]>
Commit | Line | Data |
---|---|---|
ac4d1142 NL |
1 | # main sportsillustrated.com articles\r |
2 | \r | |
3 | body: //div[@id="cnnStoryContent"]\r | |
4 | title: //div[@id="cnnStoryHeadline"]//h1\r | |
5 | author: //div[@id="cnnSubBanner"]//strong\r | |
6 | date: substring-after(//div[@id="cnnTimeStamp"], "Updated: ")\r | |
7 | date: substring-after(//div[@id="cnnTimeStamp"], "Posted: ")\r | |
8 | \r | |
9 | # kill ugly font buttons\r | |
10 | strip: //div[@id="cnnSCFontButtons"]\r | |
11 | \r | |
12 | # kill misc filler videos & etc\r | |
13 | strip: //div[@class="cnnDivideContent"]\r | |
14 | strip: //*[@class="cnnTMbox"]\r | |
15 | \r | |
16 | # si vault articles\r | |
17 | # -------------\r | |
18 | body: //div[@class="siv_artPara"]\r | |
19 | title: //div[@class="siv_artHeader"]//h1\r | |
20 | author: //div[@class="byline"]\r | |
21 | date: //div[@class="date"]\r | |
22 | \r | |
23 | next_page_link: //div[@id='cnnStoryContinue']/a\r | |
24 | strip_id_or_class: cnnstorypagination\r | |
25 | \r | |
26 | test_url: http://cnnsi.com/2012/writers/peter_king/01/08/wild.card.round/index.html |