
|
|
if tg.string is not None:
|
|
tstr = tg.string
|
|
tg.replaceWith(tstr)
|
|
return soup
|
|
|