]>
Commit | Line | Data |
---|---|---|
4e067cea NL |
1 | # This filter is tested on: |
2 | # http://www.lifeweek.com.cn/2012/1211/39439.shtml | |
3 | # http://www.lifeweek.com.cn/2013/0308/40213.shtml | |
4 | ||
5 | title:substring-before(//h1, '(') | |
6 | title://h1 | |
7 | date://ul[@class='authorbox']/li | |
8 | author: substring-after(//ul[@class='authorbox']/li/following-sibling::li, '作者:') | |
9 | ||
10 | next_page_link: //div[@class='pageturn_list']/a[@class='pagedown'] | |
11 | body: //div[@class='original '] | |
12 | ||
13 | strip://h1 | |
14 | strip://ul[@class='authorbox'] | |
15 | strip://span[@class='app_p'] | |
16 | strip://div[@style='text-align:right;'] | |
17 | strip://div[@class='pageturn_list'] | |
18 | strip://div[@class='lifespeaks'] | |
19 | strip://div[@class='vright fr'] | |
20 | strip://div[@class='copyrt mg20'] | |
21 | strip://div[@class='keyabout mg20'] | |
22 | strip://ul[@class='readabout mg20'] | |
23 | test_url: http://www.lifeweek.com.cn/2013/0308/40213.shtml |