calibre/recipes/haaretz_en.recipe
2025-01-24 11:14:14 +01:00

92 lines
3.4 KiB
Python

# -*- mode: python; coding: utf-8; -*-
# vim: set syntax=python fileencoding=utf-8
__license__ = 'GPL v3'
__copyright__ = '2010-2022, Darko Miletic <darko.miletic at gmail.com>'
'''
www.haaretz.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
try:
from urllib.parse import urlencode
except ImportError:
from urllib import urlencode
class Haaretz_en(BasicNewsRecipe):
title = 'Haaretz'
__author__ = 'Darko Miletic'
description = "Haaretz.com is the world's leading English-language Website for real-time news and analysis of Israel and the Middle East."
publisher = 'Haaretz'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'en_IL'
needs_subscription = True
remove_empty_feeds = True
ignore_duplicate_articles = {'url'}
publication_type = 'newspaper'
PREFIX = 'https://www.haaretz.com'
LOGIN = 'https://services.haaretz.com/ms-sso/loginUrlEncoded'
LOGOUT = 'https://services.haaretz.com/ms-sso/logout'
extra_css = '''
body{font-family: Merriweather, "Helvetica Neue", Helvetica, Arial, sans-serif }
div.mx time{display: none}
div.my time{display: none}
div.mq time{display: none}
div.mr time{display: none}
'''
conversion_options = {
'comment': description, 'publisher': publisher, 'language': language
}
keep_only_tags = [
dict(name='div', attrs={'data-test': 'articleHeader'}),
dict(attrs={'data-test': 'articleBodyImage'}),
dict(name='div', attrs={'class': ['bu a b d e ', 'bu a b d e']}),
dict(name='div', attrs={'data-test': 'articleBody'})
]
remove_attributes = ['width', 'height']
remove_tags = [
dict(name=['div', 'ul', 'button', 'svg'], attrs={'data-test': [
'audioPlayer', 'newsletter', 'relatedArticles', 'tags', 'writerAlertButton', 'IconAlefLogo']})
]
feeds = [
(u'Headlines', 'https://www.haaretz.com/srv/haaretz-latest-headlines'),
(u'Opinion', 'https://www.haaretz.com/srv/opinion-rss'),
(u'Security & Aviation', 'https://www.haaretz.com/srv/security-&-aviation-rss'),
(u'Israel News', 'https://www.haaretz.com/srv/israel-news-rss'),
(u'World News', 'https://www.haaretz.com/srv/world-news-rss'),
(u'Jewish World', 'https://www.haaretz.com/srv/jewish-world-rss'),
(u'Business', 'https://www.haaretz.com/srv/business-rss'),
(u'Science & Health', 'https://www.haaretz.com/srv/science-&-health-rss'),
(u'Life & Culture', 'https://www.haaretz.com/srv/life-&-culture-rss'),
(u'Books', 'https://www.haaretz.com/srv/books-rss'),
(u'Food', 'https://www.haaretz.com/srv/food-rss')
]
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open(self.PREFIX)
if self.username is not None and self.password is not None:
data = urlencode(
{
'newsso': 'true',
'fromlogin': 'true',
'site': '85',
'layer': 'login',
'anonymousId': '16549476476914546',
'userName': self.username,
'password': self.password
}
)
br.open(self.LOGIN, data)
return br