]>
Commit | Line | Data |
---|---|---|
ac4d1142 NL |
1 | title: //h2[@class='related relatedTitle']\r |
2 | author: //a[contains(@href, 'liste.php?author_id')]\r | |
3 | \r | |
4 | # can't think of a better way unfortunately, really bad markup on this site\r | |
5 | date: substring-after(//td[@style='width:85%;'], 'vom')\r | |
6 | \r | |
7 | # not sure why, but instapaper seems to suck up the teaser paragraph\r | |
8 | # not solved!\r | |
9 | body: //div[contains(@class, 'teaser')]\r | |
10 | body: //div[@id='content']\r | |
11 | \r | |
12 | # cleanup\r | |
13 | strip: //img[@src='http://www.falter.at/web/_pics/falterlogo_dblau.gif']\r | |
14 | strip: //div[@class='servicebox']\r | |
15 | strip: //h1\r | |
16 | strip: //br\r | |
17 | strip: //td[@id='adcol'] | |
18 | test_url: http://www.falter.at/web/print/detail.php?id=1634 |