# without bot as user-agent: totally NO content (FTR/wallabag UI) # with bot as user agent: content is cut for longer articles (FTR/wallabag UI) # # to get full-content in wallabag use wallabagger browser-plugin with activated # option 'Retrieve content from the browser' in it's settings http_header(User-Agent): Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html) body: //article[1] author: //meta[@name="vr:author"]/@content date: //span[@itemprop="datePublished"]/@content title: //h2[@class='headline'] # fix image lazy loading find_string: data-src=" replace_string: src=" #2023: strip_id_or_class: authors strip_id_or_class: source strip_id_or_class: kicker strip_id_or_class: headline strip: //app-toolbar strip: //button strip: //app-storyline-related-topics prune: no # Fix picture captions # wrap_in(small): //div[@class="hcf-caption"] test_url: https://www.handelsblatt.com/dpa/eu-kommission-macht-sich-fuer-bessere-radwege-stark/29427222.html test_url: https://www.handelsblatt.com/politik/deutschland/flughafen-berlin-brandenburg-vier-milliarden-euro-mehr-neun-jahre-zu-spaet-die-wichtigsten-fakten-zum-start-des-ber/26205178.html