C # Read HTML file content and write it to notepad

C # Read HTML file content and write it to notepad

 Try 
{
 Int Totalfile = 0 ;
 //  String dirpath = @ "E: \ chfumetarnet \ bsc6810 alarm \";  
                  If ( This . Textbox1.text. Trim () = "" )
{
MessageBox. Show ( "  Enter the HTML file path!  " );
}
 Else 
{
 String Dirpath = This . Textbox1.text. Trim ();
 If (! Dirpath. substring (dirpath. Length- 1 ). Contains ( "  \\ " ))
{
Dirpath = dirpath + "  \\  " ;
}
Streamwriter SW;
Directoryinfo dirinfo = New Directoryinfo (dirpath );
Fileinfo [] files = dirinfo. getfiles ();
 String Filename = dirpath + "  Warning experience database information .txt " ;
 If (File. exists (filename ))
{
Sw = file. appendtext (filename );
}
 Else 
{
Sw = file. createtext (filename );
}
 Foreach (Fileinfo In Files)
{
 If (Fileinfo. extension. Equals ("  . Htm  " )) //  Traverse all HTM files  
 {
Totalfile = totalfile + 1 ;
Webrequest mywebrequest = webrequest. Create (dirpath + fileinfo. Name );
Webresponse mywebresponse = mywebrequest. getresponse ();
Stream mystream = mywebresponse. getresponsestream ();
Encoding encode = system. Text. encoding. getencoding ( "  Gb2312  " );
Streamreader mystreamreader = New Streamreader (mystream, encode );
 String Strhtml = mystreamreader. readtoend ();
Mywebresponse. Close ();
 String Stroutput = strhtml;
RegEx = New RegEx ( @" <[^>] +> | </[^>] +>  " ); //  Remove the regular expression marked in HTML  
                              String Tmpstr = "  <H4> ([^ <] *) </H4>  " ; //  Get the expression between <H4>  
 Match titlematch = RegEx. Match (strhtml, tmpstr, regexoptions. ignorecase | regexoptions. multiline );
String Causename = titlematch. value. tostring (); //  Including <H4> and </H4> tags  
 Causename = RegEx. Replace (causename, "  [\ N | \ r | \ t]  " , "     " ); //  Remove line breaks and Tab key characters  
 Causename = causename. Trim ();
String Cause = causename. substring ( 4 , Causename. Length- 9 ); //  Alarm reason obtained  
                              String Titlestr = "  <Title> ([^ <] *) </title>  " ;
Titlematch = RegEx. Match (strhtml, titlestr, regexoptions. ignorecase | regexoptions. multiline );
 String Titlename = titlematch. value. tostring ();
Titlename = RegEx. Replace (titlename, "  [\ N | \ r | \ t]  " , "" ); //  Remove line breaks and Tab key characters  
 Titlename = titlename. Trim ();
 String Regexstr = "  <Ul> <li> (? <Key> .*?) </Ul>  " ; // Obtain the content following <ul> <li> until the end of </ul>.  
 RegEx r = New RegEx (regexstr, regexoptions. None );
Strhtml = RegEx. Replace (strhtml, "  [\ N | \ r | \ t]  " , "" ); //  Remove line breaks and Tab key characters  
 Match MC = R. Match (strhtml );
 String Datastr = mc. Groups [ "  Key  " ]. Value;
Datastr = "  <Ul> <li>  " + Datastr + "  </Ul>  " ; //  Obtain the complete source code between <ul> </ul>.  
 Strhtml = strhtml. Replace (datastr, "" ); //  Removes the <ul> </ul> source code from line breaks and Tab keys.  
 Strhtml = strhtml. Replace (titlename, "" ); //  Remove <title> </title>  
 Strhtml = RegEx. Replace (strhtml, "     " ); //  Filter out HTML tags  
 Strhtml = strhtml. Replace ( "  & Nbsp;  " , "" ); //  Remove space characters  
                              String [] Arr = cause. Split ( '     ' );
 String Zhcause = arr [arr. Length- 1 ]; // Get the last element of the array: Alert cause  
 Sw. writeline ( "  The  " + Totalfile + "  Files:  " + Fileinfo. Name );
Sw. writeline ( "  ----- Alarm reason ------:  " );
 //  Sw. writeline (cause ); //  ALM-1 meta startup  
 Zhcause = This . Chinastring (zhcause );
Sw. writeline (zhcause ); //  Network Element startup  
 Sw. writeline ( "  ----- Processing experience ------:  " );
Sw. writeline (strhtml );
Sw. writeline ();
Sw. Flush ();

}
}
Sw. Close ();
MessageBox. Show ( "  Operation successful!  " , "  Prompt  " , Messageboxbuttons. OK, messageboxicon. information );
}
}
 Catch (Exception ee)
{
MessageBox. Show ( "  Operation failed:  " + Ee. Message );
}