gibbo1715
02-20-2005, 02:51 PM
The piece of code below came from Dr J and im still impressed by it, It searches word docs for a key word and then lists the results in the spreadsheet
Now im really asking but was wondering is it possible to do something similar with pdf acrobat files
Being able to open pdf files from excel would be a start
Anyway thought id ask and get you thinking cause this is over my head at the moment
Thanks
Gibbo
Option Compare Text
Option Explicit
Private Const BIF_RETURNONLYFSDIRS As Long = &H1
Private Const BIF_DONTGOBELOWDOMAIN As Long = &H2
Private Const BIF_RETURNFSANCESTORS As Long = &H8
Private Const BIF_BROWSEFORCOMPUTER As Long = &H1000
Private Const BIF_BROWSEFORPRINTER As Long = &H2000
Private Const BIF_BROWSEINCLUDEFILES As Long = &H4000
Private Const MAX_PATH As Long = 260
Type BrowseInfo
hOwner As Long
pidlRoot As Long
pszDisplayName As String
lpszINSTRUCTIONS As String
ulFlags As Long
lpfn As Long
lParam As Long
iImage As Long
End Type
Type SHFILEOPSTRUCT
hwnd As Long
wFunc As Long
pFrom As String
pTo As String
fFlags As Integer
fAnyOperationsAborted As Boolean
hNameMappings As Long
lpszProgressTitle As String
End Type
Declare Function SHGetPathFromIDListA Lib "shell32.dll" ( _
ByVal pidl As Long, _
ByVal pszBuffer As String) As Long
Declare Function SHBrowseForFolderA Lib "shell32.dll" ( _
lpBrowseInfo As BrowseInfo) As Long
Function BrowseFolder(Optional Caption As String = "") As String
Dim BrowseInfo As BrowseInfo
Dim FolderName As String
Dim ID As Long
Dim Res As Long
With BrowseInfo
.hOwner = 0
.pidlRoot = 0
.pszDisplayName = String$(MAX_PATH, vbNullChar)
.lpszINSTRUCTIONS = Caption
.ulFlags = BIF_RETURNONLYFSDIRS
.lpfn = 0
End With
FolderName = String$(MAX_PATH, vbNullChar)
ID = SHBrowseForFolderA(BrowseInfo)
If ID Then
Res = SHGetPathFromIDListA(ID, FolderName)
If Res Then
BrowseFolder = Left$(FolderName, InStr(FolderName, _
vbNullChar) - 1)
End If
End If
End Function
Sub ListText()
Dim AppWrd As New Word.Application
Dim Doc As Word.Document
Dim Search As String
Dim Prompt As String
Dim Title As String
Dim PageX() As Long
Dim LineX() As Long
Dim FPath() As String
Dim FName() As String
Dim Row As Long
Dim Counter As Long
Dim Pos As Double
Dim Path As String
Dim FileName As String
Dim MyResponse As VbMsgBoxResult
Dim StartLine As Long
Dim StartPage As Long
Dim WS As Worksheet
WordBasic.DisableAutoMacros True
'*** Get folder from user ***
Prompt = "Select the folder with the files that you want to search through."
Title = "Folder Selection"
MsgBox Prompt, vbInformation, Title
Path = BrowseFolder("Select A Folder")
If Path = "" Then
Prompt = "You didn't select a folder. The procedure has been canceled."
Title = "Procedure Canceled"
MsgBox Prompt, vbCritical, Title
GoTo Canceled:
End If
'*** This code works with XP only and is also used to pick a folder ***
'Application.FileDialog(msoFileDialogFolderPicker) .Show
'Path = CurDir
Prompt = "What do you want to search for?"
Title = "Search Criteria"
Search = InputBox(Prompt, Title)
If Search = "" Then
GoTo Canceled
End If
'*** Confirm the procedure before continuing ***
Prompt = "Are you sure that you want to search all the files in the folder:" & _
vbCrLf & Path & " for " & """" & Search & """" & "?"
