Use regular expressions to convert html webpage data into Web Services

This question is very simple, the Bank of China has a page to check the exchange rate of the day (http://www.bank-of-china.com/info/qpindex.shtml), but is the traditional Html format, and it does not provide Xml format or WebService query. If you want other information systems to read the data at any time, it is convenient that the Bank of China provides a WebService Interface for you to call. This is also a typical secure WebService application. Unfortunately, the Bank of China did not do this. Can we do it ourselves? Of course, as long as you use a program to analyze its html webpage, you can easily read the data. Text Analysis, of course, depends on our "Regular Expression" (haha, in fact, this is the real purpose of writing this program-apply Regular expressions .)

The BOC page is similar:

Date:Valid Period: 2004/09/30 to 2004/10/07

Currency name	Current remittance purchase price	Cash purchase price	Sell bid	Base Price
Pound	1488.1700	1453.1500	1492.6400
Hong Kong dollar	105.9700	105.3300	106.2900	106.1100
USD	826.4200	821.4500	828.9000	827.6600
Swiss franc	655.9300	641.1400	659.2200
Singapore dollar	488.7600	477.2600	490.2300
Swedish krona	112.4900	109.8400	112.8300
Danish krona	136.5900	133.3700	137.0000
Norwegian Krona	121.9500	119.0800	122.3100
Yen	7.4344	7.3785	7.4717	7.4519
Canadian dollar	650.8000	635.4800	652.7600
Australian dollar	591.9900	578.6400	594.9600
Euro	1019.6400	1010.9600	1022.7000	1019.7000
Macao dollar	103.2200	102.6000	103.5300
Philippine peso	14.6700	14.3300	14.7200
	19.9000	19.4300	19.9600
New Zealand dollar	553.7000		555.3600

After the code analysis, a regular expression is provided. Of course, this expression is not perfect yet, but it is still correct for the exchange rate page of the relatively fixed bank of china.

@ "<Tr bgcolor = '#/w +'> <td height = '20'> (? <Currency>. *) </td>/s * "+
@ "<Td height = '20'> <p align = 'right'> (? <Bankbuytt>/d *.? /D *) (& nbsp) + .? </Td>/s * "+
@ "<Td height = '20'> <p align = 'right'> (? <Buynotes>/d *.? /D *) (& nbsp) + .? </Td>/s * "+
@ "<Td height = '20'> <p align = 'right'> (? <Strong>/d *.? /D *) (& nbsp) + .? </Td>/s * "+
@ "<Td height = '20'> <p align = 'right'> (? <Base>/d *.? /D *) (& nbsp) + .? </Td>/s *"

Then it is very easy to filter. I always thought that code is the best explanation, especially for elegant languages, because I will not talk much about it, and the code is waiting for me.

This is the code for ForeignExchange. asmx on the created WebService page:

Using System;
Using System. Collections;
Using System. ComponentModel;
Using System. Data;
Using System. Diagnostics;
Using System. Web;
Using System. Net;
Using System. Web. Services;
Using System. Xml;
Using System. Text;
Using System. Text. RegularExpressions;
Using System. IO;

Namespace ChinaBank
{
/// <Summary>
/// Summary description for ForeignExchange.
/// </Summary>
[WebService (Namespace = "http://dancefires.com/ChinaBank/")]
Public class foreignexchange: system. Web. Services. WebService
{
Public foreignexchange ()
{
// Codegen: This call is required by the ASP. NET web services designer
Initializecomponent ();
}

# Region component designer generated code

// Required by the Web Services designer
Private IContainer components = null;

/// <Summary>
/// Required method for Designer support-do not modify
/// The contents of this method with the code editor.
/// </Summary>
Private void InitializeComponent ()
{
}

/// <Summary>
/// Clean up any resources being used.
/// </Summary>
Protected override void Dispose (bool disposing)
{
If (disposing & components! = Null)
{
Components. Dispose ();
}
Base. Dispose (disposing );
}

# Endregion

[Webmethod]
Public xmldatadocument getforeignexchangerates ()
{
Return getxmldoc ();
}
[Webmethod]
Public dataset getforeignexchangeratesdataset ()
{
Return getXmlDoc (). DataSet;
}
[WebMethod]
Public string GetBankPage ()
{
Return getWebContent ("http://www.bank-of-china.com/info/whjrpj.html ");
}
// Private methods
Private string getWebContent (string url)
{
Using (WebClient client = new WebClient ())
{
Byte [] buffer = client. downloaddata (URL );
String STR = encoding. getencoding ("gb2312"). getstring (buffer, 0, buffer. Length );
Return STR;
}
}
Private xmldatadocument getxmldoc ()
{
String webcontent = getWebContent ("http://www.bank-of-china.com/info/whjrpj.html ");

// Prepair for DataSet
DataSet ds = new DataSet ("Exchange ");
DataTable dt = new DataTable ("ForeignExchange ");
Ds. Tables. Add (dt );
Dt. Columns. Add ("Currency", typeof (string ));
Dt. Columns. Add ("BankBuyTT", typeof (double ));
Dt. Columns. Add ("BankBuyNotes", typeof (double ));
Dt. Columns. Add ("banknames", typeof (double ));
Dt. Columns. Add ("Baseline", typeof (double ));
XmlDataDocument xmldoc = new XmlDataDocument (ds );

Regex expr = new Regex (
@ "<Tr bgcolor = '#/w +'> <td height = '20'> (? <Currency>. *) </td>/s * "+
@ "<Td height = '20'> <p align = 'right'> (? <Bankbuytt>/d *.? /D *) (& nbsp) + .? </Td>/s * "+
@ "<Td height = '20'> <p align = 'right'> (? <Buynotes>/d *.? /D *) (& nbsp) + .? </Td>/s * "+
@ "<Td height = '20'> <p align = 'right'> (? <Strong>/d *.? /D *) (& nbsp) + .? </Td>/s * "+
@ "<Td height = '20'> <p align = 'right'> (? <Base>/d *.? /D *) (& nbsp) + .? </Td>/s *"
, RegexOptions. Compiled );
For (Match m = expr. Match (webcontent); m. Success; m = m. NextMatch ())
{
String key;
DataRow row = dt. NewRow ();
Row ["Currency"] = m. Groups ["currency"];
Key = m. Groups ["bankbuytt"]. ToString ();
Row ["bankbuytt"] = key. length> 0? Convert. todouble (key)/100: 0;
Key = M. Groups ["buynotes"]. tostring ();
Row ["bankbuynotes"] = key. length> 0? Convert. todouble (key)/100: 0;
Key = M. Groups ["success"]. tostring ();
Row ["bankdetail"] = key. length> 0? Convert. todouble (key)/100: 0;
Key = M. Groups ["base"]. tostring ();
Row ["Baseline"] = key. Length> 0? Convert. ToDouble (key)/100: 0;
Dt. Rows. Add (row );
}
Return xmldoc;
}
}
}

The client is also very easy, as long as the corresponding WebService Proxy is generated using wsdl, it can be called directly, because I asked the Server to return DataSet, therefore, the client can directly use the DataGrid to display the DataSet, which is very Easy. On this issue, the client has no technical key points.

Using System;
Using System. Threading;
Using System. Drawing;
Using System. Collections;
Using System. ComponentModel;
Using System. Windows. Forms;

Namespace BankDataClient
{
/// <Summary>
/// Summary description for frmMainBankRates.
/// </Summary>
Public class frmMainBankRates: System. Windows. Forms. Form
{
Private System. Windows. Forms. DataGrid dataGrid1;
Private System. Windows. Forms. Button btnConnect;
Private System. Data. DataSet ds;
Private BankDataClient.com. dancefires. [url] www. ForeignExchange [/url] proxy = new BankDataClient.com. dancefires. www. ForeignExchange ();
Private System. Windows. Forms. TextBox txtUrl;
/// <Summary>
/// Required designer variable.
/// </Summary>
Private System. ComponentModel. Container components = null;

Public frmMainBankRates ()
{
//
// Required for Windows Form Designer support
//
InitializeComponent ();
Try
{
TxtUrl. Text = System. Configuration. ConfigurationSettings. deleettings ["url"];
Proxy. Url = txtUrl. Text;
}
Catch (Exception)
{
Proxy. Url = "http://www.dancefires.com/ChinaBank/ForeignExchange.asmx ";
Txturl. Text = proxy. url;
}
}

/// <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 ()
{
This. Maid = new System. Windows. Forms. DataGrid ();
This. ds = new System. Data. DataSet ();
This. btnConnect = new System. Windows. Forms. Button ();
This.txt Url = new System. Windows. Forms. TextBox ();
(System. ComponentModel. ISupportInitialize) (this. dataGrid1). BeginInit ();
(System. ComponentModel. ISupportInitialize) (this. ds). BeginInit ();
This. SuspendLayout ();
//
// DataGrid1
//
This. dataGrid1.DataMember = "";
This. dataGrid1.DataSource = this. ds;
This. dataGrid1.HeaderForeColor = System. Drawing. SystemColors. ControlText;
This. Maid = new System. Drawing. Point (32, 48 );
This. Maid = "maid ";
This. dataGrid1.Size = new System. Drawing. Size (480,256 );
This. Maid = 0;
//
// Ds
//
This. ds. DataSetName = "Exchange ";
This. ds. Locale = new System. Globalization. CultureInfo ("zh-CN ");
//
// BtnConnect
//
This. btnConnect. Location = new System. Drawing. Point (432, 16 );
This. btnconnect. Name = "btnconnect ";
This. btnconnect. tabindex = 1;
This. btnconnect. Text = "Connect ";
This. btnconnect. Click + = new system. eventhandler (this. btnconnect_click );
//
// Txturl
//
This.txt URL. Location = new system. Drawing. Point (32, 16 );
This.txt Url. Name = "txtUrl ";
This.txt Url. Size = new System. Drawing. Size (384, 20 );
This.txt Url. TabIndex = 2;
This.txt Url. Text = "";
//
// FrmMainBankRates
//
This. AutoScaleBaseSize = new System. Drawing. Size (5, 13 );
This. ClientSize = new System. Drawing. Size (544,318 );
This.Controls.Add(this.txt Url );
This. Controls. Add (this. btnConnect );
This. Controls. Add (this. dataGrid1 );
This. Name = "frmMainBankRates ";
This. Text = "Foreign Exchange Rates of Bank of China ";
(System. ComponentModel. ISupportInitialize) (this. dataGrid1). EndInit ();
(System. ComponentModel. ISupportInitialize) (this. ds). EndInit ();
This. ResumeLayout (false );

}
# Endregion

Private void btnConnect_Click (object sender, System. EventArgs e)
{
UpdateDataGrid ();
}
Private void UpdateDataGrid ()
{
Try
{
Btnconnect. Enabled = false;
Txturl. readonly = true;
Proxy. url = txturl. text;
DS = proxy. getforeignexchangeratesdataset ();
Datagrid1.setdatabinding (DS, "foreignexchange ");
DataGrid1.Update ();
}
Catch (Exception err)
{
MessageBox. Show (err. Message );
}
Finally
{
TxtUrl. ReadOnly = false;
Btnconnect. Enabled = true;
}
}
[Stathread]
Static void main (string [] ARGs)
{
Application. Run (New frmmainbankrates ());
}
}
}

With this example, you can learn about the most basic XML, WebService, regular expression, dataset, and DataGrid.

All software code and screenshots can be obtained from the following connection:

Http://www.dancefires.com/ChinaBank/