From e4212aef2d06ad39ecc6989080a3d7bf7ecec9e0 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Fri, 23 Aug 2013 00:54:02 +0200 Subject: theverge.com --- theverge.com.txt | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/theverge.com.txt b/theverge.com.txt index 3960fb9..6a0d560 100644 --- a/theverge.com.txt +++ b/theverge.com.txt @@ -1,13 +1,12 @@ -title: //h1[contains(@class, "headline")] - author: //p[contains(@class, "byline")]/a[contains(@class, "author")] -date: substring-after(normalize-space(//p[contains(@class, "byline")]/span[contains(@class, "publish-date")]), "on ") +date: //span[contains(@class, "publish-date")]/time[@pubdate]/@datetime -body: //article[contains(@class, 'feature-entry')] +body: //div[contains(@class, 'entry-content')] +# for vergecasts, e.g. http://www.theverge.com/2013/8/22/4648566/the-vergecast-090-august-22th-2013-video body: //article prune: no -tidy: no +#tidy: no strip: //article/header strip: //*[@id='sticky-menu'] @@ -22,9 +21,12 @@ strip_id_or_class: related-product-meta strip_id_or_class: comments strip_id_or_class: ui-jump-list strip_id_or_class: pullquote +strip_id_or_class: m-ad +strip_id_or_class: social-sharing +strip_id_or_class: m-video-entry__excerpt -find_string: