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/theeuropean-magazine.com.txt | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/theeuropean-magazine.com.txt (limited to 'inc/3rdparty/site_config/standard/theeuropean-magazine.com.txt') diff --git a/inc/3rdparty/site_config/standard/theeuropean-magazine.com.txt b/inc/3rdparty/site_config/standard/theeuropean-magazine.com.txt new file mode 100755 index 00000000..a19bae15 --- /dev/null +++ b/inc/3rdparty/site_config/standard/theeuropean-magazine.com.txt @@ -0,0 +1,17 @@ +# Tested on: +# http://theeuropean-magazine.com/352-dyson-george/353-evolution-and-innovation +# http://theeuropean-magazine.com/522-casertano-stefano/919-morsi-and-the-future-of-egypt + +title://h2[@class='article-title'] +author:substring-before(substring-after(//p[@class='article-meta'], 'by'), '—') +date:substring-after(//p[@class='article-meta'], '—') +body://div[@class='article'] + +wrap_in(strong)://p[@class='article-teaser'] +move_into(//div[@class='article-head'])://li/img + +strip://h2[@class='article-title'] +strip://p[@class='article-meta'] +strip://div[@class='copyright'] +strip://div[@class='opinions-of-readers'] +test_url: http://theeuropean-magazine.com/522-casertano-stefano/919-morsi-and-the-future-of-egypt \ No newline at end of file -- cgit v1.2.3