diff options
Diffstat (limited to 'searchengineland.com.txt')
| -rw-r--r-- | searchengineland.com.txt | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/searchengineland.com.txt b/searchengineland.com.txt new file mode 100644 index 0000000..fb6a107 --- /dev/null +++ b/searchengineland.com.txt @@ -0,0 +1,20 @@ +body: //div[@class="storyBox"] +title: //div[@class="storyBox"]/h1 +author: //a[@rel="author"] +date: substring-before(//span[@class="dateline"], 'by') + +#Removes related content but cleans up article text +strip: //h1 +strip: //p[@class="homeStory tdmSideInfo"] +strip: //div[@id="bylineShare"] +strip: //script +strip: //hr + +strip_id_or_class: homeStory +strip_id_or_class: authorpic +strip_id_or_class: insideComments +strip_id_or_class: authorbio +strip_id_or_class: gpt-ad-sel-cube +strip_id_or_class: smxTextAd + +test_url: http://searchengineland.com/googles-jaw-dropping-sponsored-post-campaign-for-chrome-106348
\ No newline at end of file |