From aedb4e5d16924080ab4e367dd05aa0d88a4685be Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 26 Aug 2015 13:40:53 +0200 Subject: philly.com --- philly.com.txt | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/philly.com.txt b/philly.com.txt index accbd60..4e04d56 100644 --- a/philly.com.txt +++ b/philly.com.txt @@ -1,10 +1,13 @@ title: //h1[@class='entry-title'] author: //p[@class='byline']/span -body: //@id='body-content' +body: //div[contains(@class, 'body-content')] date: //div[@class='article_timestamp']/span +strip_id_or_class: related-links + strip: //@class=b-group strip: //*[contains(@style, 'none')] strip: //a[contains(@href, 'comments')] strip: //*[contains(@class, 'comment')] +test_url: http://www.philly.com/philly/blogs/sports/eagles/Davis-Happy-For-Kendricks.html test_url: http://www.philly.com/philly/sports/eagles/20120127_Ohio_State_s_Posey_didn_t_waste_time_lost_to_suspension.html \ No newline at end of file -- cgit v1.3.1