C#Url操作类封装、仿Node.Js中的Url模块实例

 //string url = "http://www.gongjuji.net:8081";
//string url = "http://www.gongjuji.net/";
//string url = "http://www.gongjuji.net/abc";
// string url = "http://www.gongjuji.net/abc/1234.html";
string url = "http://www.gongjuji.net/abc/1234.html?name=张三&age=1234#one#two";
//string url = "http://www.gongjuji.net/abc/1234.html?name=&age=#one#two";
//string url = "/abc/123.html?name=张三&age=1234#one#two";
// string url = "https://mp.weixin.qq.com/debug/cgi-bin/apiinfo?t=index&type=%e7%94%a8%e6%88%b7%e7%ae%a1%e7%90%86&form=%e8%8e%b7%e5%8f%96%e5%85%b3%e6%b3%a8%e8%80%85%e5%88%97%e8%a1%a8%e6%8e%a5%e5%8f%a3%20/user/get";
urlanalyze _url = new urlanalyze(url);
jobject obj = jobject.fromobject(_url);
console.writeline(obj);
//添加或修改参数
_url.addorupdatesearch("page", "2");
_url.addorupdatesearch("name", "李四");
//重新生成链接参数
console.writeline(_url.geturl());
console.writeline(_url.geturl(true));

//string source = "工具集：http://www.gongjuji.net";
string source = @"工具集：
  http://www.gongjuji.net
  爱汉字：http://hanzi.tianma3798.cn"; 
list<string> result = urlanalyze.geturllist(source);
foreach (var item in result)
{
  console.writeline(item);
}
//替换成a标签
string result2 = urlanalyze.replacetoa(source);
console.writeline(result2);</string>

/// <summary>
/// url地址的格式化和反格式化
/// </summary>
public class urlanalyze
{
  /// <summary>
  /// 协议名称
  /// </summary>
  public string protocol { get; set; }
  /// <summary>
  /// 是否以反斜杠结尾
  /// </summary>
  public bool slashes { get; set; }
  /// <summary>
  /// 验证信息，暂时不使用
  /// </summary>
  public string auth { get; set; }
  /// <summary>
  /// 全小写主机部分，包括端口
  /// </summary>
  public string host
  {
    get
    {
      if (this.port == null)
        return this.hostname;
      return string.format("{0}:{1}", this.hostname, this.port);
    }
  }
  /// <summary>
  /// 端口，为空时http默认是80
  /// </summary>
  public int? port { get; set; }
  /// <summary>
  /// 小写主机部分
  /// </summary>
  public string hostname { get; set; }
  /// <summary>
  /// 页面锚点参数部分 #one#two
  /// </summary>
  public string hash { get; set; }
  /// <summary>
  /// 链接查询参数部分(带问号) ?one=1&two=2
  /// </summary>
  public string search { get; set; }
  /// <summary>
  /// 路径部分
  /// </summary>
  public string pathname { get; set; }
  /// <summary>
  /// 路径+参数部分(没有锚点)
  /// </summary>
  public string path
  {
    get
    {
      if (string.isnullorempty(this.search))
        return this.pathname;
      return pathname + search;
    }
  }
  /// <summary>
  /// 转码后的原链接
  /// </summary>
  public string href { get; set; }
 
  /// <summary>
  /// 参数的key=value 列表
  /// </summary>
  private dictionary<string, string=""> _searchlist = null;
  #region 初始化处理
  /// <summary>
  /// 空初始化
  /// </summary>
  public urlanalyze() { _searchlist = new dictionary<string, string="">(); }
  /// <summary>
  /// 初始化处理
  /// </summary>
  ///<param name="url">指定相对或绝对链接
  public urlanalyze(string url)
  {
    //1.转码操作
    this.href = httputility.urldecode(url);
    initparse(this.href);
    //是否反斜杠结尾
    if (!string.isnullorempty(pathname))
      this.slashes = this.pathname.endswith("/");
    //初始化参数列表
    _searchlist = getsearchlist();
  }
  /// <summary>
  /// 将字符串格式化成对象时初始化处理
  /// </summary>
  private void initparse(string url)
  {
    //判断是否是指定协议的绝对路径
    if (url.contains("://"))
    {
      // regex reg = new regex(@"(\w+):\/\/([^/:]+)(:\d*)?([^ ]*)");
      regex reg = new regex(@"(\w+):\/\/([^/:]+)(:\d*)?(.*)");
      match match = reg.match(url);
      //协议名称
      this.protocol = match.result("$1");
      //主机
      this.hostname = match.result("$2");
      //端口
      string port = match.result("$3");
      if (string.isnullorempty(port) == false)
      {
        port = port.replace(":", "");
        this.port = convert.toint32(port);
      }
      //路径和查询参数
      string path = match.result("$4");
      if (string.isnullorempty(path) == false)
        initpath(path);
    }
    else
    {
      initpath(url);
    }
  }
  /// <summary>
  /// 字符串url格式化时，路径和参数的初始化处理
  /// </summary>
  ///<param name="path">
  private void initpath(string path)
  {
    regex reg = new regex(@"([^#?& ]*)(\??[^#]*)(#?[^?& ]*)");
    match match = reg.match(path);
    //路径和查询参数
    this.pathname = match.result("$1");
    this.search = match.result("$2");
    this.hash = match.result("$3");
  }
  #endregion
 
