mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
97 lines
3.7 KiB
Plaintext
97 lines
3.7 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.ft.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
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'
|
|
publication_type = 'newspaper'
|
|
masthead_url = 'http://im.media.ft.com/m/img/masthead_main.jpg'
|
|
LOGIN = 'https://accounts.ft.com/login'
|
|
INDEX = 'http://www.ft.com'
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True
|
|
}
|
|
|
|
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='login')
|
|
br['email'] = self.username
|
|
br['password'] = self.password
|
|
br.submit()
|
|
return br
|
|
|
|
keep_only_tags = [dict(name='div', attrs={'class': [
|
|
'fullstory fullstoryHeader', 'fullstory fullstoryBody', 'ft-story-header', 'ft-story-body', 'index-detail']})]
|
|
remove_tags = [
|
|
dict(name='div', attrs={'id': 'floating-con'}), dict(name=['meta', 'iframe', 'base', 'object', 'embed', 'link']), dict(
|
|
attrs={'class': ['storyTools', 'story-package', 'screen-copy', 'story-package separator', 'expandable-image']})
|
|
]
|
|
remove_attributes = ['width', 'height', 'lang']
|
|
|
|
extra_css = """
|
|
body{font-family: Georgia,Times,"Times New Roman",serif}
|
|
h2{font-size:large}
|
|
.ft-story-header{font-size: x-small}
|
|
.container{font-size:x-small;}
|
|
h3{font-size:x-small;color:#003399;}
|
|
.copyright{font-size: x-small}
|
|
img{margin-top: 0.8em; display: block}
|
|
.lastUpdated{font-family: Arial,Helvetica,sans-serif; font-size: x-small}
|
|
.byline,.ft-story-body,.ft-story-header{font-family: Arial,Helvetica,sans-serif}
|
|
"""
|
|
|
|
feeds = [
|
|
|
|
(u'UK', u'http://www.ft.com/rss/home/uk'),
|
|
(u'US', u'http://www.ft.com/rss/home/us'),
|
|
(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):
|
|
items = ['promo-box', 'promo-title',
|
|
'promo-headline', 'promo-image',
|
|
'promo-intro', 'promo-link', 'subhead']
|
|
for item in items:
|
|
for it in soup.findAll(item):
|
|
it.name = 'div'
|
|
it.attrs = []
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
for item in soup.findAll('a'):
|
|
limg = item.find('img')
|
|
if item.string is not None:
|
|
str = item.string
|
|
item.replaceWith(str)
|
|
else:
|
|
if limg:
|
|
item.name = 'div'
|
|
item.attrs = []
|
|
else:
|
|
str = self.tag_to_string(item)
|
|
item.replaceWith(str)
|
|
for item in soup.findAll('img'):
|
|
if not item.has_key('alt'): # noqa
|
|
item['alt'] = 'image'
|
|
return soup
|