]>
Commit | Line | Data |
---|---|---|
ac4d1142 NL |
1 | # Works with old posts too, such as http://www.joelonsoftware.com/articles/fog0000000332.html\r |
2 | \r | |
3 | author: substring-after(//div[@class="author"], 'by ')\r | |
4 | date: //div[@class="date"]\r | |
5 | \r | |
6 | ## Clean stuff at top ##\r | |
7 | \r | |
8 | strip: //h1[1]\r | |
9 | strip: //h2[1]\r | |
10 | strip: //div[@class="date"]\r | |
11 | strip: //div[@class="author"]\r | |
12 | \r | |
13 | ## Clean stuff at bottom ##\r | |
14 | \r | |
15 | strip: //blockquote[@class="textmessage"]\r | |
16 | strip: //div[@style="width:500px"]/p[last()]\r | |
17 | strip: //div[@style="width:500px"]/p[last()-1]\r | |
18 | strip: //div[@style="width:500px"]/h4[last()]\r | |
19 | strip: //div[@style="width:500px"]/h4[last()-1]\r | |
20 | strip: //div[@style="width:500px"]/div[last()] | |
21 | test_url: http://www.joelonsoftware.com/items/2011/09/15.html |