Title = "Confirm Procedure"
MyResponse = MsgBox(Prompt, vbQuestion + vbYesNo, Title)
If MyResponse = vbNo Then
GoTo Canceled:
End If
Application.DisplayAlerts = False
Application.ScreenUpdating = False
'*** Loop through all Word documents and search each of
'***them for the specified criteria***
FileName = Dir(Path & "\*.doc", vbNormal)
Do Until FileName = ""
On Error Resume Next
Set Doc = AppWrd.Documents.Open(Path & "\" & FileName, ReadOnly:=True, _
PasswordDocument:="DRJWasHere")
If Err <> 0 Then
GoTo NextLoop:
End If
On Error GoTo 0
With Doc
AppWrd.Selection.Find.ClearFormatting
With AppWrd.Selection.Find
.Text = Search
.Replacement.Text = ""
.Forward = True
.Wrap = wdFindContinue
.Format = False
.MatchCase = False
.MatchWholeWord = False
.MatchWildcards = False
.MatchSoundsLike = False
.MatchAllWordForms = False
End With
AppWrd.Selection.Find.Execute
If AppWrd.Selection.Range.Text <> Search Then
GoTo NextLoop:
End If
Pos = _
AppWrd.Selection.Range.Information( _
wdHorizontalPositionRelativeToPage)
Counter = Counter + 1
ReDim Preserve LineX(1 To Counter)
ReDim Preserve PageX(1 To Counter)
ReDim Preserve FPath(1 To Counter)
ReDim Preserve FName(1 To Counter)
LineX(Counter) = AppWrd.Selection.Range.Information( _
wdFirstCharacterLineNumber)
PageX(Counter) = AppWrd.Selection.Range.Information( _
wdActiveEndPageNumber)
FPath(Counter) = Doc.Path
FName(Counter) = Doc.Name
StartLine = AppWrd.Selection.Range.Information( _
wdFirstCharacterLineNumber)
StartPage = AppWrd.Selection.Range.Information( _
wdActiveEndPageNumber)
AppWrd.Selection.Find.Execute
Do While Pos <> AppWrd.Selection.Range.Information( _
wdHorizontalPositionRelativeToPage) Or _
StartLine <> AppWrd.Selection.Range.Information( _
wdFirstCharacterLineNumber) Or _
StartPage <> AppWrd.Selection.Range.Information( _
wdActiveEndPageNumber)
Counter = Counter + 1
ReDim Preserve LineX(1 To Counter)
ReDim Preserve PageX(1 To Counter)
ReDim Preserve FPath(1 To Counter)
ReDim Preserve FName(1 To Counter)
If LineX(Counter - 1) = _
AppWrd.Selection.Range.Information( _
wdFirstCharacterLineNumber) And _
PageX(Counter - 1) = _
AppWrd.Selection.Range.Information( _
wdActiveEndPageNumber) And _
Pos = _
AppWrd.Selection.Range.Information( _
wdHorizontalPositionRelativeToPage) Then
Exit Do
Else
LineX(Counter) = _
AppWrd.Selection.Range.Information( _
wdFirstCharacterLineNumber)
PageX(Counter) = _
AppWrd.Selection.Range.Information( _
wdActiveEndPageNumber)
FPath(Counter) = Doc.Path
FName(Counter) = Doc.Name
Pos = _
AppWrd.Selection.Range.Information( _
wdHorizontalPositionRelativeToPage)
AppWrd.Selection.Find.Execute
End If
Loop
NextLoop:
End With
Doc.Close False
Set Doc = Nothing
On Error GoTo 0
FileName = Dir()
Loop
If Counter = 0 Then
MsgBox Search & " was not found.", vbInformation, "Zero Results For Search"
GoTo Canceled:
End If
Set WS = ThisWorkbook.Sheets("Sheet1")
With WS
.Range("A1").Value = "Occurrences of the word " & """" & Search & """"
.Range("A1:C1").Merge
.Range("A2").Value = "Document Path"
.Range("B2").Value = "Page Number"
.Range("C2").Value = "Line Number"
.Range("A1:C2").Font.Bold = True
.Range("A1:C2").HorizontalAlignment = xlCenter
For Row = UBound(LineX) To 1 Step -1
If PageX(Row) = 0 Or LineX(Row) = 0 Then
Else
.Range("B" & Row + 2).Value = PageX(Row)
.Range("C" & Row + 2).Value = LineX(Row)
.Hyperlinks.Add Anchor:=.Range("A" & Row + 2), _
