ASP网页抓取

网页抓取又称之为网络爬虫，咱们用来获取目标网站、目标模块的最新动态，能够直接抓取过来。 咱们提供抓取目标的url地址，而后写一个方法，抓取目标url的东西。

<!-- lang: c# -->
//获取某个URL下的内容
public string getContextByUrl(string url) 
{
    WebRequest request = WebRequest.Create(url);
    HttpWebResponse response = (HttpWebResponse)request.GetResponse();
    Stream dataStream = response.GetResponseStream();
    StreamReader reader = new StreamReader(dataStream,Encoding.Default);
    string result = reader.ReadToEnd();
    reader.Close();
    dataStream.Flush();
    dataStream.Close();
    response.Close();
    return result;    }

而后咱们调用此方法

<!-- lang: c# -->
string result = getContextByUrl(url);
    string name = result.Substring(result.IndexOf("tb-detail-hd"), 450);
    string aa = name.Substring(name.IndexOf("<h3>"), 50);
    string price = null;
if (url.Contains("detail"))
    {
        

        price = result.Substring(result.IndexOf("<strong>"), 50);
        
    }
    else if (url.Contains("item"))
    {
        
        price = result.Substring(result.IndexOf("<strong class>"), 50);
        
    }
    Label1.Text = aa;
   Label2.Text = price;