From e37feb66714437fff639340a56023a3fab0ccf57 Mon Sep 17 00:00:00 2001
From: "FiveFilters.org" <fivefilters@fivefilters.org>
Date: Sat, 30 Aug 2014 23:21:03 +0200
Subject: Add XPath expressions to check for native ads

---
 arstechnica.com.txt | 2 ++
 bbc.com.txt         | 2 ++
 theatlantic.com.txt | 2 ++
 theguardian.com.txt | 5 ++++-
 4 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/arstechnica.com.txt b/arstechnica.com.txt
index 767f680..eb92aa2 100644
--- a/arstechnica.com.txt
+++ b/arstechnica.com.txt
@@ -13,5 +13,7 @@ title: //div[@id='story']//h2[@class='title']
 strip: //div[@class='pager']
 next_page_link: //nav//a[span/@class='next']/@href
 
+native_ad_clue: //meta[@property="og:url" and contains(@content, '/sponsored/')]
+
 test_url: http://arstechnica.com/tech-policy/news/2012/02/gigabit-internet-for-80-the-unlikely-success-of-californias-sonicnet.ars
 test_url: http://arstechnica.com/apple/2005/04/macosx-10-4/
diff --git a/bbc.com.txt b/bbc.com.txt
index 93a3604..67a27c6 100644
--- a/bbc.com.txt
+++ b/bbc.com.txt
@@ -36,6 +36,8 @@ strip_id_or_class: comments_module
 replace_string(<noscript>): <div>
 replace_string(</noscript>): </div>
 
+native_ad_clue: //meta[@property="og:url" and contains(@content, '/sponsored/')]
+
 tidy: no
 prune: no
 
diff --git a/theatlantic.com.txt b/theatlantic.com.txt
index aa41b15..3fc5611 100644
--- a/theatlantic.com.txt
+++ b/theatlantic.com.txt
@@ -15,6 +15,8 @@ strip: //div[@class='earthbox']
 
 single_page_link: //article//a[contains(@class, 'print')]
 
+native_ad_clue: //meta[@property="og:url" and contains(@content, '/sponsored/')]
+
 test_url: http://www.theatlantic.com/technology/archive/2011/04/want-to-see-how-crazy-a-bot-run-market-can-be/237773/
 test_url: http://www.theatlantic.com/magazine/archive/2007/11/the-autumn-of-the-multitaskers/6342/
 test_url: http://www.theatlantic.com/entertainment/archive/2012/04/30-rock-live-a-funny-reminder-of-why-sitcoms-arent-shot-live-anymore/256447/
\ No newline at end of file
diff --git a/theguardian.com.txt b/theguardian.com.txt
index c803e4e..6243cdc 100644
--- a/theguardian.com.txt
+++ b/theguardian.com.txt
@@ -6,8 +6,11 @@ strip: //div[contains(@class, 'kindleWidget')]
 #strip: //a[not(text())]
 strip_id_or_class: pocket-btn
 author: //li[@class='byline']
+native_ad_clue: //meta[@property="article:tag" and contains(@content, "Partner zone")]
 prune: no
 tidy: no
 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
-test_url: http://www.theguardian.com/commentisfree/2014/jun/15/britishness-search-identity-my-part-in-camerons-odyssey
\ No newline at end of file
+test_url: http://www.theguardian.com/commentisfree/2014/jun/15/britishness-search-identity-my-part-in-camerons-odyssey
+# Native ad
+test_url: http://www.theguardian.com/sustainable-business/2014/jul/18/ben-jerry-turn-ice-cream-into-energy
\ No newline at end of file
-- 
cgit v1.3.1