From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- inc/3rdparty/site_config/standard/newsunspun.org.txt | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/newsunspun.org.txt (limited to 'inc/3rdparty/site_config/standard/newsunspun.org.txt') diff --git a/inc/3rdparty/site_config/standard/newsunspun.org.txt b/inc/3rdparty/site_config/standard/newsunspun.org.txt old mode 100644 new mode 100755 index 860ad66b..247bbebb --- a/inc/3rdparty/site_config/standard/newsunspun.org.txt +++ b/inc/3rdparty/site_config/standard/newsunspun.org.txt @@ -1,10 +1,10 @@ -body: //div[@class='right']//div[@class='articles'] -author: //div[@id='artinfo']//a[contains(@href, '/author/')] -strip: //div[@id='artinfo'] -strip: //table[//a[contains(@href, 'twitter.com')]] -strip_id_or_class: twitter - -prune: no -tidy: no - +body: //div[@class='right']//div[@class='articles'] +author: //div[@id='artinfo']//a[contains(@href, '/author/')] +strip: //div[@id='artinfo'] +strip: //table[//a[contains(@href, 'twitter.com')]] +strip_id_or_class: twitter + +prune: no +tidy: no + test_url: http://www.newsunspun.org/eotn/bbc-headline-change-iran-goes-from-not-building-to-undecided-on-nuclear-bomb \ No newline at end of file -- cgit v1.2.3