summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--theguardian.com.txt4
1 files changed, 3 insertions, 1 deletions
diff --git a/theguardian.com.txt b/theguardian.com.txt
index 88e2ecf..c8b70e6 100644
--- a/theguardian.com.txt
+++ b/theguardian.com.txt
@@ -1,5 +1,5 @@
title: //div[@id='main-article-info']//h1
-body: //div[@id='article-wrapper']
+body: //figure[contains(@itemprop, "associatedMedia")] | //div[contains(@itemprop, "articleBody")]
date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate]
strip: //div[contains(@class, 'email-subscription')]
strip: //div[contains(@class, 'kindleWidget')]
@@ -11,6 +11,8 @@ native_ad_clue: //meta[@property="video:tag" and contains(@content, "Partner zon
prune: no
tidy: no
+strip_id_or_class: -expand-
+
test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption
test_contains: The National Security Agency has made repeated attempts to develop
test_contains: The agency did not directly address those questions, instead providing a statement.