summaryrefslogtreecommitdiff
path: root/smithsonianmag.com.txt
diff options
context:
space:
mode:
authorFiveFilters.org <fivefilters@fivefilters.org>2015-07-15 15:16:29 +0200
committerFiveFilters.org <fivefilters@fivefilters.org>2015-07-15 15:16:29 +0200
commit14b41e0b3a357ef8dcc9b2acf7ce870d5b0ba86a (patch)
tree2b82beef76264ea310d746bd8aef3e0d612a3330 /smithsonianmag.com.txt
parenta6e76e07b7e52ff1b248d1e7f53186ff54505640 (diff)
downloadftr-site-config-14b41e0b3a357ef8dcc9b2acf7ce870d5b0ba86a.tar.gz
ftr-site-config-14b41e0b3a357ef8dcc9b2acf7ce870d5b0ba86a.zip
Update smithsonianmag.com.txt
Diffstat (limited to 'smithsonianmag.com.txt')
-rw-r--r--smithsonianmag.com.txt5
1 files changed, 4 insertions, 1 deletions
diff --git a/smithsonianmag.com.txt b/smithsonianmag.com.txt
index 3e8fee9..fc479c2 100644
--- a/smithsonianmag.com.txt
+++ b/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