diff options
Diffstat (limited to 'codinghorror.com.txt')
| -rw-r--r-- | codinghorror.com.txt | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/codinghorror.com.txt b/codinghorror.com.txt new file mode 100644 index 0000000..adf6e5a --- /dev/null +++ b/codinghorror.com.txt @@ -0,0 +1,15 @@ +body: //div[@class='blogbody'] +strip: //h3[@class='title'] +date: //h2[@class='date'] +#Should Atwood just be a literal? +author: substring-before( substring-after(//div[@class='posted'], 'y'), 'V') + +# tim.kingman@... 2011-07-26 +# Prune:no to retain all-link ULs that are part of the body content like +# http://www.codinghorror.com/blog/2011/07/building-a-pc-part-vii-rebooting.html +# Then explicitly strip the "Posted By" and prev/next links that Prune:yes would have removed. + +prune: no +strip: //div[@class='posted']/following-sibling::* +strip: //div[@class='posted'] +test_url: http://www.codinghorror.com/blog/2011/07/building-a-pc-part-vii-rebooting.html
\ No newline at end of file |