UnHTM( HTM ) { ; Remove HTML formatting / Convert to ordinary text by SKAN 19-Nov-2009
Static HT,C=";" ; Forum Topic: www.autohotkey.com/forum/topic51342.html Mod: 16-Sep-2010
IfEqual,HT,, SetEnv,HT, % "ááââ´´ææàà&ååãã&au"
. "mlä&bdquo„¦¦&bull•ç縸¢¢&circˆ©©¤¤&dagger†&dagger‡°"
. "°÷÷ééêêèèððëë&euro€&fnofƒ½½¼¼¾¾>>&h"
. "ellip…ííîî¡¡ìì¿¿ïï««&ldquo“&lsaquo‹&lsquo‘<<&m"
. "acr¯&mdash—µµ·· &ndash–¬¬ññóóôô&oeligœòò&or"
. "dfªººøøõõöö¶¶&permil‰±±££"""»»&rdquo”®"
. "®&rsaquo›&rsquo’&sbquo‚&scaronš§§ ¹¹²²³³ßßþþ&tilde˜&tim"
. "es×&trade™úúûûùù¨¨üüýý¥¥ÿÿ"
$ := RegExReplace( HTM,"<[^>]+>" ) ; Remove all tags between "<" and ">"
Loop, Parse, $, &`; ; Create a list of special characters
L := "&" A_LoopField C, R .= (!(A_Index&1)) ? ( (!InStr(R,L,1)) ? L:"" ) : ""
StringTrimRight, R, R, 1
Loop, Parse, R , %C% ; Parse Special Characters
If F := InStr( HT, L := A_LoopField ) ; Lookup HT Data
StringReplace, $,$, %L%%C%, % SubStr( HT,F+StrLen(L), 1 ), All
Else If ( SubStr( L,2,1)="#" )
StringReplace, $, $, %L%%C%, % Chr(((SubStr(L,3,1)="x") ? "0" : "" ) SubStr(L,3)), All
Return RegExReplace( $, "(^\s*|\s*$)") ; Remove leading/trailing white spaces
}
/*
; Array of Special Character Entities was created with following code
Loop % 256-33 {
Transform, F, HTML, % Chr( A := A_Index+33 )
If Strlen(F) > 1 && !Instr( F, "#" )
list .= "&" SubStr(F,2, StrLen(F)-2) Chr(A )
}
StringLower, List, List
Sort, List, D& U
Clipboard := List
MsgBox, 0, % StrLen( List ), % Clipboard
*