Address:=FPath(Row) & "\" & FName(Row), TextToDisplay:=FName(Row)
End If
Next Row
.Range("A:C").EntireColumn.AutoFit
End With
Canceled:
AppWrd.Quit
Set Doc = Nothing
Set AppWrd = Nothing
WordBasic.DisableAutoMacros False
Application.DisplayAlerts = True
Application.ScreenUpdating = True
End Sub
Now im really asking but was wondering is it possible to do something similar with pdf acrobat files
Being able to open pdf files from excel would be a start
Anyway thought id ask and get you thinking cause this is over my head at the moment
Thanks
Gibbo
Option Compare Text
Option Explicit
Private Const BIF_RETURNONLYFSDIRS As Long = &H1
Private Const BIF_DONTGOBELOWDOMAIN As Long = &H2
Private Const BIF_RETURNFSANCESTORS As Long = &H8
Private Const BIF_BROWSEFORCOMPUTER As Long = &H1000
Private Const BIF_BROWSEFORPRINTER As Long = &H2000
Private Const BIF_BROWSEINCLUDEFILES As Long = &H4000
Private Const MAX_PATH As Long = 260
Type BrowseInfo
hOwner As Long
pidlRoot As Long
pszDisplayName As String
lpszINSTRUCTIONS As String
ulFlags As Long
lpfn As Long
lParam As Long
iImage As Long
End Type
Type SHFILEOPSTRUCT
hwnd As Long
wFunc As Long
pFrom As String
pTo As String
fFlags As Integer
fAnyOperationsAborted As Boolean
hNameMappings As Long
lpszProgressTitle As String
End Type
Declare Function SHGetPathFromIDListA Lib "shell32.dll" ( _
ByVal pidl As Long, _
ByVal pszBuffer As String) As Long
Declare Function SHBrowseForFolderA Lib "shell32.dll" ( _
lpBrowseInfo As BrowseInfo) As Long
Function BrowseFolder(Optional Caption As String = "") As String
Dim BrowseInfo As BrowseInfo
Dim FolderName As String
Dim ID As Long
Dim Res As Long
With BrowseInfo
.hOwner = 0
.pidlRoot = 0
.pszDisplayName = String$(MAX_PATH, vbNullChar)
.lpszINSTRUCTIONS = Caption
.ulFlags = BIF_RETURNONLYFSDIRS
.lpfn = 0
End With
FolderName = String$(MAX_PATH, vbNullChar)
ID = SHBrowseForFolderA(BrowseInfo)
If ID Then
Res = SHGetPathFromIDListA(ID, FolderName)
If Res Then
BrowseFolder = Left$(FolderName, InStr(FolderName, _
vbNullChar) - 1)
End If
End If
End Function
Sub ListText()
Dim AppWrd As New Word.Application
Dim Doc As Word.Document
Dim Search As String
Dim Prompt As String
Dim Title As String
Dim PageX() As Long
Dim LineX() As Long
Dim FPath() As String
Dim FName() As String
Dim Row As Long
Dim Counter As Long
Dim Pos As Double
Dim Path As String
Dim FileName As String
Dim MyResponse As VbMsgBoxResult
Dim StartLine As Long
Dim StartPage As Long
Dim WS As Worksheet
WordBasic.DisableAutoMacros True
'*** Get folder from user ***
Prompt = "Select the folder with the files that you want to search through."
Title = "Folder Selection"
MsgBox Prompt, vbInformation, Title
Path = BrowseFolder("Select A Folder")
If Path = "" Then
Prompt = "You didn't select a folder. The procedure has been canceled."
Title = "Procedure Canceled"
MsgBox Prompt, vbCritical, Title
GoTo Canceled:
End If
'*** This code works with XP only and is also used to pick a folder ***
'Application.FileDialog(msoFileDialogFolderPicker) .Show
'Path = CurDir
Prompt = "What do you want to search for?"
Title = "Search Criteria"
Search = InputBox(Prompt, Title)
If Search = "" Then
GoTo Canceled
End If
'*** Confirm the procedure before continuing ***
Prompt = "Are you sure that you want to search all the files in the folder:" & _
vbCrLf & Path & " for " & """" & Search & """" & "?"
