]>
Commit | Line | Data |
---|---|---|
ac4d1142 NL |
1 | # set body\r |
2 | tidy: no\r | |
3 | body: //div[contains(@class, 'articleContent')]\r | |
4 | \r | |
5 | # remove clutter\r | |
6 | strip: //div[@class='advertising']\r | |
7 | strip: //div[@class='themenalarm']\r | |
8 | strip: //div[contains(@class, 'inTextTeaser')]\r | |
9 | \r | |
10 | # remove captions\r | |
11 | strip: //span[@class='copyRight']\r | |
12 | \r | |
13 | # remove photo galleries and extras\r | |
14 | strip: //div[contains(@class, 'textGallery')]\r | |
15 | strip: //div[contains(@class, 'videoGallery')]\r | |
16 | strip: //div[contains(@class, 'imageGallery')]\r | |
17 | strip: //div[contains(@class, 'openContent')]\r | |
18 | \r | |
19 | # remove comments\r | |
20 | strip: //div[@id = 'writeComment']\r | |
21 | \r | |
22 | test_url: http://www.welt.de/vermischtes/weltgeschehen/article11050589/27-Bergleute-in-neuseelaendischer-Mine-vermisst.html |