C#最基本的小说爬虫

新手学习C#,自己折腾弄了个简单的小说爬虫，实现了把小说内容爬下来写入txt，还只能爬指定网站。

第一次搞爬虫，涉及到了网络协议，正则表达式，弄得手忙脚乱跑起来效率还差劲，慢慢改吧。

爬的目标：http://www.166xs.com/xiaoshuo/83/83557/

一、先写HttpWebRequest把网站扒下来

这里有几个坑，大概说下：

第一个就是记得弄个代理IP爬网站，第一次忘了弄代理然后ip就被封了。。。。。

第二个就是要判断网页是否压缩，第一次没弄结果各种转码gbk utf都是乱码。后面解压就好了。

/// <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;
        }

二、下面就是用正则处理内容了，由于正则表达式不熟悉所以重复动作太多。

1.先获取网页内容

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

2.获取书名和文章列表

书名

文章列表

    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

3.因为章节列表前面有多余的<dd>,所以要剔除

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++;
            }

4.然后获取<a>的href和innerHTML，然后遍历访问获得内容和章节名称并处理，然后写入txt

   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(@"(&nbsp;&nbsp;&nbsp;&nbsp;)(.*)");
                string Rsult_Main = Regex_Main.Match(Result_Content).Value; //正文
                string Screen_Content = Rsult_Main.Replace("&nbsp;", "").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\\");

三、小说写入成功