How to read div content from a web page ?

Question

0.00/5 (No votes)

See more:

HI Experts,

I have developed a windows form application. Using this application I am opening a website. This website used to search user's data on the basis of user's last name and birth date. My application is automatically opening the website. placing the user's last name and birth date to its corresponding textboxes. After this clicking the search button and getting the result.

Problem: After getting the result in the webpage I have to read some data from the page. This result is coming in div. so how to get that div content.

Any help will be appreciated..!

What I have tried:

C#

<pre>using System;
using System.Drawing;
using System.Collections;
using System.ComponentModel;
using System.Windows.Forms;
using System.Data;
using mshtml;
using System.Collections.Generic;
using System.Configuration;
using System.IO;
using System.Text;
using System.Net;

namespace mshtml_automation_demo
{
	/// <summary>
	/// Summary description for Form1.
	/// </summary>
	public class MainForm : System.Windows.Forms.Form
	{
		private AxSHDocVw.AxWebBrowser axWebBrowser1;
		private int Task = 1; // global

		/// <summary>
		/// Required designer variable.
		/// </summary>
		private System.ComponentModel.Container components = null;

		public MainForm()
		{
			//
			// Required for Windows Form Designer support
			//
			InitializeComponent();

			//
			// TODO: Add any constructor code after InitializeComponent call
			//
		}

		/// <summary>
		/// Clean up any resources being used.
		/// </summary>
		protected override void Dispose( bool disposing )
		{
			if( disposing )
			{
				if (components != null) 
				{
					components.Dispose();
				}
			}
			base.Dispose( disposing );
		}

		#region Windows Form Designer generated code
		/// <summary>
		/// Required method for Designer support - do not modify
		/// the contents of this method with the code editor.
		/// </summary>
		private void InitializeComponent()
		{
			System.Resources.ResourceManager resources = new System.Resources.ResourceManager(typeof(MainForm));
			this.axWebBrowser1 = new AxSHDocVw.AxWebBrowser();
			((System.ComponentModel.ISupportInitialize)(this.axWebBrowser1)).BeginInit();
			this.SuspendLayout();
			// 
			// axWebBrowser1
			// 
			this.axWebBrowser1.Dock = System.Windows.Forms.DockStyle.Fill;
			this.axWebBrowser1.Enabled = true;
			this.axWebBrowser1.Location = new System.Drawing.Point(0, 0);
			this.axWebBrowser1.OcxState = ((System.Windows.Forms.AxHost.State)(resources.GetObject("axWebBrowser1.OcxState")));
			this.axWebBrowser1.Size = new System.Drawing.Size(616, 382);
			this.axWebBrowser1.TabIndex = 0;
			this.axWebBrowser1.DocumentComplete += new AxSHDocVw.DWebBrowserEvents2_DocumentCompleteEventHandler(this.axWebBrowser1_DocumentComplete);
			// 
			// MainForm
			// 
			this.AutoScaleBaseSize = new System.Drawing.Size(5, 13);
			this.ClientSize = new System.Drawing.Size(616, 382);
			this.Controls.Add(this.axWebBrowser1);
			this.Name = "MainForm";
			this.Text = "Microsoft WebBrowser Automation";
			this.Load += new System.EventHandler(this.FrmMain_Load);
			((System.ComponentModel.ISupportInitialize)(this.axWebBrowser1)).EndInit();
			this.ResumeLayout(false);

		}
		#endregion

		/// <summary>
		/// The main entry point for the application.
		/// </summary>
		[STAThread]
		static void Main() 
		{
			Application.Run(new MainForm());
		}

