zoukankan      html  css  js  c++  java
  • 获取HTML

     public class GetHtml
        {
            public string GetWebRequest(string url)
            {
                Uri uri = new Uri(url);
                WebRequest myReq = WebRequest.Create(uri);
                WebResponse result = myReq.GetResponse();
                Stream receviceStream = result.GetResponseStream();
                StreamReader readerOfStream = new StreamReader(receviceStream, System.Text.Encoding.GetEncoding("utf-8"));
                string strHTML = readerOfStream.ReadToEnd();
                readerOfStream.Close();
                receviceStream.Close();
                result.Close();
                return strHTML;
            }
            public string GetWebClient(string url)
            {
                string strHTML = "";
                WebClient myWebClient = new WebClient();
                Stream myStream = myWebClient.OpenRead(url);
                StreamReader sr = new StreamReader(myStream, System.Text.Encoding.GetEncoding("utf-8"));
                strHTML = sr.ReadToEnd();
                myStream.Close();
                return strHTML;
            }
            public string GetHttpWebRequest(string url)
            {
                Uri uri = new Uri(url);
                HttpWebRequest myReq = (HttpWebRequest)WebRequest.Create(uri);
                myReq.UserAgent = "User-Agent:Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705";
                myReq.Accept = "*/*";
                myReq.KeepAlive = true;
                myReq.Headers.Add("Accept-Language", "zh-cn,en-us;q=0.5");
                HttpWebResponse result = (HttpWebResponse)myReq.GetResponse();
                Stream receviceStream = result.GetResponseStream();
                StreamReader readerOfStream = new StreamReader(receviceStream, System.Text.Encoding.GetEncoding("utf-8"));
                string strHTML = readerOfStream.ReadToEnd();
                readerOfStream.Close();
                receviceStream.Close();
                result.Close();
                return strHTML;
            }
        }
  • 相关阅读:
    Python爬虫之-动态网页数据抓取
    Python爬虫之 正则表达式和re模块
    Python爬虫 XPath语法和lxml模块
    Python 多线程爬虫
    PAT 1037 在霍格沃茨找零钱
    PAT 1033 旧键盘打字
    PAT 1019 数字黑洞
    PAT 1057 数零壹
    PAT 1026 程序运行时间
    PAT 1023 组个最小数
  • 原文地址:https://www.cnblogs.com/liucyi/p/5479964.html
Copyright © 2011-2022 走看看