From b8588b00e9f5899f07bfaa9617ba6cf6a9282993 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Mon, 7 Oct 2013 13:14:00 +0200 Subject: theguardian.com --- theguardian.com.txt | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/theguardian.com.txt b/theguardian.com.txt index 2b50949..068b7d2 100644 --- a/theguardian.com.txt +++ b/theguardian.com.txt @@ -2,7 +2,11 @@ title: //div[@id='main-article-info']//h1 body: //div[@id='article-wrapper'] date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate] strip: //div[contains(@class, 'email-subscription')] +strip: //div[contains(@class, 'kindleWidget')] +strip: //a[not(text())] +strip_id_or_class: pocket-btn author: //li[@class='byline'] prune: no tidy: no -test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption \ No newline at end of file +test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption +test_url: http://www.theguardian.com/world/2013/oct/03/edward-snowden-files-john-lanchester \ No newline at end of file -- cgit v1.3.1