（点击上方蓝字，可快速关注我们）

来源：苍

cnblogs.com/cang12138/p/7464226.html

阅读目录

1、分析html规则

2、C#完整代码

3、最后效果

心血来潮，想研究下爬虫，爬点小说。

通过百度选择了个小说网站，随便找了一本小书http://www.23us.so/files/article/html/13/13655/index.html。

一、分析html规则

思路是获取小说章节目录，循环目录，抓取所有章节中的内容，拼到txt文本中。最后形成完本小说。

1、获取小说章节目录

通过分析，我在标注的地方获取小说名字及章节目录。

// 获取小说名字

// 所有的章节都在这个table中。

下面是利用正则，获取名字与目录。

// 获取小说名字

Match ma_name = Regex.Match(html, @"");

string name = ma_name.Groups[1].Value.ToString().Split(',')[0];

// 获取章节目录

Regex reg_mulu = new Regex(@"

(.|\n)*? ");

var mat_mulu = reg_mulu.Match(html);

string mulu = mat_mulu.Groups[0].ToString();

2、获取小说正文内容

通过章节a标签中的url地址，查看章节内容。

通过分析，正文内容在

中。

// 获取正文

Regex reg = new Regex(@"

(.|\n)*?

");

MatchCollection mc = reg.Matches(html_z);

var mat = reg.Match(html_z);

string content = mat.Groups[0].ToString().Replace("

", "").Replace("

", "").Replace(" ", "").Replace("
", "\r\n");

二、C#完整代码

namespace Test.Controllers

{

public class CrawlerController : BaseController

{

// GET: Crawler

public void Index()

{

//抓取整本小说

CrawlerController cra = new CrawlerController();// 顶点抓取小说网站小说

string html = cra.HttpGet("http://www.23us.so/files/article/html/13/13655/index.html", "");

// 获取小说名字

Match ma_name = Regex.Match(html, @"");

string name = ma_name.Groups[1].Value.ToString().Split(',')[0];

// 获取章节目录

Regex reg_mulu = new Regex(@"

(.|\n)*? ");

var mat_mulu = reg_mulu.Match(html);

string mulu = mat_mulu.Groups[0].ToString();

// 匹配a标签里面的url

Regex tmpreg = new Regex("]+?href=\"([^\"]+)\"[^>]*>([^<]+)", RegexOptions.Compiled);

MatchCollection sMC = tmpreg.Matches(mulu);

if (sMC.Count != 0)

{

//循环目录url，获取正文内容

for (int i = 0; i < sMC.Count; i++)

{

//sMC[i].Groups[1].Value

//0是第一章 泰山之巅

//1是http://www.23us.so/files/article/html/13/13655/5638725.html

//2是第一章 泰山之巅

// 获取章节标题

string title = sMC[i].Groups[2].Value;

// 获取文章内容

string html_z = cra.HttpGet(sMC[i].Groups[1].Value, "");

// 获取小说名字,章节中也可以查找名字

//Match ma_name = Regex.Match(html, @"");

//string name = ma_name.Groups[1].Value.ToString().Split(',')[0];

// 获取标题,通过分析h1标签也可以得到章节标题

//string title = html_z.Replace("

", "*").Replace("

", "*").Split('*')[1];

// 获取正文

Regex reg = new Regex(@"

(.|\n)*?

");

MatchCollection mc = reg.Matches(html_z);

var mat = reg.Match(html_z);

string content = mat.Groups[0].ToString().Replace("

", "").Replace("

", "").Replace(" ", "").Replace("
", "\r\n");

// txt文本输出

string path = AppDomain.CurrentDomain.BaseDirectory.Replace("\\", "/") + "Txt/";

Novel(title + "\r\n" + content, name, path);

}

}

}

///

/// 创建文本

///

/// 内容

/// 名字

/// 路径

public void Novel(string content, string name, string path)

{

string Log = content + "\r\n";

// 创建文件夹，如果不存在就创建file文件夹

if (Directory.Exists(path) == false)

{

Directory.CreateDirectory(path);

}

// 判断文件是否存在，不存在则创建

if (!System.IO.File.Exists(path + name + ".txt"))

{

FileStream fs1 = new FileStream(path + name + ".txt", FileMode.Create, FileAccess.Write);// 创建写入文件

StreamWriter sw = new StreamWriter(fs1);

sw.WriteLine(Log);// 开始写入值

sw.Close();

fs1.Close();

}

else

{

FileStream fs = new FileStream(path + name + ".txt" + "", FileMode.Append, FileAccess.Write);

StreamWriter sr = new StreamWriter(fs);

sr.WriteLine(Log);// 开始写入值

sr.Close();

fs.Close();

}

}

public string HttpPost(string Url, string postDataStr)

{

CookieContainer cookie = new CookieContainer();

HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);

request.Method = "POST";

request.ContentType = "application/x-www-form-urlencoded";

request.ContentLength = Encoding.UTF8.GetByteCount(postDataStr);

request.CookieContainer = cookie;

Stream myRequestStream = request.GetRequestStream();

StreamWriter myStreamWriter = new StreamWriter(myRequestStream, Encoding.GetEncoding("gb2312"));

myStreamWriter.Write(postDataStr);

myStreamWriter.Close();

HttpWebResponse response = (HttpWebResponse)request.GetResponse();

response.Cookies = cookie.GetCookies(response.ResponseUri);

Stream myResponseStream = response.GetResponseStream();

StreamReader myStreamReader = new StreamReader(myResponseStream, Encoding.GetEncoding("utf-8"));

string retString = myStreamReader.ReadToEnd();

myStreamReader.Close();

myResponseStream.Close();

return retString;

}

public string HttpGet(string Url, string postDataStr)

{

HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url + (postDataStr == "" ? "" : "?") + postDataStr);

request.Method = "GET";

HttpWebResponse response;

request.ContentType = "text/html;charset=UTF-8";

try

{

response = (HttpWebResponse)request.GetResponse();

}

catch (WebException ex)

{

response = (HttpWebResponse)request.GetResponse();

}

Stream myResponseStream = response.GetResponseStream();

StreamReader myStreamReader = new StreamReader(myResponseStream, Encoding.GetEncoding("utf-8"));

string retString = myStreamReader.ReadToEnd();

myStreamReader.Close();

myResponseStream.Close();

return retString;

}

}

}

三、最后效果

看完本文有收获？请转发分享给更多人

关注「DotNet」，提升.Net技能