I have this json array and the data I need is in the array that starts data_id which I cannot extract. I am able to extract keys,value before the array but not in the array. I believe I need to request data in a specific way with a number in () after the fieldname nest but I cannot find a beginners explanation to see what number goes in the brackets and why you chose that number.
{"api":{"results":37,"data":[{"data_id":643951,"location_id":3005,"person":{"name":"Bob","country":"Turkey",
Any tips appreciated here is some code
'Print a few object variables before parse
Dim WrkSht As Worksheet
Set WrkSht = ThisWorkbook.Worksheets("jsonoutput")
WrkSht.Cells(1, 1).Value = xml_obj.responseText
' Displays data fine in one string as shown above
'Parse the response
Set jp = JsonConverter.ParseJson(xml_obj.responseText)
For Each dict In jp
Debug.Print dict
If Not IsObject(jp(dict)) Then
Debug.Print jp(dict)
Else
For Each subDict In jp(dict)
Debug.Print subDict
'Debug.Print jp(dict)(subDict)
Next subDict
End If
Next dict
' I need to drill down into further levels but ?
End Sub
Here's a simple example
JSON used:
{"api":{"results":37,
"data":[{"data_id":643951,
"location_id":3005,
"person":{"name":"Bob","country":"Turkey"}
} ]
}}
Code:
Sub Test36()
Dim jso As Object, arr, data, obj
'loading from a cell for testing...
Set jso = JsonConverter.ParseJson(Sheet2.Range("A17").Value)
'jso is a Dictionary
Debug.Print jso("api")("results") '>> 37
Set data = jso("api")("data") 'data is a Collection
Debug.Print data.Count ' >> 1
For Each obj In data
Debug.Print obj("data_id") '>> 643951
Debug.Print obj("person")("country") '>> Turkey
Next obj
End Sub
I thought I would just share the code I ended up with. It can be improved on and some is over coded simply to make it easier to see where amendments can be made. Currently this will:
Access an API - just put as many header lines in as you need
Collect the JSON data and flatten it to one level - this code will only work with Json where
blank values are recorded as "null" rather than just "". You may
have to manually correct the columns (or update the code) for
blank values
Ask you which key you want to start with - it will
then mark that keys values to start a new row each time it comes
across this
Make replacements in the data to create delimiters
to mark which data is keys and which is values
Pastes your keys
in row 1 that have values - dictionary keys are ignored but
you can change that if needed
Remove all keys from the string to
just leave values and paste those in the rows below.
You need to have the RunScriptime XMl HTTP 6.0 and Object library ticked in Tools reference in VBA as well
Sub FlattenJsonGetDataFromKeysWithValues()
ActiveWorkbook.Worksheets("yourworksheet").Range("a1:ZZ10000").ClearContents
Dim i As Long
'Declare variables
Dim xml_obj As MSXML2.XMLHTTP60
Dim base_url As String
Dim Json1 As String, Json2, Json3, Json4, Json5, Json6, json7, Json8, Json9, Json10, Json11, Json12, Json13, Json14, Json15, Json16, Json17, Json18
Dim Json0 As String
Dim keys As String, keys2
'Create a new Request Object make sure in Tools-> reference the xml6.0, scripting runtime and object library are ticked
Set xml_obj = New MSXML2.XMLHTTP60
'Define URL Components two headers are shown but you cana dd as many as required
base_url = "https://yoururl.com"
xml_obj.Open "GET", base_url
xml_obj.SetRequestHeader "key", "55555"
xml_obj.SetRequestHeader "host", "valuefor2ndheaderkeyifneeded"
xml_obj.Send
'Print the status code in case something went wrong
MsgBox("The Request was " + CStr(xml_obj.Status))
strJson0 = xml_obj.responseText
MsgBox (Len(strJson0)) ' tells how long string is
'Look for Json current delimiters and change all to a comma
Json1 = strJson0
Const SpecialCharacters As String = "!,#,#,$,%,^,&,*,(,),{,[,],},?,:"
Dim char As Variant
For Each char In Split(SpecialCharacters, ",")
Json1 = Replace(Json1, char, " ")
Next
' Place # before all field names, I have shown in this way so if needed you can vary to suit your needs
Json2 = Replace(Json1, "," & Chr(34), "#") ' Replaces ," - Chr(34) is a "