  #region 参数处理
  /// <summary>
  /// 获取当前参数解析结果字典列表
  /// </summary>
  /// <returns></returns>
  public dictionary<string, string=""> getsearchlist()
  {
    if (_searchlist != null)
      return _searchlist;
    _searchlist = new dictionary<string, string="">();
    if (!string.isnullorempty(search))
    {
      regex reg = new regex(@"(^|&)?(\w+)=([^&]*)", regexoptions.compiled);
      matchcollection coll = reg.matches(search);
      foreach (match item in coll)
      {
        string key = item.result("$2").tolower();
        string value = item.result("$3");
        _searchlist.add(key, value);
      }
    }
    return _searchlist;
  }
  /// <summary>
  /// 获取查询参数的值
  /// </summary>
  ///<param name="key">键
  /// <returns></returns>
  public string getsearchvalue(string key)
  {
    return _searchlist[key];
  }
  /// <summary>
  /// 添加参数key=value,如果值已经存在则修改
  /// </summary>
  ///<param name="key">键
  ///<param name="value">值
  /// <returns></returns>
  public void addorupdatesearch(string key, string value, bool encode = false)
  {
    if (encode)
      value = httputility.urlencode(value);
    //判断指定键值是否存在
    if (_searchlist.containskey(key))
    {
      _searchlist[key] = value;
    }
    else
    {
      _searchlist.add(key, value);
    }
  }
  /// <summary>
  /// 删除指定key 的键值对
  /// </summary>
  ///<param name="key">键
  public void remove(string key)
  {
    if (_searchlist.any(q => q.key == key))
      _searchlist.remove(key);
  }
  /// <summary>
  /// 获取锚点列表
  /// </summary>
  /// <returns></returns>
  public list<string> gethashlist()
  {
    list<string> list = new list<string>();
    if (!string.isnullorempty(hash))
    {
      list = hash.split('#').where(q => string.isnullorempty(q) == false)
        .tolist();
    }
    return list;
  }
  #endregion
  /// <summary>
  /// 获取最终url地址,
  /// 对参数值就行urlencode 编码后，有可能和原链接不相同
  /// </summary>
  /// <returns></returns>
  public string geturl(bool encodevalue = false)
  {
    stringbuilder builder = new stringbuilder();
    if (!string.isnullorempty(protocol))
    {
      //如果有协议
      builder.append(protocol).append("://");
    }
    //如果有主机标识
    builder.append(host);
    //如果有目录和参数
    if (!string.isnullorempty(pathname))
    {
      string pathname = pathname;
      if (pathname.endswith("/"))
        pathname = pathname.substring(0, pathname.length - 1);
      builder.append(pathname);
    }
    //判断是否反斜杠
    if (slashes)
    {
      builder.append("/");
    }
    dictionary<string, string=""> searchlist = getsearchlist();
    if (searchlist != null && searchlist.count > 0)
    {
      builder.append("?");
      bool isfirst = true;
      foreach (var item in searchlist)
      {
        if (isfirst == false)
        {
          builder.append("&");
        }
        isfirst = false;
        builder.appendformat("{0}={1}", item.key, encodevalue ? httputility.urlencode(item.value) : item.value);
      }
    }
    //锚点
    builder.append(hash);
    return builder.tostring();
  }
  #region 静态方法
  /// <summary>
  /// 获取源字符串中所有的链接（可能有重复）
  /// </summary>
  ///<param name="content">源字符串
  /// <returns></returns>
  public static list<string> geturllist(string content)
  {
    list<string> list = new list<string>();
    regex re = new regex(@"(?<url>http(s)?://([\w-]+\.)+[\w-]+(/[\w- ./?%&=]*)?)");
    matchcollection mc = re.matches(content);
    foreach (match m in mc)
    {
      if (m.success)
      {
        string url = m.result("${url}");
        list.add(url);
      }
    }
    return list;
  }
  /// <summary>
  /// 将字符串中的链接成标签
  /// </summary>
  ///<param name="content">
  /// <returns></returns>
  public static string replacetoa(string content)
  {
    regex re = new regex(@"(?<url>http(s)?://([\w-]+\.)+[\w-]+(/[\w- ./?%&=]*)?)");
    matchcollection mc = re.matches(content);
    foreach (match m in mc)
    {
      content = content.replace(m.result("${url}"), string.format("</url>{0}", m.result("${url}")));
    }
    return content;
  }
  #endregion
}</url></string></string></string></string,></string></string></string></string,></string,></string,></string,>