良性URL数据集：
1，DMOZ
http://rdf.dmoz.org/rdf/
2，alexa
http://s3.amazonaws.com/alexa-static/top-1m.csv.zip
3,chinaz
http://top.chinaz.com/top500?t=48
恶意URL数据集：
1，PhishTank
http://www.phishtank.com/developer_info.php
2，malware
http://www.malwaredomainlist.com/forums/index.php?topic=3270.0
原文地址：http://blog.csdn.net/shahongzhou/article/details/44061945