Json3 = Replace(Json2, ", " & Chr(34), "#") ' replaces , "
Json4 = Replace(Json3, Chr(34) & " " & Chr(34), Chr(34) & "#") ' Replaces " "
Json5 = Replace(Json4, Chr(34) & " " & Chr(34), Chr(34) & "#") ' Replaces " "
'Place : after fieldname and before value
Json6 = Replace(Json5, Chr(34) & " " & Chr(34), ":") 'Replaces " "
json7 = Replace(Json6, Chr(34) & " ", ":") 'Replaces "(blankspace)
Json8 = Replace(json7, Chr(34), ":") 'Replaces "
Json9 = Replace(Json8, ":#", "#") 'Replaces :# with #
Json10 = Replace(Json9, "/", "") 'Removes /
Json11 = Replace(Json10, " ", "") 'Removes blankspace
If Left(Json11, 1) = ":" Then Json11 = "#" & Right(Json11, (Len(Json11) - 1)) ' Replace : with # if first character
' Now you just have field names (keys) marked by # and values marked by :
' Find Field Names - which field should we start with? How many times is that key in the data
Dim firstkey As String
MsgBox (Json11) 'View this to see your key/header row options
firstkey = InputBox("Enter First Field/Key to locate") 'This will mark where all new rows start
keys = Json11
' Now take text between #*# as dictionary keys and ignore and text between #*: as headers for field names until repeat text is found in string by finding the firstkey you input above and putting a # marker in all heading that = firstkey
Dim openPos As Long
Dim closePos As Long
Dim k As Integer
Dim jsonFields As Collection
Set jsonFields = New Collection
Dim jsonValues As Collection
Set jsonValues = New Collection
' Find wanted starting key, skip over keys without value
k = 1
openPos = InStr(keys, firstkey)
closePos = InStr(openPos, keys, ":")
If InStr(1, Mid(keys, openPos, closePos - openPos), "#") > 0 Then openPos = openPos + InStr(1, Mid(keys, openPos, closePos - openPos), "#")
jsonFields.Add Mid(keys, openPos, closePos - openPos)
keys = Replace(keys, firstkey & ":", ":#")
k = k + 1
' Find other keys with values, find dict keys
Do Until Mid(keys, openPos, closePos - openPos) = ""
openPos = InStr(closePos, keys, "#") + 1
If k = 2 Then openPos = InStr(1, keys, "#")
closePos = InStr(openPos, keys, ":")
If InStr(1, Mid(keys, openPos, closePos - openPos), "#") > 0 Then openPos = openPos + InStr(1, Mid(keys, openPos, closePos - openPos), "#")
jsonFields.Add Mid(keys, openPos, closePos - openPos)
k = k + 1
Loop
' Find values and remove delimiters, keys and replace : in https values that are removed with other delimiters
y = 2 ' use to start populate rows
currentcolumn = 1
Dim r&
p = Split(keys, "#")
For r = 0 To UBound(p)
If InStr(1, p(r), ":") Then p(r) = Right(p(r), Len(p(r)) - InStr(1, p(r), ":") + 1) ' remove keys
If InStr(1, p(r), ":") = 0 Then p(r) = "" ' remove :
If InStr(1, p(r), ":") Then p(r) = Right(p(r), Len(p(r)) - InStr(1, p(r), ":")) ' set value for collection to print later
If InStr(1, p(r), "https") Then p(r) = Replace(p(r), "https", "https:") ' fix https value by readding :
jsonValues.Add p(r) ' add to collection
Next r
' Print Values to worksheet
currentcolumn = 1
'Now Output your parsed key data, turn screen updating off
Application.ScreenUpdating = False
Application.Calculation = xlCalculationManual
For Each Item In jsonFields
ActiveWorkbook.Worksheets("yourworksheet").Cells(1, currentcolumn).Value = Item
currentcolumn = currentcolumn + 1
Next Item
y = 2
currentcolumn = 1
Dim ws As Worksheet
Set ws = Worksheets("yourworksheet")
For Each Item In jsonValues
If Len(Item) > 0 Then
If InStr(1, Item, "#") = 1 Then
y = y + 1
currentcolumn = 1
End If
ws.Cells(y, currentcolumn).Value = Item
currentcolumn = currentcolumn + 1
End If
Next Item
Application.ScreenUpdating = True
Application.Calculation = xlCalculationAutomatic
End Sub
Related
I have a problem extracting words in MS Excel. I have multiple sentences in HTML format in a row and want to extract all of the words that are delimited by <b>....</b>
Example:
<b>buat</b> <i>v</i> <b>1</b> kerjakan; lakukan; <b>2</b> bikin;<br>--<b> cendol</b>
I want to extract the words: "buat", "1", "2", "cendol"
Can you help me to solve my problem? Any code in Excel/VBA is appreciated.
