1, 需要安装库 htmlAgilityPack https://pan.baidu.com/s/1783BSrpyM6hbpUkXo68I0Q , 官网 http://htmlagilitypack.codeplex.com/
- // From File
- var doc = new HtmlDocument();
- doc.Load(filePath);
- // From String
- var doc = new HtmlDocument();
- doc.LoadHtml(html);
- // From web
- var url = "http://html-agility-pack.net/";
- var web = new HtmlWeb();
- var doc = web.Load(url);
- //XPath
- var nodes = doc.DocumentNode.SelectNodes("//*[@id=\"body\"]");
XPath 语法: http://www.w3school.com.cn/xpath/xpath_syntax.asp
其他解析网页的方法:(引用至: https://blog.csdn.net/shenmegui_zyf/article/details/78784464 )
方法一: 使用 WebClient
- static void Main(string[] args)
- {
- try {
- WebClient MyWebClient = new WebClient();
- MyWebClient.Credentials = CredentialCache.DefaultCredentials;// 获取或设置用于向 Internet 资源的请求进行身份验证的网络凭据
- Byte[] pageData = MyWebClient.DownloadData("http://www.163.com"); // 从指定网站下载数据
- string pageHtml = Encoding.Default.GetString(pageData); // 如果获取网站页面采用的是 GB2312, 则使用这句
- //string pageHtml = Encoding.UTF8.GetString(pageData); // 如果获取网站页面采用的是 UTF-8, 则使用这句
- Console.WriteLine(pageHtml);// 在控制台输入获取的内容
- using (StreamWriter sw = new StreamWriter("c:\\test\\ouput.html"))// 将获取的内容写入文本
- {
- sw.Write(pageHtml);
- }
- Console.ReadLine();
- }
- catch(WebException webEx) {
- Console.WriteLine(webEx.Message.ToString());
- }
- }
方法二: 使用 WebBrowser
- WebBrowser web = new WebBrowser();
- web.Navigate("http://www.xjflcp.com/ssc/");
- web.DocumentCompleted += new WebBrowserDocumentCompletedEventHandler(web_DocumentCompleted);
- void web_DocumentCompleted(object sender, WebBrowserDocumentCompletedEventArgs e)
- {
- WebBrowser web = (WebBrowser)sender;
- HtmlElementCollection ElementCollection = web.Document.GetElementsByTagName("Table");
- foreach (HtmlElement item in ElementCollection)
- {
- File.AppendAllText("Kaijiang_xj.txt", item.InnerText);
- }
- }
方法三: 使用 HttpWebRequest/HttpWebResponse
- HttpWebRequest httpReq;
- HttpWebResponse httpResp;
- string strBuff = "";
- char[] cbuffer = new char[256];
- int byteRead = 0;
- string filename = @"c:\log.txt";
- /// 定义写入流操作
- public void WriteStream()
- {
- Uri httpURL = new Uri(txtURL.Text);
- ///HttpWebRequest 类继承于 WebRequest, 并没有自己的构造函数, 需通过 WebRequest 的 Creat 方法 建立, 并进行强制的类型转换
- httpReq = (HttpWebRequest)WebRequest.Create(httpURL);
- /// 通过 HttpWebRequest 的 GetResponse() 方法建立 HttpWebResponse, 强制类型转换
- httpResp = (HttpWebResponse) httpReq.GetResponse();
- ///GetResponseStream() 方法获取 HTTP 响应的数据流, 并尝试取得 URL 中所指定的网页内容
- /// 若成功取得网页的内容, 则以 System.IO.Stream 形式返回, 若失败则产生 ProtoclViolationException 错 误. 在此正确的做法应将以下的代码放到一个 try 块中处理. 这里简单处理
- Stream respStream = httpResp.GetResponseStream();
- /// 返回的内容是 Stream 形式的, 所以可以利用 StreamReader 类获取 GetResponseStream 的内容, 并以
StreamReader 类的 Read 方法依次读取网页源程序代码每一行的内容, 直至行尾 (读取的编码格式: UTF8)
- StreamReader respStreamReader = new StreamReader(respStream,Encoding.UTF8);
- byteRead = respStreamReader.Read(cbuffer,0,256);
- while (byteRead != 0)
- {
- string strResp = new string(cbuffer,0,byteRead);
- strBuff = strBuff + strResp;
- byteRead = respStreamReader.Read(cbuffer,0,256);
- }
- respStream.Close();
- txtHTML.Text = strBuff;
- }
来源: http://www.bubuko.com/infodetail-2725874.html