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/motherjones.com.txt | 26 +++++++++++----------- 1 file changed, 13 insertions(+), 13 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/motherjones.com.txt (limited to 'inc/3rdparty/site_config/standard/motherjones.com.txt') diff --git a/inc/3rdparty/site_config/standard/motherjones.com.txt b/inc/3rdparty/site_config/standard/motherjones.com.txt old mode 100644 new mode 100755 index d58c7d2c..851feb7e --- a/inc/3rdparty/site_config/standard/motherjones.com.txt +++ b/inc/3rdparty/site_config/standard/motherjones.com.txt @@ -1,15 +1,15 @@ -title: //h1 -body: //div[@id = 'content-area'] -next_page_link: //div[@class='node-pager']/a[contains(@class, 'next')] -tidy: no -author: //p[contains(@class, 'byline')]/a - -strip_id_or_class: node-header -strip_id_or_class: hdr-tools -strip_id_or_class: node-body-break -strip_id_or_class: pullquote -strip_id_or_class: node-pager -strip_id_or_class: author-bio -strip_id_or_class: node-footer +title: //h1 +body: //div[@id = 'content-area'] +next_page_link: //div[@class='node-pager']/a[contains(@class, 'next')] +tidy: no +author: //p[contains(@class, 'byline')]/a + +strip_id_or_class: node-header +strip_id_or_class: hdr-tools +strip_id_or_class: node-body-break +strip_id_or_class: pullquote +strip_id_or_class: node-pager +strip_id_or_class: author-bio +strip_id_or_class: node-footer test_url: http://motherjones.com/politics/2012/02/mac-mcclelland-free-online-shipping-warehouses-labor \ No newline at end of file -- cgit v1.2.3