aboutsummaryrefslogtreecommitdiffhomepage
path: root/inc/3rdparty/site_config/standard/smithsonianmag.com.txt
diff options
context:
space:
mode:
Diffstat (limited to 'inc/3rdparty/site_config/standard/smithsonianmag.com.txt')
-rwxr-xr-xinc/3rdparty/site_config/standard/smithsonianmag.com.txt5
1 files changed, 4 insertions, 1 deletions
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']
7# full content 7# full content
8single_page_link://td/li[@class = 'article-singlepage']/a 8single_page_link://td/li[@class = 'article-singlepage']/a
9 9
10# continue link
11single_page_link: //a[@id='continue-btn']
12
10# caption clean up 13# caption clean up
11wrap_in(i)://span[@class='articleImageCaptionwide'] 14wrap_in(i)://span[@class='articleImageCaptionwide']
12move_into (//span[@class='articleImageCaptionwide'])://div[@id = 'articleImage']/p 15move_into (//span[@class='articleImageCaptionwide'])://div[@id = 'articleImage']/p
@@ -17,4 +20,4 @@ strip://p[@id = 'articlePaginationWrapper']
17strip://ul[contains(@class, 'cat-breadcrumb')] 20strip://ul[contains(@class, 'cat-breadcrumb')]
18strip://div [@class= 'viewMorePhotos'] 21strip://div [@class= 'viewMorePhotos']
19 22
20test_url: http://www.smithsonianmag.com/history-archaeology/The-Goddess-Goes-Home.html \ No newline at end of file 23test_url: http://www.smithsonianmag.com/history-archaeology/The-Goddess-Goes-Home.html