From b76cf6f14c2e469a3472934904a0206a24ea93fc Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 28 Jun 2017 17:15:50 +0200 Subject: Update theverge.com.txt --- theverge.com.txt | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/theverge.com.txt b/theverge.com.txt index 0273abc..86cb8c7 100644 --- a/theverge.com.txt +++ b/theverge.com.txt @@ -2,7 +2,9 @@ author: //meta[@name="author"]/@content title: //meta[@property="og:title"]/@content date: //meta[@property="article:published_time"]/@content -body: //picture[contains(@class, 'c-picture')] | //div[contains(@class, 'c-entry-content') or contains(@class, 'c-entry-hero__image')] +# //picture selector seems to cause problems with text extraction. +# body: //picture[contains(@class, 'c-picture')] | //div[contains(@class, 'c-entry-content') or contains(@class, 'c-entry-hero__image')] +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 ')] -- cgit v1.3.1