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/select.yeeyan.org.txt | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/select.yeeyan.org.txt (limited to 'inc/3rdparty/site_config/standard/select.yeeyan.org.txt') diff --git a/inc/3rdparty/site_config/standard/select.yeeyan.org.txt b/inc/3rdparty/site_config/standard/select.yeeyan.org.txt new file mode 100755 index 00000000..6e98b149 --- /dev/null +++ b/inc/3rdparty/site_config/standard/select.yeeyan.org.txt @@ -0,0 +1,18 @@ +# This filter is tested on: +# http://select.yeeyan.org/view/18312/332365 +# http://select.yeeyan.org/view/365295/333788 +# http://select.yeeyan.org/view/174464/332336 + +tidy:no +prune:no +title://h1 +author: //div[@class='sa_author']/span/a +date: substring-after(//div[@class='sa_author']/span/following-sibling::span, ':') +body: //div[@class='sa_left closetag'] +wrap_in(b)://div[@class='sa_abstract'] + +strip://ul[@class='sa_next clearfix'] +strip: //div[@class='sa_author'] +strip: //div[@class='sa_title_box'] + +test_url: http://select.yeeyan.org/view/258033/333481 \ No newline at end of file -- cgit v1.2.3