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/theamericanscholar.org.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/theamericanscholar.org.txt (limited to 'inc/3rdparty/site_config/standard/theamericanscholar.org.txt') diff --git a/inc/3rdparty/site_config/standard/theamericanscholar.org.txt b/inc/3rdparty/site_config/standard/theamericanscholar.org.txt new file mode 100755 index 00000000..38b96672 --- /dev/null +++ b/inc/3rdparty/site_config/standard/theamericanscholar.org.txt @@ -0,0 +1,13 @@ +# Article Metadata +title: //meta[@property="og:title"]/@content +author: substring-after(//h3, 'By ') +date: //h4/a[2] + +# Content Pruning +strip: //h4 +strip: //a[@id="print_button"] +strip: //p[@class="excerpt"] +strip: //h3 +strip: //div[@class="caption"] +strip: //center/a/img +test_url: http://theamericanscholar.org/too-big-to-fail-and-too-risky-to-exist/ \ No newline at end of file -- cgit v1.2.3