		private void FrmMain_Load(object sender, System.EventArgs e)
		{
            object loc = "https://www.vca.ssvv.nl/";
			object null_obj_str = "";
			System.Object null_obj = 0;
			this.axWebBrowser1.Navigate2(ref loc , ref null_obj, ref null_obj, ref null_obj_str, ref null_obj_str);
		}
        public static void OutputText(string VcaTypeExpDate)
        {
            string output = "C:\\Export\\Temp\\Logs\\";
            //string output = "C:\\Export\\Raildocs\\Logs\\";
            // string output = "F:\\Test_Cord\\Log\\";
            StreamWriter Res;
            FileStream fileStream = null;
            DirectoryInfo logDirInfo = null;
            FileInfo logFileInfo;
            var ResFilePath = output;
            ResFilePath = ResFilePath + "Result.txt";
            logFileInfo = new FileInfo(ResFilePath);
            logDirInfo = new DirectoryInfo(logFileInfo.DirectoryName);
            if (!logDirInfo.Exists) logDirInfo.Create();
            if (!logFileInfo.Exists)
            {
                fileStream = logFileInfo.Create();
            }
            else
            {
                fileStream = new FileStream(ResFilePath, FileMode.Append);
            }
            Res = new StreamWriter(fileStream);
            Res.WriteLine(VcaTypeExpDate);
            Res.Close();
        }

		private void axWebBrowser1_DocumentComplete(object sender, AxSHDocVw.DWebBrowserEvents2_DocumentCompleteEvent e)
		{
            List<string> CVList = new List<string>();
            string inputCV = ConfigurationManager.AppSettings["inputFile"];
            string outputCV = ConfigurationManager.AppSettings["outputFile"];
            string[] lines = File.ReadAllLines(inputCV, Encoding.UTF8);
            foreach (var item in lines)
            {
                string CVData = item.ToString().Replace('@', ' ');
                CVList.Add(CVData);

            }
            foreach(var item in CVList)
            {
                string[] cvData = item.Split(',');
                switch(Task)
			{
				case 1:

					HTMLDocument myDoc = new HTMLDocumentClass();
					myDoc = (HTMLDocument) axWebBrowser1.Document;

					// a quick look at the google html source reveals: 
					// <INPUT maxLength="256" size="55" name="q">
					//
                    HTMLInputElement otxtSearchBox = (HTMLInputElement)myDoc.all.item("ctl00_ContentPlaceHolder1_ctl00_txtAchternaam", 0);

                    otxtSearchBox.value = cvData[0].ToString();

                    HTMLInputElement dtxtSearchBox = (HTMLInputElement)myDoc.all.item("ctl00_ContentPlaceHolder1_ctl00_txtGeboortedatum", 0);

                     dtxtSearchBox.value = cvData[1].ToString();

					// google html source for the I'm Feeling Lucky Button:
					// <INPUT type=submit value="I'm Feeling Lucky" name=btnI>
					//
                    HTMLInputElement btnSearch = (HTMLInputElement)myDoc.all.item("ctl00_ContentPlaceHolder1_ctl00_cmdOpvragen", 0);
					btnSearch.click();
                   



					Task++;

                        // write to text file 


					break;

				case 2:

					// continuation of automated tasks...
					break;
			}
            }
            MessageBox.Show("Operation Completed...!");
			
		}
	}
}

Posted 4-Apr-17 3:39am

Mukesh Pr@sad

Updated 4-Apr-17 4:05am

Add a Solution

1 solution

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Wessel Beulink · Answer 1 · 2017-04-04T04:05:00

Use the HTMLDocument you can read all functions you need on: htmldocument msdn

You can use

mydoc.GetElementById(String)

Or

mydoc.GetElementsByTagName(String)

So you need to know a Element by Id for getting the result. If you don't know the element ide you searching for simple use the string and find/replace function in c# and apply with mydoc.Write(String). You can apply changes with

mydoc.CreateElement(String)
mydoc.Write(String)

try:

string urlAddress = "http://google.com.ssvv.nl/";
var doc = new HtmlDocument();

using (WebClient client = new WebClient())
{
    string htmlCode = client.DownloadString(urlAddress);
    doc.LoadHtml(htmlCode);
}


//do whatever you want with the doc
doc.GetElementById('youId')

Also if you want a more stable solution you need to checkout this htmlAgile project: htmlagilitypack it got more options. But to complex to just write down here, you should definitely check it out.