URL判断(java)

迷南。 2022-10-02 15:58 44阅读 0赞

public static boolean isURL(String str)\{  
//转换为小写  
str = str.toLowerCase();  
String regex = "^((https|http|ftp|rtsp|mms)?://)"  
\+ "?((\[0-9a-z\_!~\*'().&=+$%-\]+: )?\[0-9a-z\_!~\*'().&=+$%-\]+@)?" //ftp的user@  
\+ "((\[0-9\]\{1,3\}\\\\.)\{3\}\[0-9\]\{1,3\}" // IP形式的URL- 199.194.52.184  
\+ "|" // 允许IP和DOMAIN（域名）  
\+ "(\[0-9a-z\_!~\*'()-\]+\\\\.)\*" // 域名- www.  
\+ "(\[0-9a-z\]\[0-9a-z-\]\{0,61\})?\[0-9a-z\]\\\\." // 二级域名  
\+ "\[a-z\]\{2,6\})" // first level domain- .com or .museum  
\+ "(:\[0-9\]\{1,4\})?" // 端口- :80  
\+ "((/?)|" // a slash isn't required if there is no file name  
\+ "(/\[0-9a-z\_!~\*'().;?:@&=+$,%\#-\]+)+/?)$";  
return match( regex ,str );  
  
  
\}  
  
  
public static boolean isURL2(String str)\{  
String regex = "^((https|http|ftp|rtsp|mms)?://)"  
\+ "?((\[0-9a-z\_!~\*'().&=+$%-\]+: )?\[0-9a-z\_!~\*'().&=+$%-\]+@)?" //ftp的user@  
\+ "((\[0-9\]\{1,3\}\\\\.)\{3\}\[0-9\]\{1,3\}" // IP形式的URL- 199.194.52.184  
\+ "|" // 允许IP和DOMAIN（域名）  
\+ "(\[0-9a-z\_!~\*'()-\]+\\\\.)\*" // 域名- www.  
// + "(\[0-9a-z\]\[0-9a-z-\]\{0,61\})?\[0-9a-z\]\\\\." // 二级域名  
\+ "\[a-z\]\{2,6\})" // first level domain- .com or .museum  
\+ "(:\[0-9\]\{1,4\})?" // 端口- :80  
\+ "((/?)|" // a slash isn't required if there is no file name  
\+ "(/\[0-9a-z\_!~\*'().;?:@&=+$,%\#-\]+)+/?)$";  
return match( regex ,str );  
  
  
\}  
  
/\*\*  
\* 顶级域名判断  
\* @param str  
\* @return  
\*/  
public static boolean isTopURL(String str)\{  
//转换为小写  
str = str.toLowerCase();  
String domainRules = "com.cn|net.cn|org.cn|gov.cn|com.hk|公司|中国|网络|com|net|org|int|edu|gov|mil|arpa|Asia|biz|info|name|pro|coop|aero|museum|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cf|cg|ch|ci|ck|cl|cm|cn|co|cq|cr|cu|cv|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|eh|es|et|ev|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gh|gi|gl|gm|gn|gp|gr|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|in|io|iq|ir|is|it|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|ml|mm|mn|mo|mp|mq|mr|ms|mt|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nt|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|pt|pw|py|qa|re|ro|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|st|su|sy|sz|tc|td|tf|tg|th|tj|tk|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|va|vc|ve|vg|vn|vu|wf|ws|ye|yu|za|zm|zr|zw";  
String regex = "^((https|http|ftp|rtsp|mms)?://)"  
\+ "?((\[0-9a-z\_!~\*'().&=+$%-\]+: )?\[0-9a-z\_!~\*'().&=+$%-\]+@)?" //ftp的user@  
\+ "((\[0-9\]\{1,3\}\\\\.)\{3\}\[0-9\]\{1,3\}" // IP形式的URL- 199.194.52.184  
\+ "|" // 允许IP和DOMAIN（域名）  
\+ "(www+\\\\.)?" // 域名- www.  
\+ "(\[0-9a-z\]\[0-9a-z-\]\{0,61\})?\[0-9a-z\]\\\\." // 二级域名  
\+ "("+domainRules+"))" // first level domain- .com or .museum  
\+ "(:\[0-9\]\{1,4\})?" // 端口- :80  
\+ "((/?)|" // a slash isn't required if there is no file name  
\+ "(/\[0-9a-z\_!~\*'().;?:@&=+$,%\#-\]+)+/?)$";  
return match( regex ,str );  
  
  
\}  
  
  
/\*\*  
\* 提取主域名  
\*/  
public static String getTopUrl(String url)\{  
Pattern p = Pattern.compile("(?<=http://|\\\\.)\[^.\]\*?\\\\.(com|cn|net|org|biz|info|cc|tv)",Pattern.CASE\_INSENSITIVE);  
Matcher matcher = p.matcher(url);  
matcher.find();  
// System.out.println(matcher.group());  
return matcher.group();  
\}

转载于:https://www.cnblogs.com/xmyy/articles/2871871.html