inc/3rdparty/site_config/standard/vnexpress.net.txt


1
2
3
4
5
6
7
8

body: //div[@cpms_content]//h2[@class='Lead'] | //div[@cpms_content]//p[@class='Normal'] | //div[@cpms_content]//table
strip://div[@class="box-item"]
strip://div[@id="ARTICLE_BANNER"]
strip://a
strip://div[@class="tag-parent"]
strip://div[@class="email-print txtr"]

test_url: http://vnexpress.net/gl/xa-hoi/2011/04/tim-thay-nan-nhan-cuoi-cung-vu-sap-mo-da-o-len-co/