summaryrefslogtreecommitdiff
path: root/pcworld.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 /pcworld.com.txt
downloadftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.tar.gz
ftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.zip
Initial commit
Diffstat (limited to 'pcworld.com.txt')
-rw-r--r--pcworld.com.txt19
1 files changed, 19 insertions, 0 deletions
diff --git a/pcworld.com.txt b/pcworld.com.txt
new file mode 100644
index 0000000..7193f87
--- /dev/null
+++ b/pcworld.com.txt
@@ -0,0 +1,19 @@
+title: //div[@class='articleHead']//h1
+author: //div[@class="author-name"]/a[1]
+body: //div[@class="main"]
+
+# remove 'From the Lab' and 'Recent posts' text
+strip: //div[@class='blogLabel']
+
+# remove byline and meta info
+strip: //h1
+strip: //div[@class="article-meta"]
+strip: //div[@class="author-info"]
+
+#strip tags and categories
+strip: //div[@class="department"]
+
+#strip product cap links
+strip: //div[@class="cap-main"]
+strip: //div[@id="compare-lede"]
+test_url: http://www.pcworld.com/article/262034/are-printer-companies-gouging-us-on-laser-toner-pricing.html \ No newline at end of file