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')
-rw-r--r--inc/3rdparty/site_config/standard/smithsonianmag.com.txt20
1 files changed, 20 insertions, 0 deletions
diff --git a/inc/3rdparty/site_config/standard/smithsonianmag.com.txt b/inc/3rdparty/site_config/standard/smithsonianmag.com.txt
new file mode 100644
index 00000000..10a3f717
--- /dev/null
+++ b/inc/3rdparty/site_config/standard/smithsonianmag.com.txt
@@ -0,0 +1,20 @@
1# meta data
2title://h1[@id = 'articleTitle']
3author:substring-after(//ul[@id = 'byLine']/li[1],'By ')
4date:substring-before(substring-after(//ul[@id = 'byLine']/li[last()],','),',')
5body://div[@id = 'article-body']
6
7# full content
8single_page_link://td/li[@class = 'article-singlepage']/a
9
10# caption clean up
11wrap_in(i)://span[@class='articleImageCaptionwide']
12move_into (//span[@class='articleImageCaptionwide'])://div[@id = 'articleImage']/p
13
14
15# clean up
16strip://p[@id = 'articlePaginationWrapper']
17strip://ul[contains(@class, 'cat-breadcrumb')]
18strip://div [@class= 'viewMorePhotos']
19
20test_url: http://www.smithsonianmag.com/history-archaeology/The-Goddess-Goes-Home.html \ No newline at end of file