这篇这篇文章主要是展示了一个C#语言如何抓取网站中的图片。实现原理就是基于http请求。C#给我们提供了HttpWebRequest和WebClient两个对象,方便发送请求获取数据,下面看如何实
1,HttpGetAction方法。用于发送请求获取数据后处理字符串得到图片地址
public static void HttpGetAction(string url,string path,int name)
{
Stopwatch sw = new Stopwatch();
sw.Start();
Console.WriteLine("抓取地址:" + url);
string result = string.Empty;
HttpWebRequest webRequest = WebRequest.CreateHttp(url);
webRequest.Method = "GET";
var response= webRequest.GetResponse();
using (StreamReader reader = new StreamReader((response as HttpWebResponse).GetResponseStream(), Encoding.UTF8))
{
result = reader.ReadToEnd();
reader.Close();
}
if (string.IsNullOrEmpty(result))
{
Console.WriteLine("请求地址错误");
Console.ReadKey();
return;
}
//提取img标签src地址
Regex regImg = new Regex(@"<img\b[^<>]*?\bsrc[\s\t\r\n]*=[\s\t\r\n]*[""']?[\s\t\r\n]*(?<imgUrl>[^\s\t\r\n""'<>]*)[^<>]*?/?[\s\t\r\n]*>", RegexOptions.IgnoreCase);
// 搜索匹配的字符串
MatchCollection matches = regImg.Matches(result);
//爬取数量
int i = ;
WebClient web = new WebClient();
// 取得匹配项列表
foreach (Match match in matches)
{
string imgsrc = match.Groups["imgUrl"].Value;
if (imgsrc.Contains("http") && !imgsrc.Contains(".svg"))
{
i++;
HttpGetImg(web,imgsrc, path,name);
name++;//图片名
}
}
sw.Stop();
Console.WriteLine("爬取完成!总共爬取了" + i + "张图片!");
Console.WriteLine("爬取图片耗时:" + sw.ElapsedMilliseconds / + "秒");
}
2,HttpGetImg方法。下载图片到指定目录
public static void HttpGetImg(WebClient web, string src,string path,int name)
{
Console.WriteLine("爬取图片:" + src);
if (!Directory.Exists(path))
{
Console.WriteLine("路径错误!");
Console.ReadKey();
return;
}
web.DownloadFile(src, path+name+".jpg");
Console.WriteLine("爬取图片成功:" + name+".jpg");
}
3,控制台调用
static void Main(string[] args)
{
string url= "https://www.xxxxxx.com/";
string path = Path.Combine(@"D:\word 资料\img\冬天\");
HttpHelper.HttpGetAction(url,path,);
Console.ReadKey();
}
效果图:
一个简单的C#爬虫程序就完成了。如有错误的地方还望大神指点
原文来自:一个简单的C#程序-曾亚平个人博客