]>
Commit | Line | Data |
---|---|---|
ac4d1142 NL |
1 | title: //div[@class='articleHead']//h1\r |
2 | author: //div[@class="author-name"]/a[1]\r | |
3 | body: //div[@class="main"]\r | |
4 | \r | |
5 | # remove 'From the Lab' and 'Recent posts' text\r | |
6 | strip: //div[@class='blogLabel']\r | |
7 | \r | |
8 | # remove byline and meta info\r | |
9 | strip: //h1\r | |
10 | strip: //div[@class="article-meta"]\r | |
11 | strip: //div[@class="author-info"]\r | |
12 | \r | |
13 | #strip tags and categories\r | |
14 | strip: //div[@class="department"]\r | |
15 | \r | |
16 | #strip product cap links\r | |
17 | strip: //div[@class="cap-main"]\r | |
18 | strip: //div[@id="compare-lede"]\r | |
19 | test_url: http://www.pcworld.com/article/262034/are-printer-companies-gouging-us-on-laser-toner-pricing.html |