C# 读取网页源代码
using System.Net; using System.IO;
WebRequest
private 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; }
HttpWebRequest
private 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; }
WebClient
private 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; }
还有一种使用WebBrower的方法,这里就不讨论了。
另外编码方式,比如“utf-8”要填写具体网页的编码方式。
可以用正则表达式将网页中的编码方式进行提取,再写入网页内容流时加个判断就好了。
可以看到HttpWebRequest 方式最复杂,但确提供了更多的选择性。
有的网站检测客户端的UserAgent!如163.com,你如果使用WebClient WebRequest方式获取时,将获取到的是错误提示页面内容。
而通过HttpWebRequest 就没问题。