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/m.vanityfair.com.txt | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/m.vanityfair.com.txt (limited to 'inc/3rdparty/site_config/standard/m.vanityfair.com.txt') diff --git a/inc/3rdparty/site_config/standard/m.vanityfair.com.txt b/inc/3rdparty/site_config/standard/m.vanityfair.com.txt new file mode 100755 index 00000000..e47ce2ce --- /dev/null +++ b/inc/3rdparty/site_config/standard/m.vanityfair.com.txt @@ -0,0 +1,11 @@ +# Article Metadata +title: //h1 +author: //span[@class="name"]/a +date: //time + +# Content Pruning +strip: //h5 +strip: //time +strip: //div[@class="byline"] +strip: //h2[@class="headline "] +test_url: http://m.vanityfair.com/politics/2012/10/michael-lewis-profile-barack-obama \ No newline at end of file -- cgit v1.2.3