# chose your source feed from: # https://www.mittelhessen.de/rss/ # site has paywall, if you are using wallabag try to 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) http_header(referer): https://www.echo-online.de/ body: //article author: //meta[@name='twitter:creator']/@content title: normalize-space(//meta[@property='og:title']/@content) date: //time/@datetime strip: //path strip: //script strip: //footer strip: //div[contains(@class, 'recommendations')] strip: //div[@data-testid='storyline-intro-authors'] strip: //aside[contains(@data-testid, 'linkbox')] strip: //svg strip_id_or_class: recommendations__topStories strip_id_or_class: recommendations__cceWidget strip_id_or_class: storyElementWrapper__paywallContainer strip_id_or_class: storylineIntro__dateAndReadingTime strip_id_or_class: loadingBanner strip_id_or_class: adSlot strip_id_or_class: storylineHeader replace_string(,"value":): ,"invalid": replace_string(,"storylineText":): ,"value": # prevent the site logo to show, if article has no image insert_detected_image: no tidy: no prune: no # wallabag only: wrap_in(blockquote): //div[contains(@class, 'quoteWrapper')] # prevents wallabag to show image galery as overlay above article text find_string: class="contentWrapper slider replace_string: class="contentWrapper foo # don't remove this line! Site belongs to de_VRM group # The first URL will at some point no longer show # the full article. There is a time-based paywall # Using the feed should present valid output #test_url: https://www.mittelhessen.de/lokales/wetteraukreis/butzbach-wetteraukreis/autozug-brand-in-butzbach-sperrung-aufgehoben-2942445 test_url: https://www.mittelhessen.de/rss/lokales/hessen/