Hi,
Code:
#!/usr/bin/env python2
# -*- mode: python -*-
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2010-2017, Darko Miletic <darko.miletic at gmail.com>'
'''
www.ft.com/international-edition
'''
from calibre.web.feeds.news import BasicNewsRecipe
from collections import OrderedDict
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(BasicNewsRecipe):
title = 'Financial Times (International) printed edition'
__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
scale_news_images_to_device = True
language = 'en'
max_articles_per_feed = 250
no_stylesheets = True
use_embedded_content = False
needs_subscription = True
encoding = 'utf8'
publication_type = 'newspaper'
handle_gzip = True
LOGIN = 'https://accounts.ft.com/login?location=https%3A%2F%2Fwww.ft.com%2F'
LOGOUT = 'https://myaccount.ft.com/logout'
INDEX = 'http://www.ft.com/international-edition'
PREFIX = 'http://www.ft.com'
useHighResImages = False
compress_news_images = True
compress_news_images_auto_size = 5
excludeSections = ['life-arts']
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']
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 parse_index(self):
feeds = OrderedDict()
soup = self.index_to_soup(self.INDEX)
section_title = 'Untitled'
for column in soup.findAll('div', attrs={'class': 'feedBoxes clearfix'}):
for section in column.findAll('div', attrs={'class': 'feedBox'}):
sectiontitle = self.tag_to_string(section.find('h4'))
if '...' not in sectiontitle:
section_title = sectiontitle
for article in section.ul.findAll('li'):
articles = []
title = self.tag_to_string(article.a)
url = article.a['href']
articles.append(
{'title': title, 'url': url, 'description': '', 'date': ''})
if articles:
if section_title not in feeds:
feeds[section_title] = []
feeds[section_title] += articles
ans = [(key, val) for key, val in feeds.iteritems()]
return ans
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
def cleanup(self):
self.browser.open(self.LOGOUT)
Did I place it wrongly?