]>
Commit | Line | Data |
---|---|---|
4e067cea NL |
1 | title: //div[@class='articleHead']//h1 |
2 | author: //div[@class="author-name"]/a[1] | |
3 | body: //div[@class="main"] | |
4 | ||
5 | # remove 'From the Lab' and 'Recent posts' text | |
6 | strip: //div[@class='blogLabel'] | |
7 | ||
8 | # remove byline and meta info | |
9 | strip: //div[@class="article-meta"] | |
10 | strip: //div[@class="author-info"] | |
11 | ||
12 | #strip tags and categories | |
13 | strip: //div[@class="department"] | |
14 | ||
15 | #strip product cap links | |
16 | strip: //div[@class="cap-main"] | |
17 | strip: //div[@id="compare-lede"] | |
18 | test_url: http://www.techhive.com/article/2010549/up-close-with-blackberry-10.html |