blob: 2dc247a07e3ec785f58dce9ded8fde7a6e164587 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
|
# This filter is tested on:
# http://www.xfgjls.com/magazine/html/?131.html
# http://www.xfgjls.com/magazine/html/?170.html
body://h3/following-sibling::div
title: //h3
date: substring-before(//h3/following-sibling::div/p, ' ')
author: substring-before(substring-after(//h3/following-sibling::div/p, '作者:'), '来源')
wrap_in(strong)://span[contains(@style, "FONT-WEIGHT: bold")]
dissolve://span[@style="FONT-FAMILY: '宋体'; FONT-SIZE: 10.5pt; FONT-WEIGHT: bold; mso-spacerun: 'yes'"]
test_url: http://www.xfgjls.com/magazine/html/?170.html
|
