利用C#实现最基本的小说爬虫代码实例

/// <summary>
  /// 抓取网页并转码
  /// </summary>
  /// <param name="url"></param>
  /// <param name="post_parament"></param>
  /// <returns></returns>
  public string HttpGet(string url, string post_parament)
  {
   string html;
   HttpWebRequest Web_Request = (HttpWebRequest)WebRequest.Create(url);
   Web_Request.Timeout = 30000;
   Web_Request.Method = "GET";
   Web_Request.UserAgent = "Mozilla/4.0";
   Web_Request.Headers.Add("Accept-Encoding", "gzip, deflate");
   //Web_Request.Credentials = CredentialCache.DefaultCredentials;

   //设置代理属性WebProxy-------------------------------------------------
   WebProxy proxy = new WebProxy("111.13.7.120", 80);
   //在发起HTTP请求前将proxy赋值给HttpWebRequest的Proxy属性
   Web_Request.Proxy = proxy;

   HttpWebResponse Web_Response = (HttpWebResponse)Web_Request.GetResponse();

   if (Web_Response.ContentEncoding.ToLower() == "gzip")  // 如果使用了GZip则先解压
   {
    using (Stream Stream_Receive = Web_Response.GetResponseStream())
    {
     using (var Zip_Stream = new GZipStream(Stream_Receive, CompressionMode.Decompress))
     {
      using (StreamReader Stream_Reader = new StreamReader(Zip_Stream, Encoding.Default))
      {
       html = Stream_Reader.ReadToEnd();
      }
     }
    }
   }
   else
   {
    using (Stream Stream_Receive = Web_Response.GetResponseStream())
    {
     using (StreamReader Stream_Reader = new StreamReader(Stream_Receive, Encoding.Default))
     {
      html = Stream_Reader.ReadToEnd();
     }
    }
   }

   return html;
  }

 IWebHttpRepository webHttpRepository = new WebHttpRepository();
   string html = webHttpRepository.HttpGet(Url_Txt.Text, "");

string Novel_Name = Regex.Match(html, @"(?<=<h1>)([\S\s]*?)(?=</h1>)").Value; //获取书名

   Regex Regex_Menu = new Regex(@"(?is)(?<=<dl class=""book_list"">).+?(?=</dl>)");
   string Result_Menu = Regex_Menu.Match(html).Value; //获取列表内容


   Regex Regex_List = new Regex(@"(?is)(?<=<dd>).+?(?=</dd>)");
   var Result_List = Regex_List.Matches(Result_Menu); //获取列表集合

int i = 0; //计数
   string Menu_Content = ""; //所有章节
   foreach (var x in Result_List)
   {
    if (i < 4)
    {
     //前面五个都不是章节列表，所以剔除
    }
    else
    {
     Menu_Content += x.ToString();
    }
    i++;
   }

Regex Regex_Href = new Regex(@"(?is)<a[^>]*?href=(['""]?)(?<url>[^'""\s>]+)\1[^>]*>(?<text>(?:(?!</?a\b).)*)</a>");
   MatchCollection Result_Match_List = Regex_Href.Matches(Menu_Content); //获取href链接和a标签 innerHTML 

   string Novel_Path = Directory.GetCurrentDirectory() + "\\Novel\\" + Novel_Name + ".txt";  //小说地址
   File.Create(Novel_Path).Close();
   StreamWriter Write_Content = new StreamWriter(Novel_Path);


   foreach (Match Result_Single in Result_Match_List)
   {
    string Url_Text = Result_Single.Groups["url"].Value;
    string Content_Text = Result_Single.Groups["text"].Value;

    string Content_Html = webHttpRepository.HttpGet(Url_Txt.Text + Url_Text, "");//获取内容页

    Regex Rege_Content = new Regex(@"(?is)(?<=<p class=""Book_Text"">).+?(?=</p>)");
    string Result_Content = Rege_Content.Match(Content_Html).Value; //获取文章内容


    Regex Regex_Main = new Regex(@"(    )(.*)");
    string Rsult_Main = Regex_Main.Match(Result_Content).Value; //正文   
    string Screen_Content = Rsult_Main.Replace(" ", "").Replace("<br />", "\r\n");

    Write_Content.WriteLine(Content_Text + "\r\n");//写入标题
    Write_Content.WriteLine(Screen_Content);//写入内容
   }


   Write_Content.Dispose();
   Write_Content.Close();
   MessageBox.Show(Novel_Name+".txt 创建成功！");
   System.Diagnostics.Process.Start(Directory.GetCurrentDirectory() + \\Novel\\);