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/lrb.co.uk.txt | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/lrb.co.uk.txt (limited to 'inc/3rdparty/site_config/standard/lrb.co.uk.txt') diff --git a/inc/3rdparty/site_config/standard/lrb.co.uk.txt b/inc/3rdparty/site_config/standard/lrb.co.uk.txt old mode 100644 new mode 100755 index ce5053d4..f1aacb7d --- a/inc/3rdparty/site_config/standard/lrb.co.uk.txt +++ b/inc/3rdparty/site_config/standard/lrb.co.uk.txt @@ -1,8 +1,12 @@ -title: substring-before(//title, ' · LRB') - -body: //div[@class="article-body indent"] - -date: substring-after(//p[@class="meta-info"]/a, '· ') - -prune: no -test_url: http://www.lrb.co.uk/v33/n18/james-meek/its-already-happened \ No newline at end of file +title: //div[contains(@class, "article-body")]/hgroup/h1 +body: //div[contains(@class, "article-body")] + +date: substring-after(//p[@class="meta-info"]/a, '· ') + +author: //div[contains(@class, "article-body")]/hgroup/h2 + +strip_id_or_class: print-hide +strip_id_or_class: books + +test_url: http://www.lrb.co.uk/v33/n18/james-meek/its-already-happened +test_url: http://www.lrb.co.uk/v36/n13/benjamin-kunkel/paupers-and-richlings -- cgit v1.2.3