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/nybooks.com.txt | 24 +++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/nybooks.com.txt (limited to 'inc/3rdparty/site_config/standard/nybooks.com.txt') diff --git a/inc/3rdparty/site_config/standard/nybooks.com.txt b/inc/3rdparty/site_config/standard/nybooks.com.txt old mode 100644 new mode 100755 index 8ecb8961..d95ec68e --- a/inc/3rdparty/site_config/standard/nybooks.com.txt +++ b/inc/3rdparty/site_config/standard/nybooks.com.txt @@ -1,13 +1,13 @@ -strip_id_or_class: sIFR-alternate -title: //div[@id='page-title-wrapper']/div[@id='page-title']/h2 -single_page_link: //a[contains(@href, 'pagination=false') and not(contains(@href, 'printpage=true'))] - -body: //div[@id = 'article-body'] -strip_id_or_class:article-tools -strip_id_or_class:js_target -strip_id_or_class:marker -author://div[@id = 'page-title']/h3 -date://div[@id = 'page-title']/h5/a[starts-with(@href,'/issues/')] - - +strip_id_or_class: sIFR-alternate +title: //div[@id='page-title-wrapper']/div[@id='page-title']/h2 +single_page_link: //a[contains(@href, 'pagination=false') and not(contains(@href, 'printpage=true'))] + +body: //div[@id = 'article-body'] +strip_id_or_class:article-tools +strip_id_or_class:js_target +strip_id_or_class:marker +author://div[@id = 'page-title']/h3 +date://div[@id = 'page-title']/h5/a[starts-with(@href,'/issues/')] + + test_url: http://www.nybooks.com/articles/archives/2012/feb/23/were-more-unequal-you-think/ \ No newline at end of file -- cgit v1.2.3