diff --git a/recipes/haaretz_en.recipe b/recipes/haaretz_en.recipe index 41bfa0f166..45775bb722 100644 --- a/recipes/haaretz_en.recipe +++ b/recipes/haaretz_en.recipe @@ -1,5 +1,8 @@ +# -*- mode: python; coding: utf-8; -*- +# vim: set syntax=python fileencoding=utf-8 + __license__ = 'GPL v3' -__copyright__ = '2010-2015, Darko Miletic ' +__copyright__ = '2010-2022, Darko Miletic ' ''' www.haaretz.com ''' @@ -24,52 +27,63 @@ class Haaretz_en(BasicNewsRecipe): language = 'en_IL' needs_subscription = True remove_empty_feeds = True + ignore_duplicate_articles = {'url'} publication_type = 'newspaper' - PREFIX = 'http://www.haaretz.com' - masthead_url = PREFIX + '/images/logos/HaaretzLogo.gif' + 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: Verdana,Arial,Helvetica,sans-serif } - h1, .articleBody {font-family: Georgia, serif} - .authorBar {font-size: small} + 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={'id': 'content'})] + 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=['iframe', 'link', 'object', 'embed']), dict(name='div', attrs={ - 'class': ['rightcol', 'fblike']}), dict(name='div', attrs={'id': 'article_sso_form'}) + dict(name=['div', 'ul', 'button', 'svg'], attrs={'data-test': ['audioPlayer', 'newsletter', 'relatedArticles', 'tags', 'writerAlertButton', 'IconAlefLogo']}) ] feeds = [ - (u'Headlines', 'http://www.haaretz.com/cmlink/1.263335'), - (u'Opinion', 'http://www.haaretz.com/cmlink/1.628752'), - (u'Defence and diplomacy', 'http://www.haaretz.com/cmlink/1.628763'), - (u'National', 'http://www.haaretz.com/cmlink/1.628764'), - (u'International', 'http://www.haaretz.com/cmlink/1.628765'), - (u'Jewish World', 'http://www.haaretz.com/cmlink/1.628766'), - (u'Business', 'http://www.haaretz.com/cmlink/1.628767'), - (u'Real Estate', 'http://www.haaretz.com/cmlink/1.628768'), - (u'Features', 'http://www.haaretz.com/cmlink/1.628769'), - (u'Arts & Leisure', 'http://www.haaretz.com/cmlink/1.628771'), - (u'Books', 'http://www.haaretz.com/cmlink/1.628772'), - (u'Food & Wine', 'http://www.haaretz.com/cmlink/1.628773'), - (u'Sports', 'http://www.haaretz.com/cmlink/1.628774') + (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({'cb': 'parseEngReply', 'newsso': 'true', 'fromlogin': 'true', 'layer': 'eng_login', 'userName': self.username, 'password': self.password # noqa - }) - br.open('https://sso.haaretz.com/sso/sso/signIn', data) + 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 - - def print_version(self, url): - article = url.rpartition('/')[2] - return 'http://www.haaretz.com/misc/article-print-page/' + article