]>
Commit | Line | Data |
---|---|---|
ac4d1142 NL |
1 | title: //meta[@property="og:title"]/@content\r |
2 | body: //div[@id='article_story_body']\r | |
3 | \r | |
4 | author: //h3[@class='byline']/a\r | |
5 | # for slid show content\r | |
6 | body: //ul[@id='imageSlide']//li[@class='firstSlide']//img | (//div[@class='txt_body']//p)[1]\r | |
7 | date: //li[@class='dateStamp']/small\r | |
8 | \r | |
9 | strip_id_or_class: insetFullBracket\r | |
10 | strip_id_or_class: insettipBox\r | |
11 | #strip_id_or_class: legacyInset\r | |
12 | strip_id_or_class: recipeACShopAndBuyText\r | |
13 | \r | |
14 | strip: //div[contains(@class, 'insetContent')]//cite\r | |
15 | strip: //*[contains(@style, 'visibility: hidden;')]\r | |
16 | strip: //div[contains(@class, 'insetContent') and not(contains(@class, 'image'))]\r | |
17 | \r | |
18 | prune: no\r | |
19 | tidy: no\r | |
20 | \r | |
21 | test_url: http://online.wsj.com/article/SB10001424052970203363504577185322849515102.html\r | |
22 | # slide show\r | |
23 | test_url: http://online.wsj.com/article/SB10001424052970204791104577110550376458164.html |