]>
Commit | Line | Data |
---|---|---|
4e067cea NL |
1 | #metadata |
2 | title://div[@class = 'Topper']/h1 | |
3 | author://div[@class = 'Topper']/h3 | |
4 | date://div[@class = 'Topper']/h6 | |
5 | body://div[@class = 'Core'] | |
6 | ||
7 | ||
8 | ||
9 | # clean up | |
10 | strip://div[@class = 'Topper']/h1 | |
11 | strip://div[@class = 'Topper']/h3 | |
12 | strip://div[@class = 'Topper']/h4 | |
13 | strip://div[@class = 'Topper']/h5 | |
14 | strip://div[@class = 'Topper']/h6 | |
15 | strip://br[@clear = 'all'] | |
16 | strip://div[@class = 'adCore'] | |
17 | strip://div[@class = 'BookR'] | |
ac4d1142 NL |
18 | strip://div[@class = 'InfoBox'] |
19 | test_url: http://bookforum.com/inprint/018_04/8595 |