c# 获取页面 HTML源代码

最新推荐文章于 2021-06-17 21:27:36 发布

转载最新推荐文章于 2021-06-17 21:27:36 发布 · 5.1k 阅读

C# 专栏收录该内容

5 篇文章

订阅专栏

本文介绍了一种使用C#实现的简单方法，通过HTTP请求获取网页内容，并使用特定编码进行读取。

  public static string GetPage(string url, Encoding encoding)
        {
            HttpWebRequest request = null;
            HttpWebResponse response = null;
            StreamReader reader = null;
            try
            {
                request = (HttpWebRequest)WebRequest.Create(url);
                request.UserAgent = "www.csddt.com";
                request.Timeout = 20000;
                request.AllowAutoRedirect = false;
                response = (HttpWebResponse)request.GetResponse();
                if (response.StatusCode == HttpStatusCode.OK && response.ContentLength < 1024 * 1024)
                {
                    reader = new StreamReader(response.GetResponseStream(), encoding);
                    string html = reader.ReadToEnd();
                    return html;
                }
            } catch  { }
            finally
            {
                if (response != null)
                {
                    response.Close();
                    response = null;
                }
                if (reader != null)
                    reader.Close();
                if (request != null)
                    request = null;
            }
            return string.Empty;
        }