From 897f18d12961efd3d7ac8b7e487b1ab761273ec0 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Sun, 26 Feb 2017 15:55:31 +0100 Subject: Update theverge.com.txt --- theverge.com.txt | 35 ++++++++++------------------------- 1 file changed, 10 insertions(+), 25 deletions(-) diff --git a/theverge.com.txt b/theverge.com.txt index be1e223..61c6df6 100644 --- a/theverge.com.txt +++ b/theverge.com.txt @@ -1,28 +1,14 @@ -author: //p[contains(@class, "byline")]/a[contains(@class, "author")] -title: //section[contains(concat(' ',normalize-space(@class),' '),' lede ')]//h1 -date: //span[contains(@class, "publish-date")]/time[@pubdate]/@datetime +author: //meta[@name="author"]/@content +title: //meta[@property="og:title"]/@content +date: //meta[@property="article:published_time"]/@content -body: //div[contains(@class, 'm-article__entry-section')] +body: //div[contains(@class, 'c-entry-content') or contains(@class, 'c-entry-hero__image')] # for vergecasts, e.g. http://www.theverge.com/2013/8/22/4648566/the-vergecast-090-august-22th-2013-video body: //article body: //div[contains(concat(' ',normalize-space(@class),' '),' l-col__main ')] -prune: no -#tidy: no - -strip: //h3 -strip: //article/header -strip: //*[@id='sticky-menu'] strip: //aside strip: //nav -strip: //img[contains(@class, 'vox-lazy-load')] -# deal with bad parsing -strip: //div[contains(@class, 'story-image')]//div[contains(., 'function(')] -strip: //div[contains(@class, 'm-linkset')] -strip: //div[contains(@class, 'm-entry__sidebar')] -strip: //ul[contains(@class, 'm-article__sources')] -strip: //div[contains(@class, 'chorus-emc__content')] - strip_id_or_class: gallery strip_id_or_class: article-meta @@ -43,17 +29,16 @@ strip_id_or_class: c-river strip_id_or_class: chorus-ad-placement strip_id_or_class: c-related-list +#2017 +strip_id_or_class: e-image__meta + replace_string(