This can be done with the worksheet function FILTERXML if you have Excel 2013+
First you need to change your string into a "well-formed" XML by enclosing it in an external tag, and closing off the unmatched <br> tag:
"<t>" & $A$1 & "</br></t>"
Then it's merely a matter of using an Xpath that will return all of the wanted tags:
FILTERXML("<t>" & $A$1 & "</br></t>","//b")
Wrapping that in an INDEX function allows you to extract the substrings one at a time:
Full Formula entered in A3 and filled down
=IFERROR(INDEX(FILTERXML("<t>" & $A$1 & "</br></t>","//b"),ROWS($1:1)),"")
There's a very easy way to do this by using an HTMLDocument object:
In your VB Editor, go to Tools>References and select the Microsoft HTML Object Library.
Then you can use the following code:
Sub extract()
Dim doc As New HTMLDocument 'Declare and create an object of type HTMLDocument
Dim item As HTMLObjectElement 'Declare an object of type HTMLObjectElement. We will use this to loop through a collection of HTML elements
doc.body.innerHTML = "<b>buat</b> <i>v</i> <b>1</b> kerjakan; lakukan; <b>2</b> bikin;<br>--<b> cendol</b> " 'Assign your HTML code as a string in doc body
For Each item In doc.getElementsByTagName("b") 'Loop through all the <b></b> elements in doc
Debug.Print item.innerText 'print the text contained in <b></b> element. This will show up in your immediate window
Next item
End Sub
Try this
Sub Test()
Dim objReg As Object
Dim objMatches As Object
Dim match As Object
Dim s As String
Dim i As Integer
s = "<b>buat</b> <i>v</i> <b>1</b> kerjakan; lakukan; <b>2</b> bikin;<br>--<b> cendol</b> "
Set objReg = CreateObject("VBScript.RegExp")
With objReg
.IgnoreCase = False
.Global = True
.Pattern = "<b>(.*?)<\/b>"
Set objMatches = .Execute(s)
End With
For Each match In objMatches
For i = 0 To match.Submatches.Count - 1
Debug.Print Trim(match.Submatches.item(i))
Next i
Next match
Set objReg = Nothing
End Sub
Alternative using XML DomDocument
Analyzing a HTML string it seems evident to use document object structures as in a HTMLDocument or in ►XML. That's why I demonstrate a further approach for the sake of completeness and in addition to #StavrosJon 's valid solution (which uses the more lenient HTMLDocument not needing to be well formed as XML is):
Example call
Sub ExtractViaXML()
Dim html$, myArray()
html = "<b>buat</b> <i>v</i> <b>1</b> kerjakan; lakukan; <b>2</b> bikin;<br>--<b> cendol</b> "
myArray = getTokens(html, "b") ' assign findings to array via function getTokens()
Debug.Print UBound(myArray) + 1 & " token(s) found: " & Join(myArray, ", ") ' display results
End Sub
Main function getTokens()
Function getTokens(ByVal html$, Optional myTag$ = "b") As Variant()
' Purpose: isolate "<b>"-Tags (default value) out of html string and return found tokens as variant array
' Note: creates temporary XML DOMDocument (late bound MSXML2 reference)
Dim XmlString$
XmlString = wellformed("<?xml version=""1.0"" encoding=""utf-8""?><tokens>" & html & "</tokens>")
With CreateObject("MSXML2.DOMDocument.6.0")
.ValidateOnParse = True: .Async = False
If .LoadXML(XmlString) Then ' load xml string
Dim myNodeList As Object
Set myNodeList = .DocumentElement.SelectNodes(myTag) ' set node list to memory
Dim i&, ii&, arr()
ii = myNodeList.Length - 1 ' calculate upper boundary of zero-based array
If ii > -1 Then ReDim arr(ii) ' (re)dimension variant array arr()
For i = 0 To ii ' loop through node list
arr(i) = myNodeList.item(i).Text ' assign each found text content to array
Next i
If ii = -1 Then arr = Array("**Nothing found**") ' provide for zero findings
getTokens = arr ' return 0-based 1-dim array with found tokens
Else: ShowParseError (.ParseError) ' optional: display possible error message
End If
End With
End Function
Helper functions
XML requires a well formed node structure with opening and closing tags or, whereas HTML is more lenient towards e.g. single line breaks(<br>). Therefore I added a simple function wellformed() to cure such an issue preventing successful loading. Furthermore I demonstrate using an optional procedure ShowParseError to localize (other) possible loading Errors which you can use as supplement to any .load or .loadXML function.
