summaryrefslogtreecommitdiff
path: root/searchengineland.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 /searchengineland.com.txt
downloadftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.tar.gz
ftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.zip
Initial commit
Diffstat (limited to 'searchengineland.com.txt')
-rw-r--r--searchengineland.com.txt20
1 files changed, 20 insertions, 0 deletions
diff --git a/searchengineland.com.txt b/searchengineland.com.txt
new file mode 100644
index 0000000..fb6a107
--- /dev/null
+++ b/searchengineland.com.txt
@@ -0,0 +1,20 @@
+body: //div[@class="storyBox"]
+title: //div[@class="storyBox"]/h1
+author: //a[@rel="author"]
+date: substring-before(//span[@class="dateline"], 'by')
+
+#Removes related content but cleans up article text
+strip: //h1
+strip: //p[@class="homeStory tdmSideInfo"]
+strip: //div[@id="bylineShare"]
+strip: //script
+strip: //hr
+
+strip_id_or_class: homeStory
+strip_id_or_class: authorpic
+strip_id_or_class: insideComments
+strip_id_or_class: authorbio
+strip_id_or_class: gpt-ad-sel-cube
+strip_id_or_class: smxTextAd
+
+test_url: http://searchengineland.com/googles-jaw-dropping-sponsored-post-campaign-for-chrome-106348 \ No newline at end of file