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 --- .../site_config/standard/brookings.edu.txt | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/brookings.edu.txt (limited to 'inc/3rdparty/site_config/standard/brookings.edu.txt') diff --git a/inc/3rdparty/site_config/standard/brookings.edu.txt b/inc/3rdparty/site_config/standard/brookings.edu.txt old mode 100644 new mode 100755 index 9f4fc4e3..17a47605 --- a/inc/3rdparty/site_config/standard/brookings.edu.txt +++ b/inc/3rdparty/site_config/standard/brookings.edu.txt @@ -1,13 +1,13 @@ -title: //div[@id='contentheader']/h1 -author: //p[@class='attribution']/span[@class='author']/* -# Is there a way to pull multiple authors? My XPath here is just grabbing the first - -date: /html/head/meta[@name="date"]/@content -body: //div[@class='main-content'] - -strip: //p[@class='byline'] -strip: //div[@class='img-gallery'] -strip: //div[@class='callout'] -strip: //div[@class='add-your-view'] +title: //div[@id='contentheader']/h1 +author: //p[@class='attribution']/span[@class='author']/* +# Is there a way to pull multiple authors? My XPath here is just grabbing the first + +date: /html/head/meta[@name="date"]/@content +body: //div[@class='main-content'] + +strip: //p[@class='byline'] +strip: //div[@class='img-gallery'] +strip: //div[@class='callout'] +strip: //div[@class='add-your-view'] convert_double_br_tags: yes test_url: http://www.brookings.edu/opinions/2011/1018_cyberattack_libya_goldsmith.aspx \ No newline at end of file -- cgit v1.2.3