• Status: Solved
  • Priority: Medium
  • Security: Public
  • Views: 960
  • Last Modified:

VBSCRIPT - EXTRACT EMAIL ADDRESS FROM TEXT FILE - FIX

Hi there,

Refering to the following thread:
http://www.experts-exchange.com/Programming/Languages/Visual_Basic/VB_Script/Q_26886544.html

The following email could not be extracted from that text file:

<tr>
<td width="150" valign="top">Moyen(s) de communication&nbsp;:</td>
<td>courriel (courrier ‚lectronique) : email@domain.com</td>
</tr>
</tabl


Thanks for fixing the VBS script in order to also extract these emails.

Thanks and cheers,
Rene
Option Explicit

Dim objArgs, fso, strFile, strTestString
Dim strPattern, arrAllMatches

Set objArgs = WScript.Arguments

ErrCheck objArgs.Count < 1, 1, "No argument specified."

strFile = objArgs(0)

Set fso = CreateObject("Scripting.FileSystemObject")
ErrCheck Not fso.FileExists(strFile), 1, "File supplied as argument cannot be found: '" & strFile & "'"

'# WScript.Echo "Checking file contents for email addresses: '" & strFile & "'" & vbCrlf

strPattern = "([\w-\.]+)@\w{2,}(\.\w{2,}){1,5}"

strTestString = fso.OpenTextFile(strFile, 1).ReadAll

arrAllMatches = fGetMatches(strPattern, strTestString)

If UBound(arrAllMatches) <> 0 Then
    WScript.Echo Join(arrAllMatches, vbCrlf)
Else
    WScript.Echo "-- None Found --"
End If

'# WScript.Echo vbCrlf & "End of " & WScript.ScriptName

Function fGetMatches(sPattern, sStr)
    Dim regEx, retVal, sMatch, colMatches, temp
    Set regEx = New RegExp     ' Create a regular expression.
    regEx.Pattern = sPattern   ' Set pattern.
    regEx.IgnoreCase = True   ' Set case insensitivity.
    regEx.Global = True        ' Set global applicability.

    Set colMatches = regEx.Execute(sStr)   ' Execute search.

    If colMatches.Count = 0 Then
        temp = Array("")
    Else
        '# Convert Collection to Array
        For Each sMatch In colMatches
            temp = temp & sMatch & "¶"
        Next
        temp = Left(temp, Len(temp) - 1)
        temp = Split(temp, "¶")
    End If

    fGetMatches = temp
End Function

Sub ErrCheck(blTest, iErrNum, sTxt)
    Dim sErrText
    If Not blTest Then Exit Sub
    sErrText = "Error: " & sTxt
    MsgBox sErrText, vbSystemModal + vbCritical, "Error in: " & WScript.ScriptName
    WScript.Quit iErrNum
End Sub

Open in new window

0
ReneGe
Asked:
ReneGe
  • 5
  • 2
1 Solution
 
Daz_1234Commented:
Hi Rene,

There was a bug in the script I originally wrote for you.

I have fixed it by a little bit of juggling and it should now be Ok.

I don't think that you should give any more points, since the original solution I gave you was obviously flawed (  sorry about that :o)  )

Regards,
Daz.
Option Explicit

Dim objArgs, fso, strFile, strTestString
Dim strPattern, strAllMatches

Set objArgs = WScript.Arguments

ErrCheck objArgs.Count < 1, 1, "No argument specified."

strFile = objArgs(0)

Set fso = CreateObject("Scripting.FileSystemObject")
ErrCheck Not fso.FileExists(strFile), 1, "File supplied as argument cannot be found: '" & strFile & "'"

'# WScript.Echo "Checking file contents for email addresses: '" & strFile & "'" & vbCrlf

strPattern = "([\w-\.]+)@\w{2,}(\.\w{2,}){1,5}"

strTestString = fso.OpenTextFile(strFile, 1).ReadAll

strAllMatches = fGetMatches(strPattern, strTestString)

If strAllMatches <> "" Then
    WScript.Echo strAllMatches
Else
    WScript.Echo "-- None Found --"
End If

'# WScript.Echo vbCrlf & "End of " & WScript.ScriptName

Function fGetMatches(sPattern, sStr)
    Dim regEx, retVal, sMatch, colMatches, temp
    Set regEx = New RegExp     ' Create a regular expression.
    regEx.Pattern = sPattern   ' Set pattern.
    regEx.IgnoreCase = True   ' Set case insensitivity.
    regEx.Global = True        ' Set global applicability.

