mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
91 lines
3.3 KiB
Plaintext
91 lines
3.3 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2010-2011, 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 get_artlinks(self, elem):
|
|
articles = []
|
|
for item in elem.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 articles
|
|
|
|
def parse_index(self):
|
|
feeds = []
|
|
soup = self.index_to_soup(self.INDEX)
|
|
wide = soup.find('div',attrs={'class':'wide'})
|
|
if not wide:
|
|
return feeds
|
|
strest = wide.findAll('h3', attrs={'class':'section'})
|
|
if not strest:
|
|
return feeds
|
|
st = wide.find('h4',attrs={'class':'section-no-arrow'})
|
|
if st:
|
|
strest.insert(0,st)
|
|
for item in strest:
|
|
ftitle = self.tag_to_string(item)
|
|
self.report_progress(0, _('Fetching feed')+' %s...'%(ftitle))
|
|
feedarts = self.get_artlinks(item.parent.ul)
|
|
feeds.append((ftitle,feedarts))
|
|
return feeds
|
|
|
|
def preprocess_html(self, soup):
|
|
return self.adeify_images(soup)
|
|
|