Fix #7157 (New recipe for Financial times UK Printed edition)

This commit is contained in:
Kovid Goyal 2010-10-12 15:15:16 -06:00
parent 80bf40ba5f
commit ef5f30994b

View File

@ -0,0 +1,74 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
ft.com
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class FinancialTimes(BasicNewsRecipe):
title = u'Financial Times - UK printed edition'
__author__ = 'Darko Miletic'
description = 'Financial world news'
oldest_article = 2
language = 'en_GB'
max_articles_per_feed = 250
no_stylesheets = True
use_embedded_content = False
needs_subscription = True
encoding = 'utf8'
simultaneous_downloads= 1
delay = 1
LOGIN = 'https://registration.ft.com/registration/barrier/login'
INDEX = 'http://www.ft.com/uk-edition'
PREFIX = 'http://www.ft.com'
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'})
,dict(name=['meta','iframe','base','object','embed','link'])
]
remove_attributes = ['width','height','lang']
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;}
.copyright{font-size: x-small}
"""
def parse_index(self):
articles = []
soup = self.index_to_soup(self.INDEX)
wide = soup.find('div',attrs={'class':'wide'})
if wide:
for item in wide.findAll('a',href=True):
url = self.PREFIX + item['href']
title = self.tag_to_string(item)
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':''
})
return [('FT UK edition',articles)]
def preprocess_html(self, soup):
return self.adeify_images(soup)