title: //main//h1[contains(@class, 'headline')] author: //div[contains(@class, "authors")]//*[contains(@class, "author")] date: //meta[@name="datePublished"]/@content body: //main//h2[contains(@class, 'subheader')] | (//main//div[contains(@class, 'image')])[1] | //article[@id="article-body"] strip_id_or_class: bgmp-comments strip_id_or_class: aside strip_id_or_class: promo strip_id_or_class: skip-nav strip_id_or_class: article-more strip_id_or_class: article-bar strip_id_or_class: post-comment strip_id_or_class: link-related_links_link strip_id_or_class: newsletter strip_id_or_class: arc_ad strip_id_or_class: teads-inread strip_id_or_class: continue_button strip_id_or_class: affiliation # remove tiny image (full size not present in element) [update Nov 2023: activating full size, see below] #strip: //img/[contains(@src, '/20x0/')]/@src # This removes image captions. #strip_id_or_class: figure find_string: " data-src="https://bostonglobe-prod.cdn.arcpublishing.com replace_string: " x src="https://bostonglobe-prod.cdn.arcpublishing.com find_string: " src="https://bostonglobe-prod.cdn.arcpublishing.com/resizer/ replace_string: tinysrc="https://bostonglobe-prod.cdn.arcpublishing.com/resizer/ prune: no test_url: https://www.bostonglobe.com/2020/04/07/metro/coronavirus-cases-surge-citys-safety-net-hospital-four-out-10-cases-are-now-related-pandemic/ test_url: https://www.bostonglobe.com/2021/03/01/metro/charlie-youre-making-big-mistake-experts-criticize-states-monday-reopening/