summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--theguardian.com.txt3
1 files changed, 3 insertions, 0 deletions
diff --git a/theguardian.com.txt b/theguardian.com.txt
index c8b70e6..738e7d3 100644
--- a/theguardian.com.txt
+++ b/theguardian.com.txt
@@ -1,4 +1,5 @@
title: //div[@id='main-article-info']//h1
+body: //figure[contains(@itemprop, "associatedMedia")] | //div[contains(@class, "content__article-body")]
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')]
@@ -11,6 +12,8 @@ native_ad_clue: //meta[@property="video:tag" and contains(@content, "Partner zon
prune: no
tidy: no
+parser: html5php
+
strip_id_or_class: -expand-
test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption