]>
Commit | Line | Data |
---|---|---|
90a1a78b | 1 | body: //div[contains(concat(' ',normalize-space(@class),' '),' article ') and (contains(concat(' ',normalize-space(@class),' '),' clear '))] |
4e067cea NL |
2 | title: //div[@class="storyBox"]/h1 |
3 | author: //a[@rel="author"] | |
4 | date: substring-before(//span[@class="dateline"], 'by') | |
5 | ||
6 | #Removes related content but cleans up article text | |
7 | strip: //h1 | |
8 | strip: //p[@class="homeStory tdmSideInfo"] | |
9 | strip: //div[@id="bylineShare"] | |
10 | strip: //script | |
11 | strip: //hr | |
12 | ||
13 | strip_id_or_class: homeStory | |
14 | strip_id_or_class: authorpic | |
15 | strip_id_or_class: insideComments | |
16 | strip_id_or_class: authorbio | |
17 | strip_id_or_class: gpt-ad-sel-cube | |
18 | strip_id_or_class: smxTextAd | |
ac4d1142 NL |
19 | |
20 | test_url: http://searchengineland.com/googles-jaw-dropping-sponsored-post-campaign-for-chrome-106348 |