2014-07-13 04:15:40 -04:00
|
|
|
# Works with old posts too, such as http://www.joelonsoftware.com/articles/fog0000000332.html
|
|
|
|
|
|
|
|
author: substring-after(//div[@class="author"], 'by ')
|
|
|
|
date: //div[@class="date"]
|
|
|
|
|
|
|
|
## Clean stuff at top ##
|
|
|
|
|
|
|
|
strip: //h1[1]
|
|
|
|
strip: //h2[1]
|
|
|
|
strip: //div[@class="date"]
|
|
|
|
strip: //div[@class="author"]
|
|
|
|
|
|
|
|
## Clean stuff at bottom ##
|
|
|
|
|
|
|
|
strip: //blockquote[@class="textmessage"]
|
|
|
|
strip: //div[@style="width:500px"]/p[last()]
|
|
|
|
strip: //div[@style="width:500px"]/p[last()-1]
|
|
|
|
strip: //div[@style="width:500px"]/h4[last()]
|
|
|
|
strip: //div[@style="width:500px"]/h4[last()-1]
|
2013-12-06 04:13:03 -05:00
|
|
|
strip: //div[@style="width:500px"]/div[last()]
|
|
|
|
test_url: http://www.joelonsoftware.com/items/2011/09/15.html
|