    Set colMatches = regEx.Execute(sStr)   ' Execute search.

    If colMatches.Count = 0 Then
        temp = ""
    Else
        For Each sMatch In colMatches
            temp = temp & sMatch & "¶"
        Next
        temp = Left(temp, Len(temp) - 1)
        temp = Replace(temp, "¶", vbCrlf)
    End If
    fGetMatches = temp
End Function

Sub ErrCheck(blTest, iErrNum, sTxt)
    Dim sErrText
    If Not blTest Then Exit Sub
    sErrText = "Error: " & sTxt
    MsgBox sErrText, vbSystemModal + vbCritical, "Error in: " & WScript.ScriptName
    WScript.Quit iErrNum
End Sub

Open in new window

0
 
ReneGeAuthor Commented:
Don't worry, you absolutely deserve the points.

I'll try it now, and let you know how it goes.

It will pass through more than 500k files so it will take a little while, but I'll know it tonight.

Cheers,
Rene
0
 
ReneGeAuthor Commented:
Your new script worked a lot better.

It was not able to extract email from:

<td width="150" valign="top">Moyen(s) de communication&nbsp;:</td>
<td>t?l?copieur&nbsp;: 905-555-1212<br />
courriel (courrier ?lectronique)&nbsp;: test.email@domain-name.com<br />
</td>


Thanks and cheers,
Rene
0
Independent Software Vendors: We Want Your Opinion

We value your feedback.

Take our survey and automatically be enter to win anyone of the following:
Yeti Cooler, Amazon eGift Card, and Movie eGift Card!

 
Daz_1234Commented:
You are a brilliant test of my regular expressions!

Below is the same script with an amended regular expression on line 17.

Regards,
Daz.


Option Explicit

Dim objArgs, fso, strFile, strTestString
Dim strPattern, strAllMatches

Set objArgs = WScript.Arguments

ErrCheck objArgs.Count < 1, 1, "No argument specified."

strFile = objArgs(0)

Set fso = CreateObject("Scripting.FileSystemObject")
ErrCheck Not fso.FileExists(strFile), 1, "File supplied as argument cannot be found: '" & strFile & "'"

'# WScript.Echo "Checking file contents for email addresses: '" & strFile & "'" & vbCrlf

strPattern = "([\w-\.]+)@[\w-]{2,}(\.[\w-]{2,}){1,5}"

strTestString = fso.OpenTextFile(strFile, 1).ReadAll

strAllMatches = fGetMatches(strPattern, strTestString)

If strAllMatches <> "" Then
    WScript.Echo strAllMatches
Else
    WScript.Echo "-- None Found --"
End If

'# WScript.Echo vbCrlf & "End of " & WScript.ScriptName

Function fGetMatches(sPattern, sStr)
    Dim regEx, retVal, sMatch, colMatches, temp
    Set regEx = New RegExp     ' Create a regular expression.
    regEx.Pattern = sPattern   ' Set pattern.
    regEx.IgnoreCase = True   ' Set case insensitivity.
    regEx.Global = True        ' Set global applicability.

    Set colMatches = regEx.Execute(sStr)   ' Execute search.

    If colMatches.Count = 0 Then
        temp = ""
    Else
        For Each sMatch In colMatches
            temp = temp & sMatch & "¶"
        Next
        temp = Left(temp, Len(temp) - 1)
        temp = Replace(temp, "¶", vbCrlf)
    End If
    fGetMatches = temp
End Function

Sub ErrCheck(blTest, iErrNum, sTxt)
    Dim sErrText
    If Not blTest Then Exit Sub
    sErrText = "Error: " & sTxt
    MsgBox sErrText, vbSystemModal + vbCritical, "Error in: " & WScript.ScriptName
    WScript.Quit iErrNum
End Sub

Open in new window

0
 
ReneGeAuthor Commented:
Thanks Daz, testing it now!

Cheers,
Rene
0
 
ReneGeAuthor Commented:
Hey Daz,

It's working like a charm.

I need to add a function to it, so I'll create a new thread and let you know.

Thanks and cheers,
Rene
0
 
ReneGeAuthor Commented:
0

Featured Post

Technology Partners: We Want Your Opinion!

We value your feedback.

Take our survey and automatically be enter to win anyone of the following:
Yeti Cooler, Amazon eGift Card, and Movie eGift Card!

  • 5
  • 2
Tackle projects and never again get stuck behind a technical roadblock.
Join Now