body: //body title: //p[@class='TitelText'] # sometimes the title
has the wrong class="Author" title: //div[@class='WordSection1']/p[1] author: (//p[@class='Author'])[last()] # site uses iframe to display its own content single_page_link: //iframe/@src if_page_contains: //iframe[contains(@src, 'triple-c.at/index.php/tripleC/article/download/')] prune: no tidy: no # wallabag needs removing these placeholder/comments, otherwise they got literal into the text find_string: replace_string: find_string: replace_string: find_string: replace_string: test_url: https://www.triple-c.at/index.php/tripleC/article/view/1498/1543 test_url: https://www.triple-c.at/index.php/tripleC/article/view/1483/1507