View Single Post
Old 03-10-2019, 08:03 PM   #4
lui1
Enthusiast
lui1 began at the beginning.
 
Posts: 36
Karma: 10
Join Date: Dec 2017
Location: Los Angeles, CA
Device: Smart Phone
update to derStandard

I think this fixes the problem.

Recipe for derStandard:
Code:
#!/usr/bin/env  python2
# -*- coding: utf-8 -*-
from __future__ import unicode_literals, division, absolute_import, print_function

__license__ = 'GPL v3'
__copyright__ = '2009, Gerhard Aigner <gerhard.aigner at gmail.com>'

''' http://www.derstandard.at - Austrian Newspaper '''

from calibre.web.feeds.news import BasicNewsRecipe

def classes(classes):
    q = frozenset(classes.split(' '))
    return dict(attrs={
        'class': lambda x: x and frozenset(x.split()).intersection(q)})


class DerStandardRecipe(BasicNewsRecipe):
    title = u'derStandard'
    __author__ = 'Gerhard Aigner and Sujata Raman and Marcel Jira and Peter Reschenhofer'
    description = u'Nachrichten aus Österreich'
    publisher = 'derStandard.at'
    category = 'news, politics, nachrichten, Austria'
    use_embedded_content = False
    remove_empty_feeds = True
    no_stylesheets = True
    encoding = 'utf-8'
    language = 'de_AT'

    oldest_article = 1
    max_articles_per_feed = 100
    ignore_duplicate_articles = {'title', 'url'}

    masthead_url = 'http://images.derstandard.at/2012/06/19/derStandardat_1417x274.gif'

    feeds = [
        (u'Newsroom', u'https://derStandard.at/?page=rss&ressort=Seite1'),
        (u'International', u'https://derstandard.at/?page=rss&ressort=International'),
        (u'Inland', u'https://derstandard.at/?page=rss&ressort=Inland'),
        (u'Wirtschaft', u'https://derStandard.at/?page=rss&ressort=Wirtschaft'),
        (u'Web', u'https://derStandard.at/?page=rss&ressort=Web'),
        (u'Sport', u'https://derStandard.at/?page=rss&ressort=Sport'),
        (u'Panorama', u'https://derStandard.at/?page=rss&ressort=Panorama'),
        (u'Etat', u'https://derStandard.at/?page=rss&ressort=Etat'),
        (u'Kultur', u'https://derStandard.at/?page=rss&ressort=Kultur'),
        (u'Wissenschaft', u'https://derStandard.at/?page=rss&ressort=Wissenschaft'),
        (u'Gesundheit', u'https://derStandard.at/?page=rss&ressort=Gesundheit'),
        (u'Bildung', u'https://derStandard.at/?page=rss&ressort=Bildung'),
        (u'Meinung', u'https://derStandard.at/?page=rss&ressort=Meinung'),
        (u'Lifestyle', u'https://derStandard.at/?page=rss&ressort=Lifestyle'),
        (u'Reisen', u'https://derStandard.at/?page=rss&ressort=Reisen'),
        (u'Familie', u'https://derstandard.at/?page=rss&ressort=Familie'),
        (u'Meinung', u'https://derStandard.at/?page=rss&ressort=Meinung'),
        (u'User', u'https://derStandard.at/?page=rss&ressort=User'),
        (u'Karriere', u'https://derStandard.at/?page=rss&ressort=Karriere'),
        (u'Immobilien', u'https://derstandard.at/?page=rss&ressort=Immobilien'),
        (u'Automobil', u'https://derstandard.at/?page=rss&ressort=Automobil'),
        (u'dieStandard', u'https://derStandard.at/?page=rss&ressort=diestandard'),
    ]

    def get_browser(self):
        br = BasicNewsRecipe.get_browser(self)
        headers = {
            'X-Requested-With': 'XMLHttpRequest',
            'Content-Type': 'application/json; charset=UTF-8',
            'DNT': '1',
            'Pragma': 'no-cache',
            'Cache-Control': 'no-cache'
        }
        import mechanize
        req =   mechanize.Request(url='https://derstandard.at/privacyprotection/api/agree', data=None, headers=headers, method='POST')
        br.open(req)
        return br

    keep_only_tags = [
        classes('artikel'),
    ]

    remove_tags = [
        dict(name=['link', 'iframe', 'style', 'hr']),
        dict(attrs={'class': ['lookup-links', 'media-list']}),
        dict(name='form', attrs={'name': 'sitesearch'}),
        dict(name='div', attrs={'class': ['socialsharing', 'block video',
                                          'blog-browsing section',
                                          'diashow', 'supplemental']}),
        dict(name='div', attrs={'id': 'highlighted'})
    ]

    remove_attributes = ['width', 'height']
lui1 is offline   Reply With Quote