blob: 4a5ae34433f995e450b3a7d9354abdcbc2d2ca64 (
plain) (
tree)
|
|
author: substring-before(substring-after(//div[@class='post-byline'], 'By '), ', on')
date: substring-after(//div[@class='post-byline'], ', on')
# for some reason, the following is producing a "no text [48]" error
#title: //div[@class='post-headline']
# for some reason, the following doesn't appear to isolate just the body copy
body: //div[@class='post-bodycopy']
# we solve the above issue by stripping out everything else we don't want
# these can probably all be removed if the body: command above worked
strip_id_or_class: reply
strip_id_or_class: left
strip_id_or_class: post-headline
strip_id_or_class: post-byline
strip_id_or_class: footer
test_url: http://www.uni-watch.com/2011/10/18/the-curious-case-of-steve-debergs-microphone-and-speaker/
|
