下载网页信息

 private void button1_Click(object sender, EventArgs e)
        {

            String urlDownLoad = "http://www.cnblogs.com"; //需要获取网页内容的URL地址
            //因为URL地址是HTTP协议的,所以返回一个HttpWebRequest对象
            HttpWebRequest request = (HttpWebRequest) System.Net.WebRequest.Create(urlDownLoad);
            HttpWebResponse response = (HttpWebResponse) request.GetResponse();
           
                var buffer = GetBytes(response); 

                string strResult  = Encoding.ASCII.GetString(buffer);
                #region 获取网页编码

                //验证 字符编码 的正则表达式
                const string regCharset =
                    "(<meta[^>]*charset=(?<charset>[^>'\"]*)[\\s\\S]*?>)|(xml[^>]+encoding=(\"|')*(?<charset>[^>'\"]*)[\\s\\S]*?>)";
                //使用正则表达式获取网页中的实际字符编码
                var r = new Regex(regCharset, RegexOptions.IgnoreCase);
                var m1 = r.Match(strResult);
                string encodingName = (m1.Captures.Count != 0) ? m1.Groups["charset"].Value : "";

                //如果未获取  这手动替换判断
                if (string.IsNullOrEmpty(encodingName))
                {
                    //如果未获取  这手动替换判断
                    string str = m1.Groups[1].Value;
                    const string pattern = "<meta charset=\"|\">|\" />";
                    encodingName = Regex.Replace(str, pattern, "");
                }

                #endregion

                // 用网页中真实的字符编码获取下载的数据
                string strHtml = GetEncodingByName(encodingName).GetString(buffer);
            response.Close();
        }

        /// <summary>
        /// 获取网页字符编码
        /// </summary>
        /// <param name="encodingName"></param>
        /// <returns></returns>
        private static Encoding GetEncodingByName(
            string encodingName)
        {
            Encoding encoding = Encoding.Default;

            if (string.IsNullOrEmpty(encodingName)) return encoding;
            try
            {
                encoding = Encoding.GetEncoding(encodingName);
            }
            catch
            {
                encoding = Encoding.UTF8;
            }

            return encoding;
        }

        private static byte[] GetBytes(WebResponse response)
        {
            byte[] data;
            using (var memoryStream = new MemoryStream())
            {
                var buffer = new byte[0x100];

                using (var rs = response.GetResponseStream())
                {
                    if (rs != null)
                    {
                        for (var i = rs.Read(buffer, 0, buffer.Length); i > 0; i = rs.Read(buffer, 0, buffer.Length))
                        {
                            memoryStream.Write(buffer, 0, i);
                        }
                    }

                }

                data = memoryStream.ToArray();
            }

            return data;
        }

 

转载于:https://www.cnblogs.com/prolion/p/3644628.html

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值