From 94a8cc2f55be5b3596825e3661529f0498b8ebb6 Mon Sep 17 00:00:00 2001 From: yes Date: Thu, 16 Jun 2016 21:41:40 +0200 Subject: fix content fetching of theatlantic.com with the help of single_page_link (#171) --- theatlantic.com.txt | 3 +++ 1 file changed, 3 insertions(+) diff --git a/theatlantic.com.txt b/theatlantic.com.txt index 3686419..0c6e7c1 100644 --- a/theatlantic.com.txt +++ b/theatlantic.com.txt @@ -1,5 +1,7 @@ title: //div[contains(@class, 'articleHead')]//h1 +single_page_link: //link[contains(@href, '/amp/article/')] + body: //div[@itemprop='articleBody'] body: //div[@class='articleText'] body: //div[@class='articleContent'] @@ -25,3 +27,4 @@ test_contains: The curve tends to evince itself test_url: http://www.theatlantic.com/technology/archive/2011/04/want-to-see-how-crazy-a-bot-run-market-can-be/237773/ test_url: http://www.theatlantic.com/magazine/archive/2007/11/the-autumn-of-the-multitaskers/6342/ test_url: http://www.theatlantic.com/entertainment/archive/2012/04/30-rock-live-a-funny-reminder-of-why-sitcoms-arent-shot-live-anymore/256447/ +test_url: http://www.theatlantic.com/technology/archive/2013/06/fix-things-never-force-it-lessons-from-grandpa/276873/ -- cgit v1.3.1