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/lifeweek.com.cn.txt | 23 ++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/lifeweek.com.cn.txt (limited to 'inc/3rdparty/site_config/standard/lifeweek.com.cn.txt') diff --git a/inc/3rdparty/site_config/standard/lifeweek.com.cn.txt b/inc/3rdparty/site_config/standard/lifeweek.com.cn.txt new file mode 100755 index 00000000..e09f6692 --- /dev/null +++ b/inc/3rdparty/site_config/standard/lifeweek.com.cn.txt @@ -0,0 +1,23 @@ +# This filter is tested on: +# http://www.lifeweek.com.cn/2012/1211/39439.shtml +# http://www.lifeweek.com.cn/2013/0308/40213.shtml + +title:substring-before(//h1, '(') +title://h1 +date://ul[@class='authorbox']/li +author: substring-after(//ul[@class='authorbox']/li/following-sibling::li, '作者:') + +next_page_link: //div[@class='pageturn_list']/a[@class='pagedown'] +body: //div[@class='original '] + +strip://h1 +strip://ul[@class='authorbox'] +strip://span[@class='app_p'] +strip://div[@style='text-align:right;'] +strip://div[@class='pageturn_list'] +strip://div[@class='lifespeaks'] +strip://div[@class='vright fr'] +strip://div[@class='copyrt mg20'] +strip://div[@class='keyabout mg20'] +strip://ul[@class='readabout mg20'] +test_url: http://www.lifeweek.com.cn/2013/0308/40213.shtml \ No newline at end of file -- cgit v1.2.3