| 1 |
# -*- mode: python; coding: utf-8; -*- |
| 2 |
# vim: set syntax=python fileencoding=utf-8 |
| 3 |
|
| 4 |
__license__ = 'GPL v3' |
| 5 |
__copyright__ = '2010-2022, Darko Miletic <darko.miletic at gmail.com>' |
| 6 |
''' |
| 7 |
www.haaretz.com |
| 8 |
''' |
| 9 |
|
| 10 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 11 |
|
| 12 |
try: |
| 13 |
from urllib.parse import urlencode |
| 14 |
except ImportError: |
| 15 |
from urllib import urlencode |
| 16 |
|
| 17 |
|
| 18 |
class Haaretz_en(BasicNewsRecipe): |
| 19 |
title = 'Haaretz' |
| 20 |
__author__ = 'Darko Miletic' |
| 21 |
description = "Haaretz.com is the world's leading English-language Website for real-time news and analysis of Israel and the Middle East." |
| 22 |
publisher = 'Haaretz' |
| 23 |
oldest_article = 2 |
| 24 |
max_articles_per_feed = 200 |
| 25 |
no_stylesheets = True |
| 26 |
encoding = 'utf8' |
| 27 |
use_embedded_content = False |
| 28 |
language = 'en_IL' |
| 29 |
needs_subscription = True |
| 30 |
remove_empty_feeds = True |
| 31 |
ignore_duplicate_articles = {'url'} |
| 32 |
publication_type = 'newspaper' |
| 33 |
PREFIX = 'https://www.haaretz.com' |
| 34 |
LOGIN = 'https://services.haaretz.com/ms-sso/loginUrlEncoded' |
| 35 |
LOGOUT = 'https://services.haaretz.com/ms-sso/logout' |
| 36 |
extra_css = ''' |
| 37 |
body{font-family: Merriweather, "Helvetica Neue", Helvetica, Arial, sans-serif } |
| 38 |
div.mx time{display: none} |
| 39 |
div.my time{display: none} |
| 40 |
div.mq time{display: none} |
| 41 |
div.mr time{display: none} |
| 42 |
''' |
| 43 |
|
| 44 |
conversion_options = {'comment': description, 'publisher': publisher, 'language': language} |
| 45 |
|
| 46 |
keep_only_tags = [ |
| 47 |
dict(name='div', attrs={'data-test': 'articleHeader'}), |
| 48 |
dict(attrs={'data-test': 'articleBodyImage'}), |
| 49 |
dict(name='div', attrs={'class': ['bu a b d e ', 'bu a b d e']}), |
| 50 |
dict(name='div', attrs={'data-test': 'articleBody'}), |
| 51 |
] |
| 52 |
remove_attributes = ['width', 'height'] |
| 53 |
remove_tags = [ |
| 54 |
dict( |
| 55 |
name=['div', 'ul', 'button', 'svg'], |
| 56 |
attrs={'data-test': ['audioPlayer', 'newsletter', 'relatedArticles', 'tags', 'writerAlertButton', 'IconAlefLogo']}, |
| 57 |
) |
| 58 |
] |
| 59 |
|
| 60 |
feeds = [ |
| 61 |
('Headlines', 'https://www.haaretz.com/srv/haaretz-latest-headlines'), |
| 62 |
('Opinion', 'https://www.haaretz.com/srv/opinion-rss'), |
| 63 |
('Security & Aviation', 'https://www.haaretz.com/srv/security-&-aviation-rss'), |
| 64 |
('Israel News', 'https://www.haaretz.com/srv/israel-news-rss'), |
| 65 |
('World News', 'https://www.haaretz.com/srv/world-news-rss'), |
| 66 |
('Jewish World', 'https://www.haaretz.com/srv/jewish-world-rss'), |
| 67 |
('Business', 'https://www.haaretz.com/srv/business-rss'), |
| 68 |
('Science & Health', 'https://www.haaretz.com/srv/science-&-health-rss'), |
| 69 |
('Life & Culture', 'https://www.haaretz.com/srv/life-&-culture-rss'), |
| 70 |
('Books', 'https://www.haaretz.com/srv/books-rss'), |
| 71 |
('Food', 'https://www.haaretz.com/srv/food-rss'), |
| 72 |
] |
| 73 |
|
| 74 |
def get_browser(self): |
| 75 |
br = BasicNewsRecipe.get_browser(self) |
| 76 |
br.open(self.PREFIX) |
| 77 |
if self.username is not None and self.password is not None: |
| 78 |
data = urlencode({ |
| 79 |
'newsso': 'true', |
| 80 |
'fromlogin': 'true', |
| 81 |
'site': '85', |
| 82 |
'layer': 'login', |
| 83 |
'anonymousId': '16549476476914546', |
| 84 |
'userName': self.username, |
| 85 |
'password': self.password, |
| 86 |
}) |
| 87 |
br.open(self.LOGIN, data) |
| 88 |
return br |