summaryrefslogtreecommitdiff
path: root/newyorker.com.txt
diff options
context:
space:
mode:
authorFiveFilters.org <fivefilters@fivefilters.org>2013-02-27 23:43:10 +0100
committerFiveFilters.org <fivefilters@fivefilters.org>2013-02-27 23:43:10 +0100
commit9a69161c8646f63b4d9fa17c6ac3ab922d625859 (patch)
tree62a446347e1279f00383fdd7f9637cfd58a50879 /newyorker.com.txt
downloadftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.tar.gz
ftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.zip
Initial commit
Diffstat (limited to 'newyorker.com.txt')
-rw-r--r--newyorker.com.txt10
1 files changed, 10 insertions, 0 deletions
diff --git a/newyorker.com.txt b/newyorker.com.txt
new file mode 100644
index 0000000..f1e2ffa
--- /dev/null
+++ b/newyorker.com.txt
@@ -0,0 +1,10 @@
+title: //h1[@id='articlehed'] | //h2[@id="articleintro"]
+body: //div[@id='articletext']
+
+strip: //ul[@id="bc"] | //div[@id="yrail"] | //div[@class="entry-keywords"] | //div[@class="entry-categories"] | //div[@class="socialUtils"] | //div[@id="footer"]
+
+date: //h4[@id='articleauthor']/span[@class='dd dds']
+date: //div[@id="pagebody"]/div[@class='hentry entry']/div[@class='published']
+
+single_page_link: //div[@class='paginationViewSinglePage']/a
+test_url: http://www.newyorker.com/online/blogs/culture/2012/06/mug-shot-web-sites.html \ No newline at end of file