blob: 8dcdb42b56b41fba0c6df80a47fab0de40c5bd57 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
|
body: //div[@class='byline' or @id='storyEmbSlide' or @id='mainBodyArea']
strip: //p[@class='comments']
strip: //div[@id='storyEmbSlide']//div[contains(@class, "hide")]
strip: //div[@id='tmg-related-links' or @id='outbrain-related-links' or @id='onespot-related-links']
strip: //p[@class='bbpTweet']/span[@class='timestamp']
strip: //p[@class='bbpTweet']/span[@class='metadata']//img
tidy: no
prune: no
test_url: http://www.telegraph.co.uk/news/worldnews/europe/ireland/8663451/Is-Ireland-divorcing-from-the-Catholic-Church.html
|
