body: //article[@class='article']/div[@class='container'] body: //article[@class='article']/div[@class='foo-cntnr'] title: //h1[@class='article__title'] strip_id_or_class: article-info strip_id_or_class: table-of-contents-wrp strip_id_or_class: table-of-contents strip_id_or_class: article-bottom strip_id_or_class: article-crumbs strip_id_or_class: share strip: //h1[@class='article__title'] strip: //div[contains(@class, 'lazyblock-link-aside')] strip: //div[contains(@class, 'lazyblock-banner')] strip: //div[contains(@class, 'lazyblock-titry')] ## [wallabag] remove literal script code, which has not been removed completely by graby/wallabag ## e.g. see test_url, the problem is the "Table of Content" part (JavaScript generated) strip: //div[contains(@class, 'article-header')]/following-sibling::text() strip: //aside/text() ## [wallabag] prevent removing sub-headings strip_attr: //h*[contains(@class,'wp-block-heading')]/@class ## [wallabag] prevent indentation. only one of these lines: replace_string(class="container): class="foo-cntnr prune: no test_url: https://thecode.media/razbiraem-shemy-moshennikov-arbitrazh-kriptovalyuty/