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/baseballprospectus.com.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/baseballprospectus.com.txt (limited to 'inc/3rdparty/site_config/standard/baseballprospectus.com.txt') diff --git a/inc/3rdparty/site_config/standard/baseballprospectus.com.txt b/inc/3rdparty/site_config/standard/baseballprospectus.com.txt new file mode 100755 index 00000000..1207b343 --- /dev/null +++ b/inc/3rdparty/site_config/standard/baseballprospectus.com.txt @@ -0,0 +1,13 @@ +title: //h1[@class='title'] +author: //p[@class="author"]/a[1] +body: //div[@class="article"] +date: //p[@class="date"] + +# remove user tools +strip: //div[@class='tools'] +strip: //h1 +strip: //h2[@class='subtitle'] +strip: //p[@class='author'] +strip: //p[@class='date'] + +test_url: http://www.baseballprospectus.com/article.php?articleid=18463 \ No newline at end of file -- cgit v1.2.3