XML size to follow?

[youtuber]

how to follow XML size change?

my example

expandcollapse popup

#include <ButtonConstants.au3>
#include <EditConstants.au3>
#include <GUIConstantsEx.au3>
#include <WindowsConstants.au3>
#include <MsgBoxConstants.au3>
#include <File.au3>
#include <Array.au3>
#include <Inet.au3>
#include <String.au3>
$aTime = 5
$Form1 = GUICreate("Form1", 615, 322, 192, 124)
$Edit1 = GUICtrlCreateEdit("", 24, 40, 393, 225)
GUICtrlSetData(-1, FileRead(@ScriptDir & "\sitelist.txt"))
$afirstdown = GUICtrlCreateButton("First down", 128, 280, 75, 25)
$aStart = GUICtrlCreateButton("Xml Test", 216, 282, 75, 25)
GUISetState(@SW_SHOW)
FileInstall("alarm.mp3", @TempDir & "\alarm.mp3")
While 1
    $nMsg = GUIGetMsg()
    Switch $nMsg
        Case $GUI_EVENT_CLOSE
            Exit
        Case $afirstdown
            _firstdownloaded()
        Case $aStart
            _xmlread()

    EndSwitch
WEnd

Func _xmlread()
    Local $sitelisturl = StringSplit(StringStripCR(GUICtrlRead($Edit1)), @LF)
    While 1
        For $i = 1 To UBound($sitelisturl) - 1
            $sitenamestr = StringRegExp($sitelisturl[$i], 'https?://(?:www.)?([^.]+)', 3)
            $sitenames = $sitenamestr[0]
            ConsoleWrite('@@ Debug(' & @ScriptLineNumber & ') : $sitenames = ' & $sitenames & @CRLF & '>Error code: ' & @error & @CRLF)
            $firstdown = @ScriptDir & '\firstdownloaded\' & $sitenames & '.xml'
            $downloadtemp = @ScriptDir & '\sitefiles\' & $sitenames & '.xml'
            If FileExists(@ScriptDir & "\sitefiles" & $downloadtemp) Then
                $inetgetsites = InetGet($sitelisturl[$i], $downloadtemp, 1, 1)
            Else
                DirCreate(@ScriptDir & "\" & "sitefiles")
                $inetgetsites = InetGet($sitelisturl[$i], $downloadtemp, 1, 1)
                ;ConsoleWrite('@@ Debug(' & @ScriptLineNumber & ') : $sitelisturl[$i] = ' & $sitelisturl[$i] & @CRLF & '>Error code: ' & @error & @CRLF)
            EndIf
            Sleep($aTime * 1000)
            $old = FileGetSize($firstdown)
            $anew = FileGetSize($downloadtemp)
            If $anew <> $old Then
                $aUrlread = BinaryToString(InetRead($sitelisturl[$i], 0), 4)
                $aUrlextract = _StringBetween($aUrlread, '<loc>', '</loc>')
                ConsoleWrite('@@ Debug(' & @ScriptLineNumber & ') : $aUrlextract[0] = ' & $aUrlextract[0] & @CRLF & '>Error code: ' & @error & @CRLF)
                FileOpen(@ScriptDir & '\URLs.txt', 1)
                FileWrite(@ScriptDir & '\URLs.txt', $aUrlextract[0] & @CRLF)
                FileClose(@ScriptDir & '\URLs.txt')
                SoundPlay(@TempDir & "\alarm.mp3", 10)
                ClipPut($aUrlextract[0])
                TrayTip($sitenames, " An article published URL Copied " & @CRLF & $aUrlextract[0], 30, 4)
                Sleep(3000)
                If MsgBox(36, "Did you get to go to a new article? " & $sitenames, $aUrlextract[0], 10) = 6 Then ShellExecute($aUrlextract[0])
            EndIf
        Next
    WEnd
EndFunc

