java 解析URL里的協議及參數工具類,解析URL中的主域名,並統一把協議修改成http或去掉協議
public class UrlDomainUtils {
private static final Logger LOGGER = LoggerFactory.getLogger(UrlDomainUtils.class);
/**
* 獲取主域名,即URL頭
* @param url
* @return
*/
public static String getDomainHost(String url){
String pattern = "^((http://)|(https://))?([a-zA-Z0-9]([a-zA-Z0-9\\-]{0,61}[a-zA-Z0-9])?\\.)+[a-zA-Z]{2,6}(/)";
Pattern p = Pattern.compile(pattern);
String line = url;
Matcher m = p.matcher(line);
if(m.find()){
//匹配結果
String domain = m.group();
LOGGER.info("解析的URL主域名是------------>{} 原始url is {}" ,domain,url);
domain = domain.replace("https","http");
LOGGER.info("修改解析出的URL主域名的協議成http------------>{} 原始url is {}" ,domain,url);
// domain = domain.replace("http://","");
// LOGGER.info("修改解析出的URL主域名后去掉協議------------>{} 原始url is {}" ,domain,url);
return domain;
}
LOGGER.info("未找到的URL主域名 原始url is {}" ,url);
return null;
}
/**
* 獲取主域名,即URL頭
* @param url
* @param key url中的參數key
* @return
*/
public static Map<String, String> parseURLParam(String URL, String key) {
Map<String, String> mapRequest = new HashMap<String, String>();
String[] arrSplit = null;
String strUrlParam = TruncateUrlPage(URL);
if (strUrlParam == null) {
return mapRequest;
}
//每個鍵值為一組
arrSplit = strUrlParam.split("[&]");
for (String strSplit : arrSplit) {
String[] arrSplitEqual = null;
arrSplitEqual = strSplit.split("[=]");
//解析出鍵值
if (arrSplitEqual.length > 1) {
//正確解析
if(key.equals(arrSplitEqual[0])){
mapRequest.put(arrSplitEqual[0], arrSplitEqual[1]);
break;
}
} else {
if (arrSplitEqual[0] != "") {
//只有參數沒有值,不加入
mapRequest.put(arrSplitEqual[0], "");
}
}
}
return mapRequest;
}
/**
* 截取URL中的?之后的部分
* @param strUrl
* @return
*/
private static String TruncateUrlPage(String strURL) {
String strAllParam = null;
String[] arrSplit = null;
strURL = strURL.trim();
arrSplit = strURL.split("[?]");
if (strURL.length() > 1) {
if (arrSplit.length > 1) {
if (arrSplit[1] != null) {
strAllParam = arrSplit[1];
}
}
}
return strAllParam;
}
public static void main(String[] args) {
String url = "https://www.baidu.com/s?wd=%E6%B5%8B%E8%AF%95&rsv_spt=1&rsv_iqid=0xeb51775c000b6302&issp=1&f=8&rsv_bp=1&rsv_idx=2&ie=utf-8&tn=baiduhome_pg&rsv_enter=1&rsv_dl=tb&rsv_sug3=6&rsv_sug1=2&rsv_sug7=100&rsv_sug2=0&inputT=928&rsv_sug4=3731";
getDomainHost(url);
}
}