mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
66 lines
2.3 KiB
Python
66 lines
2.3 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
ft.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class FinancialTimes(BasicNewsRecipe):
|
|
title = u'Financial Times'
|
|
__author__ = 'Darko Miletic and Sujata Raman'
|
|
description = ('Financial world news. Available after 5AM '
|
|
'GMT, daily.')
|
|
oldest_article = 2
|
|
language = 'en'
|
|
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
needs_subscription = True
|
|
simultaneous_downloads= 1
|
|
delay = 1
|
|
|
|
LOGIN = 'https://registration.ft.com/registration/barrier/login'
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser()
|
|
if self.username is not None and self.password is not None:
|
|
br.open(self.LOGIN)
|
|
br.select_form(name='loginForm')
|
|
br['username'] = self.username
|
|
br['password'] = self.password
|
|
br.submit()
|
|
return br
|
|
|
|
keep_only_tags = [ dict(name='div', attrs={'id':'cont'}) ]
|
|
remove_tags_after = dict(name='p', attrs={'class':'copyright'})
|
|
remove_tags = [
|
|
dict(name='div', attrs={'id':'floating-con'})
|
|
]
|
|
|
|
extra_css = '''
|
|
body{font-family:Arial,Helvetica,sans-serif;}
|
|
h2(font-size:large;}
|
|
.ft-story-header(font-size:xx-small;}
|
|
.ft-story-body(font-size:small;}
|
|
a{color:#003399;}
|
|
.container{font-size:x-small;}
|
|
h3{font-size:x-small;color:#003399;}
|
|
'''
|
|
feeds = [
|
|
(u'UK' , u'http://www.ft.com/rss/home/uk' )
|
|
,(u'US' , u'http://www.ft.com/rss/home/us' )
|
|
,(u'Europe' , u'http://www.ft.com/rss/home/europe' )
|
|
,(u'Asia' , u'http://www.ft.com/rss/home/asia' )
|
|
,(u'Middle East', u'http://www.ft.com/rss/home/middleeast')
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
content_type = soup.find('meta', {'http-equiv':'Content-Type'})
|
|
if content_type:
|
|
content_type['content'] = 'text/html; charset=utf-8'
|
|
return soup
|