判断 url

我们在 android 和 java 开发中可能会遇到一个问题, 就是判断用户输入的 url 或者从网页或其他地方复制来的 url 是否为一个有效的 url, 下面是一些方法, 供大家参考:
在没有 encode 的情况下可以使用下面方法
URI uriObj = new URI(url);
这个方法来进行判定, 如果该方法抛出异常 URISyntaxException, 那么就说明这个 url 不是一个正确的 url, 不过当遇到一个 url 地址中包含字符串的时候, 也会抛出异常, 可以这个含有的链接却是一个有效的地址, 比如百度中的某些地址, 因此可以通过下面的代码进行改进:
URL urlObj = new URL(url);
URI uriObj = new URI(urlObj.getProtocol(), urlObj.getHost(), urlObj.getPath(), urlObj.getQuery(), null);
这两个方法分别会抛出 MalformedURLException 和 URISyntaxException.
不过如果你想对一些 schemes 进行限制, 可以加入以下代码:
private static final String acceptableSchemes[] = {
“http:”,
“https:”,
“file:”
};

private static boolean urlHasAcceptableScheme(String url) { 
    if (url == null) { 
        return false; 
    } 


    for (int i = 0; i < acceptableSchemes.length; i++) { 
        if (url.startsWith(acceptableSchemes[i])) { 
            return true; 
        } 
    } 
    return false; 
} 


private String isValidUrl(String incommingString) throws Exception{ 
    String url = ""; 
    URL urlObj = new URL(incommingString); 
    URI uriObj = new URI(urlObj.getProtocol(), urlObj.getHost(), urlObj.getPath(), urlObj.getQuery(), null); 
    String scheme = uriObj.getScheme(); 
    if (!urlHasAcceptableScheme(incommingString)) { 
        if (scheme != null) { 
            throw new URISyntaxException("", ""); 
        } 
    } 
    //此处需要对url进行赋值操作,例如需要加http://等 
    return url; 
} 

对于 android 开发, 还可以以这样处理:
import android.util.Patterns;//android 包下的

if (Patterns.WEB_URL.matcher(searchContent).matches()) {
// 符合标准
} else{
// 不符合标准
}
接下来提供一个完整的封装类, 不但提供了对 url 的校验, 还对 url 的大部分信息进行了封装操作, 代码如下:
package 随便写;

import static android.util.Patterns.GOOD_IRI_CHAR;

import java.util.Locale;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class WebAddress {

private String mScheme; 
private String mHost; 
private int mPort; 
private String mPath; 
private String mAuthInfo; 


static final int MATCH_GROUP_SCHEME = 1; 
static final int MATCH_GROUP_AUTHORITY = 2; 
static final int MATCH_GROUP_HOST = 3; 
static final int MATCH_GROUP_PORT = 4; 
static final int MATCH_GROUP_PATH = 5; 


/* ENRICO: imported the ParseExeption here */ 
public static class ParseException extends RuntimeException { 
    public String response; 


    ParseException(String response) { 
        this.response = response; 
    } 
} 

// 根据正则表达式进行判断
static Pattern sAddressPattern = Pattern.compile(
/* scheme / “(?:(http|https|file)\:\/\/)?” +
/
authority / “(?:([-A-Za-z0-9$_.+!*’(),;?&=]+(?:\:[-A-Za-z0-9$_.+!*’(),;?&=]+)?)@)?” +
/
host / "([" + GOOD_IRI_CHAR + "%_-][" + GOOD_IRI_CHAR + "%_\.-]|\[[0-9a-fA-F:\.]+\])?" +
/* port / "(?:\:([0-9]))?" +
/* path / "(\/?[^#])?" +
/* anchor / ".", Pattern.CASE_INSENSITIVE);

/** parses given uriString. */ 

// 用法: 将需要判断的 url 传入,new WebAddress(address) 如果抛出异常, 则会出现问题
public WebAddress(String address) throws ParseException {
if (address == null) {
throw new NullPointerException();
}

    // android.util.Log.d(LOGTAG, "WebAddress: " + address); 


    mScheme = ""; 
    mHost = ""; 
    mPort = -1; 
    mPath = "/"; 
    mAuthInfo = ""; 


    Matcher m = sAddressPattern.matcher(address); 
    String t; 
    if (m.matches()) { 
        t = m.group(MATCH_GROUP_SCHEME); 
        if (t != null) mScheme = t.toLowerCase(Locale.getDefault()); 
        t = m.group(MATCH_GROUP_AUTHORITY); 
        if (t != null) mAuthInfo = t; 
        t = m.group(MATCH_GROUP_HOST); 
        if (t != null) mHost = t; 
        t = m.group(MATCH_GROUP_PORT); 
        if (t != null && t.length() > 0) { 
            // The ':' character is not returned by the regex. 
            try { 
                mPort = Integer.parseInt(t); 
            } catch (NumberFormatException ex) { 
                throw new ParseException("Bad port"); 
            } 
        } 
        t = m.group(MATCH_GROUP_PATH); 
        if (t != null && t.length() > 0) { 
            /* handle busted myspace frontpage redirect with 
               missing initial "/" */ 
            if (t.charAt(0) == '/') { 
                mPath = t; 
            } else { 
                mPath = "/" + t; 
            } 
        } 


    } else { 
        // nothing found... outa here 
        throw new ParseException("Bad address"); 
    } 


    /* Get port from scheme or scheme from port, if necessary and 
       possible */ 
    if (mPort == 443 && mScheme.equals("")) { 
        mScheme = "https"; 
    } else if (mPort == -1) { 
        if (mScheme.equals("https")) 
            mPort = 443; 
        else 
            mPort = 80; // default 
    } 
    if (mScheme.equals("")) mScheme = "http"; 
} 


@Override 
public String toString() { 
    String port = ""; 
    if ((mPort != 443 && mScheme.equals("https")) || 
        (mPort != 80 && mScheme.equals("http"))) { 
        port = ":" + Integer.toString(mPort); 
    } 
    String authInfo = ""; 
    if (mAuthInfo.length() > 0) { 
        authInfo = mAuthInfo + "@"; 
    } 


    return mScheme + "://" + authInfo + mHost + port + mPath; 
} 


public void setScheme(String scheme) { 
  mScheme = scheme; 
} 


public String getScheme() { 
  return mScheme; 
} 


public void setHost(String host) { 
  mHost = host; 
} 


public String getHost() { 
  return mHost; 
} 


public void setPort(int port) { 
  mPort = port; 
} 


public int getPort() { 
  return mPort; 
} 


public void setPath(String path) { 
  mPath = path; 
} 


public String getPath() { 
  return mPath; 
} 


public void setAuthInfo(String authInfo) { 
  mAuthInfo = authInfo; 
} 


public String getAuthInfo() { 
  return mAuthInfo; 
} 

}

通过以上方法, 可以判断出一个 url 是否为真正的 url