]>
Commit | Line | Data |
---|---|---|
1 | title: //article//h1\r | |
2 | date: //meta[@name="date"]/@content\r | |
3 | author: //div[@class="author-name" or @class="article-byline"]/a[1]\r | |
4 | \r | |
5 | body: //section[@class="page"]\r | |
6 | \r | |
7 | # remove 'From the Lab' and 'Recent posts' text\r | |
8 | strip: //div[@class='blogLabel']\r | |
9 | \r | |
10 | # remove byline and meta info\r | |
11 | strip: //div[@class="article-meta"]\r | |
12 | strip: //div[@class="author-info"]\r | |
13 | \r | |
14 | #strip tags and categories\r | |
15 | strip: //div[@class="department"]\r | |
16 | \r | |
17 | #strip product cap links\r | |
18 | strip: //div[@class="cap-main"]\r | |
19 | strip: //div[@id="compare-lede"]\r | |
20 | \r | |
21 | prune: no\r | |
22 | \r | |
23 | # copes less well with Review pages, seems fine for News\r | |
24 | test_url: http://www.macworld.com/article/163184/2011/10/the_ipod_as_an_iconic_cultural_force.html |