Func _firstdownloaded()
    Local $sitelisturl = StringSplit(StringStripCR(GUICtrlRead($Edit1)), @LF)
        For $i = 1 To UBound($sitelisturl) - 1
            $sitenamestr = StringRegExp($sitelisturl[$i], 'https?://(?:www.)?([^.]+)', 3)
            $sitenames = $sitenamestr[0]
            ConsoleWrite('@@ Debug(' & @ScriptLineNumber & ') : $sitenames = ' & $sitenames & @CRLF & '>Error code: ' & @error & @CRLF)
            $downloadtemp = @ScriptDir & '\firstdownloaded\' & $sitenames & '.xml'
            If FileExists(@ScriptDir & "\firstdownloaded" & $downloadtemp) Then
                $inetgetsites = InetGet($sitelisturl[$i], $downloadtemp, 1, 1)
            Else
                DirCreate(@ScriptDir & "\" & "firstdownloaded")
                $inetgetsites = InetGet($sitelisturl[$i], $downloadtemp, 1, 1)
            EndIf

        Next
EndFunc

 

[genius257]

I'm sorry could you explain your problem in more detail?

[mikell]

What is the trouble with the FileGetSize you already use ?

[UEZ]

His question is how to detect changes in the XML files when the file size doesn't change.

This is not easy to solve because you want only changes detected on some URLs not the full content.

 

I would suggest to read out the text between <loc>' * '</loc>' and compare it with previous versions. I showed you how to save filesizes in an array. You can extend it by the content and compare it instead.

[mLipok]

1. Tidy both XML (old and new)
2. split lines to Arrays
3. check Arrays OLD<> NEW

 

[mikell]

UEZ,
I understand
A nice way IMHO could be to check  StringStripWS(FileRead("1.xml"), $STR_STRIPALL)  against the same for 2.xml
This should detect any change 

[youtuber]

@mLipok @mikell @UEZ

sometimes OK

sometimes confuses the difference

sitelist.txt

https://wmtrseo.wordpress.com/sitemap.xml
https://autoitscriptblog.wordpress.com/sitemap.xml
http://autoitscripttr.blogspot.com.tr/sitemap.xml
http://youtubertr.com/sitemap.xml
https://autoittr.wordpress.com/sitemap.xml

 

expandcollapse popup

#include <ButtonConstants.au3>
#include <EditConstants.au3>
#include <GUIConstantsEx.au3>
#include <WindowsConstants.au3>
#include <MsgBoxConstants.au3>
#include <File.au3>
#include <Array.au3>
#include <Inet.au3>
#include <String.au3>
$aTime = 5
$Form1 = GUICreate("Form1", 615, 322, 192, 124)
$Edit1 = GUICtrlCreateEdit("", 24, 40, 393, 225)
GUICtrlSetData(-1, FileRead(@ScriptDir & "\sitelist.txt"))
$afirstdown = GUICtrlCreateButton("First down", 128, 280, 75, 25)
$aStart = GUICtrlCreateButton("Xml Test", 216, 282, 75, 25)
GUISetState(@SW_SHOW)
FileInstall("alarm.mp3", @TempDir & "\alarm.mp3")
While 1
    $nMsg = GUIGetMsg()
    Switch $nMsg
        Case $GUI_EVENT_CLOSE
            Exit
         Case $afirstdown
            _firstdownloaded()
        Case $aStart
            _xmlread()
    EndSwitch
WEnd

Func _xmlread()

    Local $sitelisturl = StringSplit(StringStripCR(GUICtrlRead($Edit1)), @LF)
    Local $aFileInfo[UBound($sitelisturl) + 1][2]
    While 1
        For $i = 1 To UBound($sitelisturl) - 1
            $sitenamestr = StringRegExp($sitelisturl[$i], 'https?://(?:www.)?([^.]+)', 3)
            $sitenames = $sitenamestr[0]
            ConsoleWrite('@@ Debug(' & @ScriptLineNumber & ') : $sitenames = ' & $sitenames & @CRLF & '>Error code: ' & @error & @CRLF)

