使用聚合接口获取汉字数据字典

如何获取全部汉字及汉字的详细信息？

刚刚扒了一通汉字完整的数据字典，mark作下记录。

所有汉字集合

我们匹配中文字符时，经常使用Unicode字符"[^u4e00-u9fa5]"正则表达式来校验。

详细的汉字字符集列表可参考：

具体的汉字对应的字符，可查询汉字字符集编码查询网站

基本汉字中从4e00到9fa5，十六进制转化为十进制后，可知共有20902个汉字。

汉字的集合，是开源的，可以直接从网上获取。

• 百度文库-中国汉字大全
• Github-HanziToPinyin
• CSDN-中国所有汉字-简体

从以上链接中，下载汉字集合

获取汉字信息

汉字的详细信息，包括拼音/笔画数/部首/五笔输入/笔顺编号/注解

网上有相应的新华字典Api接口，这里选的是聚合平台-新华字典

通过他的C#源码,我们可以获取到汉字字典的详细信息

详细数据请点击 下载

PS:

• 部首和五笔可能为空，部首返回的数据为："难检字"。
• 笔顺编号可通过返回的简解中得到。笔顺编号，即指每个笔画对应的号码，这个非常有用！

聚合接口-汉字

获取汉字：

        public static HanziDetail FindHanzi(string hanzi)
        {
            //1.根据汉字查询字典
            string url1 = "http://v.juhe.cn/xhzd/query";

            var parameters1 = new Dictionary<string, string>();

            parameters1.Add("word", hanzi); //填写需要查询的汉字，UTF8 urlencode编码
            parameters1.Add("key", "XXXXXX");//你申请的key
            parameters1.Add("dtype", ""); //返回数据的格式,xml或json，默认json

            string result2 = SendPost(url1, parameters1, "get");

            var hanziRequestResponse = JsonConvert.DeserializeObject<HanziRequestResponse>(result2);

            //HanziDetail hanziDetail = null;
            //if (hanziRequestResponse.ErrorCode == "0" && hanziRequestResponse.Result != null)
            //{
            //    hanziDetail = hanziRequestResponse.Result;
            //}

            return hanziRequestResponse.Result;
        }
    }

解析类：

    [DataContract]
    public class HanziRequestResponse
    {
        [DataMember(Name = "reason")]
        public string Reason { get; set; }

        [DataMember(Name = "error_code")]
        public string ErrorCode { get; set; }

        [DataMember(Name = "result")]
        public HanziDetail Result { get; set; }
    }
    [DataContract]
    public class HanziDetail
    {
        [DataMember(Name = "zi")]
        public string Hanzi { get; set; }

        /// <summary>
        /// 部首
        /// </summary>
        [DataMember(Name = "bushou")]
        public string Radical { get; set; }

        /// <summary>
        /// 拼音
        /// </summary>
        [DataMember(Name = "pinyin")]
        public string Pinyin { get; set; }

        /// <summary>
        /// 笔画数
        /// </summary>
        [DataMember(Name = "bihua")]
        public string Bihua { get; set; }

        /// <summary>
        /// 五笔
        /// </summary>
        [DataMember(Name = "wubi")]
        public string WuBi { get; set; }

        /// <summary>
        /// 极简介绍
        /// </summary>
        [DataMember(Name = "jijie")]
        public List<string> SimpleDetailContent { get; set; }
    }

访问后台接口通用类：

    public class HttpRequestBase
    {
        /// <summary>
        /// Http (GET/POST)
        /// </summary>
        /// <param name="url">请求URL</param>
        /// <param name="parameters">请求参数</param>
        /// <param name="method">请求方法</param>
        /// <returns>响应内容</returns>
        public static string SendPost(string url, IDictionary<string, string> parameters, string method)
        {
            if (method.ToLower() == "post")
            {
                HttpWebRequest req = null;
                HttpWebResponse rsp = null;
                System.IO.Stream reqStream = null;
                try
                {
                    req = (HttpWebRequest)WebRequest.Create(url);
                    req.Method = method;
                    req.KeepAlive = false;
                    req.ProtocolVersion = HttpVersion.Version10;
                    req.Timeout = 5000;
                    req.ContentType = "application/x-www-form-urlencoded;charset=utf-8";
                    byte[] postData = Encoding.UTF8.GetBytes(BuildQuery(parameters, "utf8"));
                    reqStream = req.GetRequestStream();
                    reqStream.Write(postData, 0, postData.Length);
                    rsp = (HttpWebResponse)req.GetResponse();
                    Encoding encoding = Encoding.GetEncoding(rsp.CharacterSet);
                    return GetResponseAsString(rsp, encoding);
                }
                catch (Exception ex)
                {
                    return ex.Message;
                }
                finally
                {
                    if (reqStream != null) reqStream.Close();
                    if (rsp != null) rsp.Close();
                }
            }
            else
            {
                //创建请求
                HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url + "?" + BuildQuery(parameters, "utf8"));

                //GET请求
                request.Method = "GET";
                request.ReadWriteTimeout = 5000;
                request.ContentType = "text/html;charset=UTF-8";
                HttpWebResponse response = (HttpWebResponse)request.GetResponse();
                Stream myResponseStream = response.GetResponseStream();
                StreamReader myStreamReader = new StreamReader(myResponseStream, Encoding.GetEncoding("utf-8"));

                //返回内容
                string retString = myStreamReader.ReadToEnd();
                return retString;
            }
        }

        /// <summary>
        /// 组装普通文本请求参数。
        /// </summary>
        /// <param name="parameters">Key-Value形式请求参数字典</param>
        /// <returns>URL编码后的请求数据</returns>
        public static string BuildQuery(IDictionary<string, string> parameters, string encode)
        {
            StringBuilder postData = new StringBuilder();
            bool hasParam = false;
            IEnumerator<KeyValuePair<string, string>> dem = parameters.GetEnumerator();
            while (dem.MoveNext())
            {
                string name = dem.Current.Key;
                string value = dem.Current.Value;
                // 忽略参数名或参数值为空的参数
                if (!string.IsNullOrEmpty(name))//&& !string.IsNullOrEmpty(value)
                {
                    if (hasParam)
                    {
                        postData.Append("&");
                    }
                    postData.Append(name);
                    postData.Append("=");
                    if (encode == "gb2312")
                    {
                        postData.Append(HttpUtility.UrlEncode(value, Encoding.GetEncoding("gb2312")));
                    }
                    else if (encode == "utf8")
                    {
                        postData.Append(HttpUtility.UrlEncode(value, Encoding.UTF8));
                    }
                    else
                    {
                        postData.Append(value);
                    }
                    hasParam = true;
                }
            }
            return postData.ToString();
        }

        /// <summary>
        /// 把响应流转换为文本。
        /// </summary>
        /// <param name="rsp">响应流对象</param>
        /// <param name="encoding">编码方式</param>
        /// <returns>响应文本</returns>
        public static string GetResponseAsString(HttpWebResponse rsp, Encoding encoding)
        {
            System.IO.Stream stream = null;
            StreamReader reader = null;
            try
            {
                // 以字符流的方式读取HTTP响应
                stream = rsp.GetResponseStream();
                reader = new StreamReader(stream, encoding);
                return reader.ReadToEnd();
            }
            finally
            {
                // 释放资源
                if (reader != null) reader.Close();
                if (stream != null) stream.Close();
                if (rsp != null) rsp.Close();
            }
        }
    }

详细的源Demo，可查看Github ：HanziDictionary