2014-07-13 04:15:40 -04:00
|
|
|
# Author's name, when present, has 'skrifar:' ('writes:') appended to it.
|
|
|
|
|
# In case of multiple authors, this would be 'skrifa:', hence only 7 characters
|
|
|
|
|
# are stripped off.
|
|
|
|
|
author: substring(//div[@class='paragraph']/div[@class='meta'], 0, string-length(//div[@class='paragraph']/div[@class='meta']) - 7)
|
|
|
|
|
|
|
|
|
|
date: //span[@class='date']
|
|
|
|
|
title: //h1
|
|
|
|
|
body: //div[@class='paragraph']
|
|
|
|
|
|
|
|
|
|
# Strip out author string when present
|
|
|
|
|
strip: //div[@class='paragraph']/div[@class='meta']
|
|
|
|
|
|
2013-12-06 04:13:03 -05:00
|
|
|
convert_double_br_tags: yes
|
|
|
|
|
test_url: http://visir.is/esb,-ipa,-bhm-og-bsrb/article/2012701319997
|
