mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
0a2291ae06
Fixes #1666609 [Financial Times download broken](https://bugs.launchpad.net/calibre/+bug/1666609)
80 lines
2.6 KiB
Python
80 lines
2.6 KiB
Python
#!/usr/bin/env python2
|
|
# vim:fileencoding=utf-8
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.ft.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from urllib import unquote
|
|
|
|
|
|
def classes(classes):
|
|
q = frozenset(classes.split(' '))
|
|
return dict(attrs={
|
|
'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
|
|
|
|
|
class FinancialTimes_rss(BasicNewsRecipe):
|
|
title = 'Financial Times'
|
|
__author__ = 'Darko Miletic'
|
|
description = "The Financial Times (FT) is one of the world's leading business news and information organisations, recognised internationally for its authority, integrity and accuracy." # noqa
|
|
publisher = 'The Financial Times Ltd.'
|
|
category = 'news, finances, politics, World'
|
|
oldest_article = 2
|
|
language = 'en'
|
|
max_articles_per_feed = 250
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
needs_subscription = True
|
|
encoding = 'utf8'
|
|
ignore_duplicate_articles = {'title'}
|
|
remove_empty_feeds = True
|
|
publication_type = 'newspaper'
|
|
masthead_url = 'http://im.media.ft.com/m/img/masthead_main.jpg'
|
|
handle_gzip = True
|
|
LOGIN = 'https://www.ft.com/login?location=/'
|
|
INDEX = 'https://www.ft.com'
|
|
LOGOUT = 'https://myaccount.ft.com/logout'
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
br.open(self.INDEX)
|
|
if self.username is not None and self.password is not None:
|
|
br.open(self.LOGIN)
|
|
br.select_form(name='enter-email-form')
|
|
br['email'] = self.username
|
|
br.submit()
|
|
br.select_form(name='enter-password-form')
|
|
br['password'] = self.password
|
|
br.submit()
|
|
return br
|
|
|
|
def cleanup(self):
|
|
self.browser.open(self.LOGOUT)
|
|
|
|
keep_only_tags = [
|
|
classes('article__header--wrapper article__time-byline article__body n-content-image barrier-grid__heading')
|
|
]
|
|
|
|
remove_tags = [
|
|
classes('n-content-related-box tour-tip')
|
|
]
|
|
|
|
remove_attributes = ['width', 'height', 'lang', 'style']
|
|
|
|
feeds = [
|
|
(u'UK', u'https://www.ft.com/rss/home/uk'),
|
|
(u'US', u'https://www.ft.com/rss/home/us'),
|
|
(u'Asia', u'https://www.ft.com/rss/home/asia'),
|
|
(u'Middle East', u'https://www.ft.com/rss/home/middleeast')
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', srcset=True):
|
|
src = img['srcset'].split(',')[0].strip()
|
|
src = unquote(src.rpartition('/')[2].partition('?')[0])
|
|
img['src'] = src
|
|
return soup
|