]>
Commit | Line | Data |
---|---|---|
ac4d1142 NL |
1 | #keep all body text\r |
2 | prune: no\r | |
3 | \r | |
4 | #title, body, metadata\r | |
5 | title: //div[@class='story_header']/h1\r | |
6 | body: //div[@id='content']\r | |
7 | author: substring-after(//span[@class='byline'], "by ")\r | |
8 | author: substring-after(//span[@class='byline'], "By ")\r | |
9 | author: //span[@class='byline']\r | |
10 | date: //span[@class='date']\r | |
11 | \r | |
12 | #formatting\r | |
13 | convert_double_br_tags: yes\r | |
14 | dissolve: //div[@class='slides_full']/ul/li\r | |
15 | \r | |
16 | # cleanup\r | |
17 | strip: //a[@id='story_note']\r | |
18 | strip: //br\r | |
19 | strip: //div[@class='intro']\r | |
20 | strip: //div[@class='share-block']\r | |
21 | strip: //div[@class='sidebar-social']\r | |
22 | strip: //div[@class='top-stories']\r | |
23 | strip: //div[@class='prevnext']\r | |
24 | test_url: http://www.thedaily.com/page/2012/01/09/010912-news-college-costs-1-5/ |