Function wellformed$(ByVal s$)
' Purpose: force a wellformed version of line breaks in html/xml string ("<br/>")
' Note: unclosed tags like <br> only would prevent a successful load of the xml document
wellformed = Replace(Replace(s, "</br>", "<br>"), "<br>", "<br/>")
End Function
Sub ShowParseError(pe As Object)
' Purpose: display possible parse error
' Note: localizes error occurrence also by indicating position
Dim ErrText$
With pe
ErrText = "Load error " & .ErrorCode & " xml file " & vbCrLf & _
Replace(.URL, "file:///", "") & vbCrLf & vbCrLf & _
.reason & _
"Source Text: " & .srcText & vbCrLf & vbCrLf & _
"Line No.: " & .Line & vbCrLf & _
"Line Pos.: " & .linepos & vbCrLf & _
"File Pos.: " & .filepos & vbCrLf & vbCrLf
End With
MsgBox ErrText, vbExclamation
End Sub
I tried something different, with splitting and joining and splitting again and looping trough array. I typed the text <b>buat</b> <i>v</i> <b>1</b> kerjakan; lakukan; <b>2</b> bikin;<br>--<b> cendol</b> in cell A1:
Sub Macro1()
Dim MyWords As Variant
Dim i As Long
Dim MyDelimiter As String
Dim MyLen As Byte
MyDelimiter = "||" 'Choose 1 not common delimiter
MyLen = Len(MyDelimiter)
MyWords = Split(Join(Split(Range("A1").Value, "<b>"), MyDelimiter), "</b>")
For i = 0 To UBound(MyWords) Step 1
Debug.Print Mid(MyWords(i), InStr(1, MyWords(i), MyDelimiter) + MyLen, 99) 'Increase 99 if you are sure there will be longer texts between tags <b>..</b>
Next i
Erase MyWords
End Sub
I get this:
i have tried to simulate this on excel. please check my sample solution below.
Sub test()
Dim testString As String
Dim startPos As Integer
Dim endPos As Integer
Dim resultString As String
Dim str As String
testString = "<b>buat</b> <i>v</i> <b>1</b> kerjakan; lakukan; <b>2</b> bikin;<br>--<b> cendol</b>"
'get the position of start tag
startPos = InStr(1, testString, "<b>") + 3
'get the position of end tag
endPos = InStr(startPos, testString, "</b>")
Do While Len(testString) > 1
'check if the start pos and end pos is correct
If startPos > 0 And endPos > startPos Then
'get the value in between the start tag and end tag
str = Mid(testString, startPos, endPos - startPos)
resultString = resultString + str + ","
'remove the value retrieved from the original string
testString = Mid(testString, endPos + 4)
startPos = InStr(1, testString, "<b>") + 3
endPos = InStr(startPos, testString, "</b>")
End If
Loop
End Sub
I'm building a VBA app that creates and modifies Wordpress website pages using resources scraped from the web. The Wordpress API returns a JSON file but there is no native support for parsing JSON in VBA so I imported VBA-JSON from GitHub. Here is the subroutine:
Sub Wordpress()
'
' Wordpress API Test
'
Dim wpResp As Variant
Dim sourceSheet As String
Dim resourceURL As String
sourceSheet = "Resources"
resourceURL = Sheets(sourceSheet).Cells(6, 1)
wpResp = getJSON(resourceURL + "/wp-json/wp/v2/posts")
End Sub
And the function it calls.
