C# 网页图片爬虫的几种技术基础

一、文件流方式获取网络图片资源

方法1

string url = string.Format(@"http://webservice.36wu.com/DimensionalCodeService.asmx/GetCodeImgByString?size={0}&content={1}", 5, 123456);
System.Net.WebRequest webreq = System.Net.WebRequest.Create(url);
System.Net.WebResponse webres = webreq.GetResponse();
using(System.IO.Stream stream = webres.GetResponseStream())
{
　　ictureBox1.Image = Image.FromStream(stream);
}

方法2

生成图片的URL假设是这样：http://localhost/administrator/qrcode.aspx?pid=78

qrcode.aspx.cs的生成图片的部分代码：

Image image = new Bitmap(200, 200);
Graphics g = Graphics.FromImage(image);
try
{
  string url="http://localhost";

  DotNetBarcode bc = new DotNetBarcode();
  bc.Type = DotNetBarcode.Types.QRCode;
  bc.PrintCheckDigitChar = true;
  bc.WriteBar(url, 0, 0, 210, 210, g);

  System.IO.MemoryStream ms = new System.IO.MemoryStream();
  image.Save(ms, System.Drawing.Imaging.ImageFormat.Png);

  Response.ClearContent();
  //Response.ContentType = "image/Png";
  //Response.BinaryWrite(ms.ToArray());

  Response.ContentType = "application/octet-stream";
  Response.AddHeader("Content-Disposition", "attachment;  filename=" + HttpUtility.UrlEncode("qrcode.png", System.Text.Encoding.UTF8));
  Response.BinaryWrite(ms.ToArray());

  ms.Dispose();
}
finally
{
 g.Dispose();
 image.Dispose();
}

或者这样

string fileName = "aaa.txt";//客户端保存的文件名
string filePath = Server.MapPath("DownLoad/aaa.txt");//路径

//以字符流的形式下载文件
FileStream fs = new FileStream(filePath, FileMode.Open);
byte[] bytes = new byte[(int)fs.Length];
fs.Read(bytes, 0, bytes.Length);
fs.Close();
Response.ContentType = "application/octet-stream";
//通知浏览器下载文件而不是打开
Response.AddHeader("Content-Disposition", "attachment; filename=" + HttpUtility.UrlEncode(fileName, System.Text.Encoding.UTF8));
Response.BinaryWrite(bytes);
Response.Flush();
Response.End();

二、WebClient方式从服务器上下载文件

参考方法1：

/// <summary>
/// 下载服务器文件至客户端
/// </summary>
/// <param name="url">被下载的文件地址，绝对路径</param>
/// <param name="dir">另存放的目录</param>
public void DownloadUrlFile(string url, string dir)
{
    WebClient client = new WebClient();
    string fileName = Path.GetFileName(url);  //被下载的文件名
    string path = dir + fileName;   //另存为的绝对路径＋文件名
    try
    {
if (!System.IO.Directory.Exists(dir))
{
    System.IO.Directory.CreateDirectory(dir);
}
if (!System.IO.File.Exists(path))
{
    client.DownloadFile(url, path);
}
    }
    catch (Exception)
    {
// ShowError("文件下载失败！");
    }
}

参考方法2 ^[2]

<%@ Page Language="C#" AutoEventWireup="true" CodeBehind="GetPictureByUrl.aspx.cs" Inherits="HoverTreeMobile.GetPictureByUrl" %>
<!DOCTYPE html>
<html xmlns="http://www.w3.org/1999/xhtml">
<head runat="server">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
    <meta name="viewport" content="width=device-width, initial-scale=1" />
    <title>根据网址把图片下载到服务器 - 何问起</title>
</head>
<body>
    <form id="form1" runat="server">
    <div>
    图片网址：<br /><asp:TextBox runat="server" ID="textBoxImgUrl" Width="500" Text="http://hovertree.com/hvtimg/201508/cnvkv745.jpg" />
     <br />   <asp:Button runat="server" ID="btnImg" Text="下载" OnClick="btnImg_Click" />
        <br /><asp:Image runat="server" ID="hvtImg" />
        <br />
        <asp:Literal runat="server" ID="ltlTips" />
    </div>
    </form>
</body>
</html>

页面所对应的代码

using System;

namespace HoverTreeMobile
{
    public partial class GetPictureByUrl : System.Web.UI.Page
    {
        protected void Page_Load(object sender, EventArgs e)
        {

        }

        protected void btnImg_Click(object sender, EventArgs e)
        {
            try
            {
                System.Net.WebClient m_hvtWebClient = new System.Net.WebClient();
                

                //如果不是指定格式图片
                //例如http://hovertree.com/hvtart/bjae/t2lo8pf7.htm 是htm文件，不是图片
                if (!(textBoxImgUrl.Text.EndsWith(".jpg")
                    || textBoxImgUrl.Text.EndsWith(".gif")
                    || textBoxImgUrl.Text.EndsWith(".png")))
                {
                    ltlTips.Text = "输入的不是指定格式的图片的网址";

                    return;
                }

                //生成随机的图片文件名
                string m_picFileName = HoverTree.HoverTreeFrame.Utils.GetHoverTreeString()+ HoverTree.HoverTreeFrame.HoverString.GetLastStr(textBoxImgUrl.Text,4);

                string m_keleyiPicture = Server.MapPath("/hovertreeimages/"+ m_picFileName);
                //根据网址下载文件
                m_hvtWebClient.DownloadFile(textBoxImgUrl.Text, m_keleyiPicture);

                hvtImg.ImageUrl = "/hovertreeimages/" + m_picFileName;
                ltlTips.Text = string.Empty;
            }
            catch(Exception ex)
            {
                ltlTips.Text = ex.ToString();
            }
        }
    }
}

//生成随机的图片文件名
string m_picFileName = HoverTree.HoverTreeFrame.Utils.GetHoverTreeString()+ HoverTree.HoverTreeFrame.HoverString.GetLastStr(textBoxImgUrl.Text,4);
以上代码，请下载源代码查看详细实现方法。部分可到 LINK 查看。

HoverTree 开源项目：新增根据网址把图片下载到服务器功能

请看 HoverTreeMobile 项目，http://hovertree.com，何问起，源代码下载 LINK。

三、网页相关的方式

方法1：

　　 public partial class DownLoadFile : System.Web.UI.Page
    {
        protected void Page_Load(object sender, EventArgs e)
        {
            string picName = Request.QueryString["InternalSysURL"];
            if (!String.IsNullOrEmpty(picName))
            {
                byte[] content = this.GetImageContent(picName);
                this.WriteResponse(picName, content);
            }
        }

 

        #region
        private byte[] GetImageContent(string picName)
        {
            string fileURL = GetImgUrlPrefix() + picName;

 

            HttpWebRequest request = (HttpWebRequest)WebRequest.Create(fileURL);
            request.AllowAutoRedirect = true;

 

            WebProxy proxy = new WebProxy();
            proxy.BypassProxyOnLocal = true;
            proxy.UseDefaultCredentials = true;

 

            request.Proxy = proxy;

 

            WebResponse response = request.GetResponse();

 

            using (Stream stream = response.GetResponseStream())
            {
                using (MemoryStream ms = new MemoryStream())
                {
                    Byte[] buffer = new Byte[1024];
                    int current = 0;
                    while ((current = stream.Read(buffer, 0, buffer.Length)) != 0)
                    {
                        ms.Write(buffer, 0, current);
                    }
                    return ms.ToArray();
                }
            }
        }

 

        private void WriteResponse(string picName, byte[] content)
        {
            Response.Clear();
            Response.ClearHeaders();
            Response.Buffer = false;
            Response.ContentType = "application/octet-stream";
            Response.AppendHeader("Content-Disposition", "attachment;filename=" + HttpUtility.UrlEncode(picName, Encoding.Default));
            Response.AppendHeader("Content-Length", content.Length.ToString());
            Response.BinaryWrite(content);
            Response.Flush();
            Response.End();
        }

 

        private static string GetImgUrlPrefix()
        {
            XmlDocument xmlDoc = new XmlDocument();
            xmlDoc.Load(AppDomain.CurrentDomain.BaseDirectory + "//Pages//ItemMaintain//ImageDownLoad.xml");
            XmlNodeList nodes = xmlDoc.GetElementsByTagName("ProductImageOriginal");
            if (nodes.Count > 0)
            {
                return nodes[0].ChildNodes[0].Value;
            }
            else { return ""; }
        }

 

        #endregion
    }

方法2^[3]：

根据URL请求获取页面HTML代码

    /// <summary>  
    /// 获取网页的HTML码  
    /// </summary>  
    /// <param name="url">链接地址</param>  
    /// <param name="encoding">编码类型</param>  
    /// <returns></returns>  
    public static string GetHtmlStr(string url, string encoding)  
    {  
        string htmlStr = "";  
        if (!String.IsNullOrEmpty(url))  
        {  
            WebRequest request = WebRequest.Create(url);            //实例化WebRequest对象  
            WebResponse response = request.GetResponse();           //创建WebResponse对象  
            Stream datastream = response.GetResponseStream();       //创建流对象  
            Encoding ec = Encoding.Default;  
            if (encoding == "UTF8")  
            {  
                ec = Encoding.UTF8;  
            }  
            else if (encoding == "Default")  
            {  
                ec = Encoding.Default;  
            }  
            StreamReader reader = new StreamReader(datastream, ec);  
            htmlStr = reader.ReadToEnd();                           //读取数据  
            reader.Close();  
            datastream.Close();  
            response.Close();  
        }  
        return htmlStr;  
    }

下载网站图片

    /// <summary>  
    /// 下载网站图片  
    /// </summary>  
    /// <param name="picUrl"></param>  
    /// <returns></returns>  
    public string SaveAsWebImg(string picUrl)  
    {  
        string result = "";  
        string path = AppDomain.CurrentDomain.SetupInformation.ApplicationBase + @"/File/";  //目录  
        try  
        {  
            if (!String.IsNullOrEmpty(picUrl))  
            {  
                Random rd = new Random();  
                DateTime nowTime = DateTime.Now;  
                string fileName = nowTime.Month.ToString() + nowTime.Day.ToString() + nowTime.Hour.ToString() + nowTime.Minute.ToString() + nowTime.Second.ToString() + rd.Next(1000, 1000000) + ".jpeg";  
                WebClient webClient = new WebClient();  
                webClient.DownloadFile(picUrl, path + fileName);  
                result = fileName;  
            }  
        }  
        catch { }  
        return result;  
    }

参考文章

1. C# 通过URL获取图片并显示在PictureBox上的方法

2. 根据网址把图片下载到服务器C#代码

3. C#获取网页的HTML码、下载网站图片

4. C#如何通过URL下载图片？

相关阅读:
Python Day23
Python Day22
Python Day21
Python Day20
Python Day19
Python Day18
Python Day17
Python Day15
Appium python unittest pageobject如何实现加载多个case
Appium python Uiautomator2 多进程问题
原文地址：https://www.cnblogs.com/arxive/p/5926259.html