            $downloadtemp = @ScriptDir & '\sitefiles\' & $sitenames & '.xml'
            $aFileInfo[$i][1] = StringRegExp(FileRead($downloadtemp), "\<loc\>(.+?)<\/loc\>", 3)

            If FileExists(@ScriptDir & "\sitefiles" & $downloadtemp) Then
                $inetgetsites = InetGet($sitelisturl[$i], $downloadtemp, 1, 1)

            Else
                DirCreate(@ScriptDir & "\" & "sitefiles")
                $inetgetsites = InetGet($sitelisturl[$i], $downloadtemp, 1, 1)
                ;ConsoleWrite('@@ Debug(' & @ScriptLineNumber & ') : $sitelisturl[$i] = ' & $sitelisturl[$i] & @CRLF & '>Error code: ' & @error & @CRLF)
            EndIf

            Sleep($aTime * 1000)
            $anew = FileGetSize($downloadtemp)
            ;ConsoleWrite("Chk: " & Chk($aFileInfo[$i][1], $downloadtemp) & @CRLF)
            If $anew <> $aFileInfo[$i][0] Or Not Chk($aFileInfo[$i][1], $downloadtemp) Then
                $aFileInfo[$i][0] = $anew
                $aUrlread = BinaryToString(InetRead($sitelisturl[$i], 0), 4)
                $aUrlextract = _StringBetween($aUrlread, '<loc>','</loc>')
                ConsoleWrite('@@ Debug(' & @ScriptLineNumber & ') : $aUrlextract[0] = ' & $aUrlextract[0] & @CRLF & '>Error code: ' & @error & @CRLF)
                FileOpen(@ScriptDir & '\URLs.txt', 1)
                FileWrite(@ScriptDir & '\URLs.txt', $aUrlextract[0] & @CRLF)
                FileClose(@ScriptDir & '\URLs.txt')
                SoundPlay(@TempDir & "\alarm.mp3", 10)
                ClipPut($aUrlextract[0])
                TrayTip($sitenames, " An article published URL Copied " & @CRLF & $aUrlextract[0], 30, 4)
                Sleep(3000)
                If MsgBox(36, "Did you get to go to a new article? " & $sitenames, $aUrlextract[0], 10) = 6 Then ShellExecute($aUrlextract[0])
            EndIf
        Next
    WEnd
EndFunc

Func Chk($array, $path)
    Local $aFile = StringRegExp(FileRead($path), "\<loc\>(.+?)<\/loc\>", 3), $i
    If UBound($array) <> UBound($aFile) Then Return 0
    For $i = 0 To UBound($array) - 1
        If $array[$i] <> $aFile[$i] Then Return 0
    Next
    Return 1
EndFunc

Func _firstdownloaded()
    Local $sitelisturl = StringSplit(StringStripCR(GUICtrlRead($Edit1)), @LF)
        For $i = 1 To UBound($sitelisturl) - 1
            $sitenamestr = StringRegExp($sitelisturl[$i], 'https?://(?:www.)?([^.]+)', 3)
            $sitenames = $sitenamestr[0]
            ConsoleWrite('@@ Debug(' & @ScriptLineNumber & ') : $sitenames = ' & $sitenames & @CRLF & '>Error code: ' & @error & @CRLF)
            $downloadtemp = @ScriptDir & '\sitefiles\' & $sitenames & '.xml'
            If FileExists(@ScriptDir & "\sitefiles" & $downloadtemp) Then
                $inetgetsites = InetGet($sitelisturl[$i], $downloadtemp, 1, 1)
            Else
                DirCreate(@ScriptDir & "\" & "sitefiles")
                $inetgetsites = InetGet($sitelisturl[$i], $downloadtemp, 1, 1)
            EndIf

        Next
EndFunc

 

Edited October 8, 2016 by youtuber