C#制作多线程处理强化版网络爬虫

上次做了一个帮公司妹子做了爬虫，不是很精致，这次公司项目里要用到，于是有做了一番修改，功能添加了网址图片采集，下载，线程处理界面网址图片下载等。

说说思路：首相获取初始网址的所有内容 在初始网址采集图片 去初始网址采集链接 把采集到的链接放入队列 继续采集图片，然后继续采集链接，无限循环

还是上图片大家看一下，

处理网页内容抓取跟网页网址爬取都做了改进，下面还是大家来看看代码，有不足之处，还请之处!

网页内容抓取HtmlCodeRequest,

网页网址爬取GetHttpLinks，用正则去筛选html中的Links

图片抓取GetHtmlImageUrlList，用正则去筛选html中的Img

都写进了一个封装类里面 HttpHelper

  /// <summary>  
    /// 取得HTML中所有图片的 URL。  
    /// </summary>  
    /// <param name="sHtmlText">HTML代码</param>  
    /// <returns>图片的URL列表</returns> 
public static string HtmlCodeRequest(string Url)
    {
      if (string.IsNullOrEmpty(Url))
      {
        return "";
      }
      try
      {
        //创建一个请求
        HttpWebRequest httprequst = (HttpWebRequest)WebRequest.Create(Url);
        //不建立持久性链接
        httprequst.KeepAlive = true;
        //设置请求的方法
        httprequst.Method = "GET";
        //设置标头值
        httprequst.UserAgent = "User-Agent:Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705";
        httprequst.Accept = "*/*";
        httprequst.Headers.Add("Accept-Language", "zh-cn,en-us;q=0.5");
        httprequst.ServicePoint.Expect100Continue = false;
        httprequst.Timeout = 5000;
        httprequst.AllowAutoRedirect = true;//是否允许302
        ServicePointManager.DefaultConnectionLimit = 30;
        //获取响应
        HttpWebResponse webRes = (HttpWebResponse)httprequst.GetResponse();
        //获取响应的文本流
        string content = string.Empty;
        using (System.IO.Stream stream = webRes.GetResponseStream())
        {
          using (System.IO.StreamReader reader = new StreamReader(stream, System.Text.Encoding.GetEncoding("utf-8")))
          {
            content = reader.ReadToEnd();
          }
        }
        //取消请求
        httprequst.Abort();
        //返回数据内容
        return content;
      }
      catch (Exception)
      {

        return "";
      }
    }
/// <summary>
    /// 提取页面链接
    /// </summary>
    /// <param name="html"></param>
    /// <returns></returns>
public static List<string> GetHtmlImageUrlList(string url)
    {
      string html = HttpHelper.HtmlCodeRequest(url);
      if (string.IsNullOrEmpty(html))
      {
        return new List<string>();
      }
      // 定义正则表达式用来匹配 img 标签  
      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(html);
      List<string> sUrlList = new List<string>();

      // 取得匹配项列表  
      foreach (Match match in matches)
        sUrlList.Add(match.Groups["imgUrl"].Value);
      return sUrlList;
    }


    /// <summary>
    /// 提取页面链接
    /// </summary>
    /// <param name="html"></param>
    /// <returns></returns>
    public static List<string> GetHttpLinks(string url)
    {
      //获取网址内容
      string html = HttpHelper.HtmlCodeRequest(url);
      if (string.IsNullOrEmpty(html))
      {
        return new List<string>();
      }
      //匹配http链接
      const string pattern2 = @"http(s)?://([\w-]+\.)+[\w-]+(/[\w- ./?%&=]*)?";
      Regex r2 = new Regex(pattern2, RegexOptions.IgnoreCase);
      //获得匹配结果
      MatchCollection m2 = r2.Matches(html);
      List<string> links = new List<string>();
      foreach (Match url2 in m2)
      {
        if (StringHelper.CheckUrlIsLegal(url2.ToString()) || !StringHelper.IsPureUrl(url2.ToString()) || links.Contains(url2.ToString()))
          continue;
        links.Add(url2.ToString());
      }
      //匹配href里面的链接
      const string pattern = @"(?i)<a\s[^>]*?href=(['""]?)(?!javascript|__doPostBack)(?<url>[^'""\s*#<>]+)[^>]*>"; ;
      Regex r = new Regex(pattern, RegexOptions.IgnoreCase);
      //获得匹配结果
      MatchCollection m = r.Matches(html);
      foreach (Match url1 in m)
      {
        string href1 = url1.Groups["url"].Value;
        if (!href1.Contains("http"))
        {
          href1 = Global.WebUrl + href1;
        }
        if (!StringHelper.IsPureUrl(href1) || links.Contains(href1)) continue;
        links.Add(href1);
      }
      return links;
    }  

这边下载图片有个任务条数限制，限制是200条。如果超过的话线程等待5秒，这里下载图片是异步调用的委托

public string DownLoadimg(string url)
    {
      if (!string.IsNullOrEmpty(url))
      {
        try
        {
          if (!url.Contains("http"))
          {
            url = Global.WebUrl + url;
          }
          HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
          request.Timeout = 2000;
          request.UserAgent = "User-Agent:Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705";
          //是否允许302
          request.AllowAutoRedirect = true;
          WebResponse response = request.GetResponse();
          Stream reader = response.GetResponseStream();
          //文件名
          string aFirstName = Guid.NewGuid().ToString();
          //扩展名
          string aLastName = url.Substring(url.LastIndexOf(".") + 1, (url.Length - url.LastIndexOf(".") - 1));
          FileStream writer = new FileStream(Global.FloderUrl + aFirstName + "." + aLastName, FileMode.OpenOrCreate, FileAccess.Write);
          byte[] buff = new byte[512];
          //实际读取的字节数
          int c = 0;
          while ((c = reader.Read(buff, 0, buff.Length)) > 0)
          {
            writer.Write(buff, 0, c);
          }
          writer.Close();
          writer.Dispose();
          reader.Close();
          reader.Dispose();
          response.Close();
          return (aFirstName + "." + aLastName);
        }
        catch (Exception)
        {
          return "错误：地址" + url;
        }
      }
      return "错误：地址为空";
    }

话不多说，更多的需要大家自己去改进咯！欢迎读者来与楼主进行交流。