blob: 409a89774a2c33836d7fcd9a58d7a8316b680437 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
|
body: //div[@id="main"]
title: //div[@id="main"]/h3
# Remove ‘Review’ and ‘Wii’.
strip: //div[@class="badge"]
# Remove duplicate title and country flag.
strip: //h3
# Commented out below are attempts to extract the author and date, which did not work.
# author: //p[@class="extra "]/a
# date: //p[@class="extra "]/span[@class="when"]
test_url: http://www.nintendoworldreport.com/review/28400
|