Title = "Confirm Procedure"
MyResponse = MsgBox(Prompt, vbQuestion + vbYesNo, Title)
If MyResponse = vbNo Then
GoTo Canceled:
End If
Application.DisplayAlerts = False
Application.ScreenUpdating = False
'*** Loop through all Word documents and search each of
'***them for the specified criteria***
FileName = Dir(Path & "\*.doc", vbNormal)
Do Until FileName = ""
On Error Resume Next
Set Doc = AppWrd.Documents.Open(Path & "\" & FileName, ReadOnly:=True, _
PasswordDocument:="DRJWasHere")
If Err <> 0 Then
GoTo NextLoop:
End If
On Error GoTo 0
With Doc
AppWrd.Selection.Find.ClearFormatting
With AppWrd.Selection.Find
.Text = Search
.Replacement.Text = ""
.Forward = True
.Wrap = wdFindContinue
.Format = False
.MatchCase = False
.MatchWholeWord = False
.MatchWildcards = False
.MatchSoundsLike = False
.MatchAllWordForms = False
End With
AppWrd.Selection.Find.Execute
If AppWrd.Selection.Range.Text <> Search Then
GoTo NextLoop:
End If
Pos = _
AppWrd.Selection.Range.Information( _
wdHorizontalPositionRelativeToPage)
Counter = Counter + 1
ReDim Preserve LineX(1 To Counter)
ReDim Preserve PageX(1 To Counter)
ReDim Preserve FPath(1 To Counter)
ReDim Preserve FName(1 To Counter)
LineX(Counter) = AppWrd.Selection.Range.Information( _
wdFirstCharacterLineNumber)
PageX(Counter) = AppWrd.Selection.Range.Information( _
wdActiveEndPageNumber)
FPath(Counter) = Doc.Path
FName(Counter) = Doc.Name
StartLine = AppWrd.Selection.Range.Information( _
wdFirstCharacterLineNumber)
StartPage = AppWrd.Selection.Range.Information( _
wdActiveEndPageNumber)
AppWrd.Selection.Find.Execute
Do While Pos <> AppWrd.Selection.Range.Information( _
wdHorizontalPositionRelativeToPage) Or _
StartLine <> AppWrd.Selection.Range.Information( _
wdFirstCharacterLineNumber) Or _
StartPage <> AppWrd.Selection.Range.Information( _
wdActiveEndPageNumber)
Counter = Counter + 1
ReDim Preserve LineX(1 To Counter)
ReDim Preserve PageX(1 To Counter)
ReDim Preserve FPath(1 To Counter)
ReDim Preserve FName(1 To Counter)
If LineX(Counter - 1) = _
AppWrd.Selection.Range.Information( _
wdFirstCharacterLineNumber) And _
PageX(Counter - 1) = _
AppWrd.Selection.Range.Information( _
wdActiveEndPageNumber) And _
Pos = _
AppWrd.Selection.Range.Information( _
wdHorizontalPositionRelativeToPage) Then
Exit Do
Else
LineX(Counter) = _
AppWrd.Selection.Range.Information( _
wdFirstCharacterLineNumber)
PageX(Counter) = _
AppWrd.Selection.Range.Information( _
wdActiveEndPageNumber)
FPath(Counter) = Doc.Path
FName(Counter) = Doc.Name
Pos = _
AppWrd.Selection.Range.Information( _
wdHorizontalPositionRelativeToPage)
AppWrd.Selection.Find.Execute
End If
Loop
NextLoop:
End With
Doc.Close False
Set Doc = Nothing
On Error GoTo 0
FileName = Dir()
Loop
If Counter = 0 Then
MsgBox Search & " was not found.", vbInformation, "Zero Results For Search"
GoTo Canceled:
End If
Set WS = ThisWorkbook.Sheets("Sheet1")
With WS
.Range("A1").Value = "Occurrences of the word " & """" & Search & """"
.Range("A1:C1").Merge
.Range("A2").Value = "Document Path"
.Range("B2").Value = "Page Number"
.Range("C2").Value = "Line Number"
.Range("A1:C2").Font.Bold = True
.Range("A1:C2").HorizontalAlignment = xlCenter
For Row = UBound(LineX) To 1 Step -1
If PageX(Row) = 0 Or LineX(Row) = 0 Then
Else
.Range("B" & Row + 2).Value = PageX(Row)
.Range("C" & Row + 2).Value = LineX(Row)
.Hyperlinks.Add Anchor:=.Range("A" & Row + 2), _
Address:=FPath(Row) & "\" & FName(Row), TextToDisplay:=FName(Row)
End If
Next Row
.Range("A:C").EntireColumn.AutoFit
End With
Canceled:
AppWrd.Quit
Set Doc = Nothing
Set AppWrd = Nothing
WordBasic.DisableAutoMacros False
Application.DisplayAlerts = True
Application.ScreenUpdating = True
End Sub