From 3bb6a8ed2ab40b17d3f3b9925664c8da38ea2570 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sat, 1 Aug 2015 21:20:43 +0200 Subject: update config from @fivefilters --- inc/3rdparty/site_config/standard/smithsonianmag.com.txt | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'inc/3rdparty/site_config/standard/smithsonianmag.com.txt') diff --git a/inc/3rdparty/site_config/standard/smithsonianmag.com.txt b/inc/3rdparty/site_config/standard/smithsonianmag.com.txt index 3e8fee95..fc479c2a 100755 --- a/inc/3rdparty/site_config/standard/smithsonianmag.com.txt +++ b/inc/3rdparty/site_config/standard/smithsonianmag.com.txt @@ -7,6 +7,9 @@ body://div[@id = 'article-body'] # full content single_page_link://td/li[@class = 'article-singlepage']/a +# continue link +single_page_link: //a[@id='continue-btn'] + # caption clean up wrap_in(i)://span[@class='articleImageCaptionwide'] move_into (//span[@class='articleImageCaptionwide'])://div[@id = 'articleImage']/p @@ -17,4 +20,4 @@ strip://p[@id = 'articlePaginationWrapper'] strip://ul[contains(@class, 'cat-breadcrumb')] strip://div [@class= 'viewMorePhotos'] -test_url: http://www.smithsonianmag.com/history-archaeology/The-Goddess-Goes-Home.html \ No newline at end of file +test_url: http://www.smithsonianmag.com/history-archaeology/The-Goddess-Goes-Home.html -- cgit v1.2.3