]>
Commit | Line | Data |
---|---|---|
4e067cea NL |
1 | author: substring-after(substring-before(//div[@id='byline'],'|'),'By') |
2 | author: //div[@class='byline']/a | |
3 | date: //span[@class='pubdate'] | |
4 | # print friendly page | |
5 | body: //div[@id='text'] | |
6 | # regular page | |
7 | body: //div[@id= 'articlecontent'] | |
8 | ||
9 | strip: //div[@id= 'articlecontent']/h1 | |
10 | strip: //div[@id='articlecontent']/p[@class='deck'] | |
11 | strip: //div[@id='articlecontent']/div[@class='byline'] | |
12 | strip: //div[@id='articlespacer'] | |
13 | strip: //div[@id='incsharebox'] | |
14 | strip: //div[@id='articlesidebar'] | |
15 | ||
16 | prune: no | |
17 | ||
18 | single_page_link: //a[contains(@href, 'Printer_Friendly.html')] | |
19 | strip: //a[contains(., 'Dig Deeper')] | |
20 | test_url: http://www.inc.com/guides/2010/11/seven-tips-for-lobbying-politicians.html | |
ac4d1142 | 21 | test_url: http://www.inc.com/eric-schurenberg/startups-are-we-geting-irrationally-exuberant.html |