Separate strings in a text file

vivka · #1 12-09-2023, 06:29 AM

RobiNew, what do you mean by "extract": hilighting, msgboxing, adding to a collection, deleting...? For me your task is not quite clear.

If you need to hilight the found strings, you may use the followng code, which was once made by gmaxey and slightly modified by me:
Sub Hilite_Array_T()
'In selection, hilite all instances of 'width=' and 'height=' followed
'by three-digit numbers.

Application.ScreenUpdating = False
Dim vFindTxt As Variant
Dim oRng As range
Dim i As Long
vFindTxt = Array("width=", "height=")
For i = 0 To UBound(vFindTxt)
Set oRng = selection.range
With oRng.Find
.ClearFormatting
.Replacement.ClearFormatting
Do While .Execute(FindText:=vFindTxt(i), _
MatchWholeWord:=True, _
Forward:=True, _
Wrap:=wdFindStop) = True And _
oRng.End <= selection.range.End
oRng.MoveEnd unit:=wdCharacter, count:=3
oRng.HighlightColorIndex = wdYellow
oRng.Collapse wdCollapseEnd
Loop
End With
DoEvents
Next
lbl_Exit:
Set oRng = Nothing
Exit Sub
Application.ScreenUpdating = True
End Sub

RobiNew · #2 12-09-2023, 07:54 AM

Thank you, Vivka! Your code leaves everything unchanged. But what I need is not to highlight all instances of 'width=' and 'height=' followed by three-digit numbers.
As I suggested in the original post, I have a text file with several sequences of this type:

<p class=NonNrPar align=center style='text-align:center;line-height:
normal'><img width=453 height=255 id="Immagine 1"
src="E_DIME_ORIG_file/image001.jpg"></p>

I'm trying to write a code that will
1) Find part of the above string: from <img to ><;
2) create a variable that contains the string width=### in the Found string;
3) create a variable that contains the string height=### in the Found string;
4) Delete the Found string: from <img to ><.

Hope someone can help. Thanks!

RobiNew · #3 12-09-2023, 09:46 AM

I managed to make it work correctly, provisionally on a single instance of the text mentioned above.
Perhaps someone can make it less clumsy.

Code:

Sub ThreeStrings()
Dim oRng As Range
Set oRng = ActiveDocument.Range
With oRng.Find
        .Text = "<img width"
        .Replacement.Text = ""
        .Forward = True
        .Wrap = wdFindStop
        .Format = False
        .MatchWildcards = False
While .Execute
oRng.MoveEndUntil Cset:="><"
VarStrg1 = oRng
'MsgBox VarStrg1
oRng.Collapse
oRng.MoveEndUntil Cset:=" "
oRng.Move Unit:=wdCharacter, Count:=2
oRng.MoveEndUntil Cset:=" "
VarWd = oRng
'MsgBox VarWd
oRng.Move Unit:=wdCharacter, Count:=2
oRng.MoveEndUntil Cset:=" "
VarHi = oRng
'MsgBox VarHi
Set oRng = ActiveDocument.Range
With oRng.Find
        .Text = "<img width"
        .Replacement.Text = ""
        .Forward = False
        .Wrap = wdFindStop
        .Format = False
        .MatchWildcards = False
        .Execute
End With
oRng.MoveEndUntil Cset:="><"
oRng.Delete
Goto End
Wend
    End With
End:
End Sub

vivka · #4 12-09-2023, 01:30 PM

As a simple variant:

Code:

Sub Test()

Dim oRng As range
Dim vWd As Variant
 Dim vHi As Variant

    Set oRng = ActiveDocument.range
    With oRng.Find
        .ClearFormatting
        .Replacement.ClearFormatting
        .text = "width=^#^#^#"
        .Replacement.text = ""
        .MatchWildcards = False
        .Forward = True
        .Wrap = wdFindStop
        If .Execute Then vWd = oRng
    End With

    Set oRng = ActiveDocument.range
    With oRng.Find
        .text = "height=^#^#^#"
        If .Execute Then vHi = oRng
    End With

    With ActiveDocument.range.Find
        .text = "\<" & "img width" & "*" & "\>\<"
        .MatchWildcards = True
        .Execute Replace:=wdReplaceAll
    End With
MsgBox vWd & vbCr & vHi
lbl_Exit:
Set oRng = Nothing
End Sub

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
How to hide/delete slides based on keyword in a separate text file based on AND\|OR condition?	rupd911	PowerPoint	0	02-22-2021 08:22 AM
Auto Save Every Page(s) as a separate file, and name each new file automatically by the first line?	commissarmo	Word VBA	3	03-14-2015 12:53 AM
Copying a part of a docx file as a separate file	officeboy09	Word	6	09-26-2014 05:15 PM
Search Multiple strings and create new word file	subodhgupta	Word	4	05-22-2014 03:34 AM
update style of all strings available between two specific strings	vikrantkale	Word	1	03-28-2011 06:13 PM