Function CleanTags(HTML As String) As String
'PURPOSE: Clean HTML tags except the paragraph, weblinks and title
' You can comment out if you want these to supress these as well
' The instructions are given at the spots.
' SOURCE: Unknown and AutarKaw.org
Dim result As String, StripIt As Boolean, c As String, i As Long
HTML = TextFile_PullData()
'StripIt is used to figure out to include or exclude in output
StripIt = False
'Looking at each character in the HTML file
For i = 1 To Len(HTML)
'c is each character
c = Mid(HTML, i, 1)
'Some conditions to take care for end of input file
If i <= Len(HTML) - 1 Then
'd is last two characters of file to capture <a and <p
'Just in case
d = Mid(HTML, i, 2)
Else
d = ""
End If
If i <= Len(HTML) - 3 Then
'e is last four characters of file to capture </a> and </p>
e = Mid(HTML, i, 4)
Else
e = ""
End If
'Checking for < character that begins an HTML tag
If c = "<" Then StripIt = True
'Comment this if you want to strip paragraphs
If d = "<p" Then StripIt = False
If e = "</p>" Then StripIt = False
'Comment this if you want to strip URL tags and title tags as well.
If d = "<a" Then StripIt = False
If e = "</a>" Then StripIt = False
'Adds to output or skips it
If StripIt = False Then result = result & c
'Taking care of closing tag to change the StripIt Boolean
If c = ">" Then StripIt = False
Next i
CleanTags = result
'Putting the output in a new file
abc = TextFile_Create(result)
'Run the program by entering =CleanTags(A1) in a blank excel file
'where you have this module. Puts Done in cell if it runs correctly
CleanTags = "Done"
'This lets you know the work is done. Comment if you like.
'MsgBox ("Done")
End Function
Function TextFile_PullData()
'PURPOSE: Send All Data From Text File To A String Variable
'SOURCE: www.TheSpreadsheetGuru.com
Dim TextFile As Integer
Dim FilePath As String
Dim FileContent As String
'File Path of Text File
FilePath = "C:\Users\Tranq\Documents\abc\inputhtml.txt"
'Determine the next file number available for use by the FileOpen function
TextFile = FreeFile
'Open the text file
Open FilePath For Input As TextFile
'Store file content inside a variable
FileContent = Input(LOF(TextFile), TextFile)
'Report Out Text File Contents
'MsgBox FileContent
'Close Text File
Close TextFile
TextFile_PullData = FileContent
End Function
Function TextFile_Create(HTML As String)
'PURPOSE: Create A New Text File
'SOURCE: www.TheSpreadsheetGuru.com
Dim TextFile As Integer
Dim FilePath As String
'What is the file path and name for the new text file?
FilePath = "C:\Users\Tranq\Documents\abc\outputhtml.txt"
'Determine the next file number available for use by the FileOpen function
TextFile = FreeFile
'Open the text file
Open FilePath For Output As TextFile
'Write some lines of text
Print #TextFile, HTML
'Save & Close Text File
Close TextFile
End Function