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>)([Ss]*?)(?=</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>(?:(?!</?ab).)*)</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 />", "rn");
Write_Content.WriteLine(Content_Text + "rn");//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);
