title://h1[@class="articleHeadline"] body://div[@id="article"] body://*[@itemprop="articleBody"] strip_id_or_class:articleTools strip_id_or_class:readerscomment #strip://div[contains(@class, "articleInline runaroundLeft")] strip: //div[contains(@class, "doubleRule")] # strip image credit - appears as a bold heading strip: //div[contains(@class, "articleInline")]//h6 strip_id_or_class:enlargeThis strip_id_or_class:pageLinks strip_id_or_class:memberTools strip_id_or_class:articleExtras strip_id_or_class:singleAd strip_id_or_class:byline strip_id_or_class:dateline strip_id_or_class:articleheadline strip_id_or_class:articleBottomExtra strip_id_or_class:shareTools strip://a[contains(@href, 'nytimes.com/adx/')] strip: //nyt_byline strip: //span[contains(@class, 'slideshow') or contains(@class, 'video')] strip: //p[@class='caption']//a[contains(., 'More Photos')] prune: no tidy: no find_string: