C# 爬虫简单教程

// From File 从文件获取html信息
var doc = new HtmlDocument();
doc.Load(filePath);

// From String 从字符串获取html信息
var doc = new HtmlDocument();
doc.LoadHtml(html);

// From Web  从网址获取html信息
var url = "http://html-agility-pack.net/";
var web = new HtmlWeb();
var doc = web.Load(url);

var web = new HtmlWeb();
var doc = web.Load(url);

var web = new HtmlWeb();
var doc = web.Load(url);
var htmlnode = doc?.DocumentNode?.SelectSingleNode("/html/body/header")

htmlnode.InnerText;
htmlnode.InnerHtml;
//根据属性取值
htmlnode?.GetAttributeValue("src", "未找到")

 /// <summary>
  /// 下载HTML帮助类
  /// </summary>
  public static class LoadHtmlHelper
  {
    /// <summary>
    /// 从Url地址下载页面
    /// </summary>
    /// <param name="url"></param>
    /// <returns></returns>
    public async static ValueTask<HtmlDocument> LoadHtmlFromUrlAsync(string url)
    {
      HtmlWeb web = new HtmlWeb();
       return await
         web?.LoadFromWebAsync(url);
    }

    /// <summary>
    /// 获取单个节点扩展方法
    /// </summary>
    /// <param name="htmlDocument">文档对象</param>
    /// <param name="xPath">xPath路径</param>
    /// <returns></returns>
    public static HtmlNode GetSingleNode(this HtmlDocument htmlDocument, string xPath)
    {
     return htmlDocument?.DocumentNode?.SelectSingleNode(xPath);
    }

    /// <summary>
    /// 获取多个节点扩展方法
    /// </summary>
    /// <param name="htmlDocument">文档对象</param>
    /// <param name="xPath">xPath路径</param>
    /// <returns></returns>
    public static HtmlNodeCollection GetNodes(this HtmlDocument htmlDocument, string xPath)
    {
      return htmlDocument?.DocumentNode?.SelectNodes(xPath);
    }

   

    /// <summary>
    /// 获取多个节点扩展方法
    /// </summary>
    /// <param name="htmlDocument">文档对象</param>
    /// <param name="xPath">xPath路径</param>
    /// <returns></returns>
    public static HtmlNodeCollection GetNodes(this HtmlNode htmlNode, string xPath)
    {
      return htmlNode?.SelectNodes(xPath);
    }


    /// <summary>
    /// 获取单个节点扩展方法
    /// </summary>
    /// <param name="htmlDocument">文档对象</param>
    /// <param name="xPath">xPath路径</param>
    /// <returns></returns>
    public static HtmlNode GetSingleNode(this HtmlNode htmlNode, string xPath)
    {
      return htmlNode?.SelectSingleNode(xPath);
    }

    /// <summary>
    /// 下载图片
    /// </summary>
    /// <param name="url">地址</param>
    /// <param name="filpath">文件路径</param>
    /// <returns></returns>
    public async static ValueTask<bool> DownloadImg(string url ,string filpath)
    {
      HttpClient httpClient = new HttpClient();
      try
      {
        var bytes = await httpClient.GetByteArrayAsync(url);
        using (FileStream fs = File.Create(filpath))
        {
          fs.Write(bytes, 0, bytes.Length);
        }
        return File.Exists(filpath);
      }
      catch (Exception ex)
      {
       
        throw new Exception("下载图片异常", ex);
      }
      
    }
  }