




























目的:通过将网页源码自动提取,为以后自动分析网页中的元素提供了基础。进一步提取德国奔驰汽车股票数据的网页信息。将各个指数写进数据库。今天迈出了第一步。
功能:可以设定主机地址后,自动连接主机,并将源码保存到制定位置。
用到了MSXML2,在项目中添加引用“msxml3”,然后加上using MSXML2,通过他连接网络,并获取源码。
XMLHTTPClass xmlhttp=new XMLHTTPClass();
xmlhttp.open("GET",textBox2.Text,false,null,null);
xmlhttp.send(null);
string takehtml=xmlhttp.responseText;
用System.IO类对读取文件进行操作
FileInfo f = new FileInfo(filename);//创建文件
StreamWriter w = f.CreateText();
w.Write(takehtml);
w.Close();
所有源码如下:
using System;
using System.Drawing;
using System.Collections;
using System.ComponentModel;
using System.Windows.Forms;
using System.Data;
using System.Xml;
using MSXML2;
using System.IO;
namespace MyXmlHttp
{
/// <summary>
/// Form1 的摘要说明。
/// </summary>
public class Form1 : System.Windows.Forms.Form
{
private System.Windows.Forms.Button button1;
private System.Windows.Forms.TextBox textBox1;
private System.Windows.Forms.TextBox textBox2;
private System.Windows.Forms.TextBox textBox3;
private System.Windows.Forms.FolderBrowserDialog folderBrowserDialog1;
private System.Windows.Forms.Button button2;
private System.Windows.Forms.Label label1;
private System.Windows.Forms.Label label2;
/// <summary>
/// 必需的设计器变量。
/// </summary>
private System.ComponentModel.Container components = null;
public Form1()
{
//
// Windows 窗体设计器支持所必需的
//
InitializeComponent();
//
// TODO: 在 InitializeComponent 调用后添加任何构造函数代码
//
}
/// <summary>
/// 清理所有正在使用的资源。
/// </summary>
protected override void Dispose( bool disposing )
{
if( disposing )
{
if (components != null)
{
components.Dispose();
}
}
base.Dispose( disposing );
}
#region Windows 窗体设计器生成的代码
/// <summary>
/// 设计器支持所需的方法 - 不要使用代码编辑器修改
/// 此方法的内容。
/// </summary>
private void InitializeComponent()
{
this.button1 = new System.Windows.Forms.Button();
this.textBox1 = new System.Windows.Forms.TextBox();
this.textBox2 = new System.Windows.Forms.TextBox();
this.textBox3 = new System.Windows.Forms.TextBox();
this.folderBrowserDialog1 = new System.Windows.Forms.FolderBrowserDialog();
this.button2 = new System.Windows.Forms.Button();
this.label1 = new System.Windows.Forms.Label();
this.label2 = new System.Windows.Forms.Label();
this.SuspendLayout();
//
// button1
//
this.button1.Location = new System.Drawing.Point(408, 24);
this.button1.Name = "button1";
this.button1.Size = new System.Drawing.Size(56, 24);
this.button1.TabIndex = 0;
this.button1.Text = "下载";
this.button1.Click += new System.EventHandler(this.button1_Click);
//
// textBox1
//
this.textBox1.AutoSize = false;
this.textBox1.Dock = System.Windows.Forms.DockStyle.Bottom;
this.textBox1.Location = new System.Drawing.Point(0, 118);
this.textBox1.Multiline = true;
this.textBox1.Name = "textBox1";
this.textBox1.ScrollBars = System.Windows.Forms.ScrollBars.Both;
this.textBox1.Size = new System.Drawing.Size(632, 256);
this.textBox1.TabIndex = 1;
this.textBox1.Text = "";
//
// textBox2
//
this.textBox2.Location = new System.Drawing.Point(88, 24);
this.textBox2.Name = "textBox2";
this.textBox2.Size = new System.Drawing.Size(248, 21);
this.textBox2.TabIndex = 2;
this.textBox2.Text = "textBox2";
//
// textBox3
//
this.textBox3.Location = new System.Drawing.Point(88, 64);
this.textBox3.Name = "textBox3";
this.textBox3.Size = new System.Drawing.Size(248, 21);
this.textBox3.TabIndex = 3;
this.textBox3.Text = "textBox3";
//
// button2
//
this.button2.Location = new System.Drawing.Point(408, 64);
this.button2.Name = "button2";
this.button2.Size = new System.Drawing.Size(56, 24);
this.button2.TabIndex = 4;
this.button2.Text = "选择";
this.button2.Click += new System.EventHandler(this.button2_Click);
//
// label1
//
this.label1.AutoSize = true;
this.label1.Location = new System.Drawing.Point(24, 24);
this.label1.Name = "label1";
this.label1.Size = new System.Drawing.Size(54, 17);
this.label1.TabIndex = 5;
this.label1.Text = "主机地址";
//
// label2
//
this.label2.AutoSize = true;
this.label2.Location = new System.Drawing.Point(24, 64);
this.label2.Name = "label2";
this.label2.Size = new System.Drawing.Size(54, 17);
this.label2.TabIndex = 6;
this.label2.Text = "保存路径";
//
// Form1
//
this.AutoScaleBaseSize = new System.Drawing.Size(6, 14);
this.ClientSize = new System.Drawing.Size(632, 374);
this.Controls.Add(this.label2);
this.Controls.Add(this.label1);
this.Controls.Add(this.button2);
this.Controls.Add(this.textBox3);
this.Controls.Add(this.textBox2);
this.Controls.Add(this.textBox1);
this.Controls.Add(this.button1);
this.Name = "Form1";
this.Text = "网页源码读取器";
this.ResumeLayout(false);
}
#endregion
/// <summary>
/// 应用程序的主入口点。
/// </summary>
[STAThread]
static void Main()
{
Application.Run(new Form1());
}
private void button1_Click(object sender, System.EventArgs e)
{
XMLHTTPClass xmlhttp=new XMLHTTPClass();
xmlhttp.open("GET",textBox2.Text,false,null,null);
xmlhttp.send(null);
string takehtml=xmlhttp.responseText;
textBox1.Text=takehtml;
//FileStream myFile;
//myFile=new FileStream("data.text",FileMode.Create,FileAccess.ReadWrite);
String filename;
filename=textBox3.Text+"\\myText.txt";
//MessageBox.Show(filename);
FileInfo f = new FileInfo(filename);
StreamWriter w = f.CreateText();
w.Write(takehtml);
w.Close();
}
private void button2_Click(object sender, System.EventArgs e)
{
folderBrowserDialog1.ShowDialog();
textBox3.Text=folderBrowserDialog1.SelectedPath;
}
}
}
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。