Function getJSON(link) As Object
Dim response As String
Dim json As Object
On Error GoTo recovery
Dim retryCount As Integer
retryCount = 0
Dim web As MSXML2.XMLHTTP60
Set web = New MSXML2.XMLHTTP60
the_start:
web.Open "GET", link, False, UserName, pw
web.setRequestHeader "Content-type", "application/json"
web.send
response = web.responseText
While web.readyState <> 4
DoEvents
Wend
On Error GoTo 0
Debug.Print link
Debug.Print web.Status; "XMLHTTP status "; web.statusText; " at "; Time
Set json = JsonConverter.ParseJson(response)
'getJSON = json ' this line produces Object variable or With block variable not set error but I can deal with it later
Exit Function
recovery:
retryCount = retryCount + 1
Debug.Print "Error number: " & Err.Number & " " & Err.Description & " Retry " & retryCount
Application.StatusBar = "Error number: " & Err.Number & " " & Err.Description & " Retry " & retryCount
If retryCount < 4 Then GoTo the_start Else Exit Function
End Function
This code returns an Object/Collection with 1 item that contains a Variant/Object/Dictionary with 24 items but I'm lost on how to access these items. Here is a screenshot:
If I use the immediate window to query ?json.count I get the correct result "1" but after about six hours of researching on the web and trying as many variants as I could find, I'm still stuck on how to access the other 24.
Here is the JSON:
[{"id":1,"date":"2018-06-22T18:13:00","date_gmt":"2018-06-22T22:13:00","guid":{"rendered":"http:\/\/mytestsite.org\/?p=1"},"modified":"2018-06-22T18:13:00","modified_gmt":"2018-06-22T22:13:00","slug":"hello-world","status":"publish","type":"post","link":"http:\/\/mytestsite.org\/hello-world\/","title":{"rendered":"Blog Post Title"},"content":{"rendered":"<p>What goes into a blog post? Helpful, industry-specific content that: 1) gives readers a useful takeaway, and 2) shows you’re an industry expert. <\/p>\n<p>Use your company’s blog posts to opine on current industry topics, humanize your company, and show how your products and services can help people.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>What goes into a blog post? Helpful, industry-specific content that: 1) gives readers a useful takeaway, and 2) shows you’re…<\/p>\n","protected":false},"author":1,"featured_media":212,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"http:\/\/mytestsite.org\/wp-json\/wp\/v2\/posts\/1"}],"collection":[{"href":"http:\/\/mytestsite.org\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/mytestsite.org\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/mytestsite.org\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/mytestsite.org\/wp-json\/wp\/v2\/comments?post=1"}],"version-history":[{"href":"http:\/\/mytestsite.org\/wp-json\/wp\/v2\/posts\/1\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/mytestsite.org\/wp-json\/wp\/v2\/media\/212"}],"wp:attachment":[{"href":"http:\/\/mytestsite.org\/wp-json\/wp\/v2\/media?parent=1"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/mytestsite.org\/wp-json\/wp\/v2\/categories?post=1"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/mytestsite.org\/wp-json\/wp\/v2\/tags?post=1"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}]
At the end of the day, I want to be able to spin up a few hundred pages of WP content extracted and collated from several internet sources and keep them up to date using this app. Further suggestions beyond the problem here would also be useful so long as we don't get outside of VBA.
The JsonConverter is returning a collection of VBA.Collections Scripting.Dictionaries, and Values. In order to understand the output you will have to test the TypeName of all the returned values.
The real question is "How to navigate through a json object (or any unknown object for that matter) and access the values within.
Immediate Window
Using the Immediate Window and the json object from the OP's post I will try to describe the thought process (in the style of the must read book: The Little Schemer)
' What is json?
?TypeName(JSON)
Collection
'json is a collection
'How big is JSON
?JSON.Count
1
'JSON is a collection of 1 Item
'What is Type that Item?
?TypeName(JSON(1))
Dictionary
'JSON(1) is a Dictionary
'What is the first key in the JSON(1) Dictionary?
?JSON(1).Keys()(0)
id
'The first key in the JSON(1) Dictionary is "id"
'What is the Type of the value of "id"?
?TypeName(JSON(1)("id"))
Double
'JSON(1)("id") is a number
'What is its value
?JSON(1)("id")
1
Of course this process can get tedious consider the amount of nesting in this JSON Object.
JSON(1)("_links")("curies")(1)("templated")
Collection|Dictionary|Dictionary|Collection|Boolean Value
So I guess the best thing to do is write a function that will print all the accessor to the Immediate Window and go from there.
PrintJSONAccessors:Sub
Sub PrintJSONAccessors(JSON As Variant, Optional Prefix As String)
Dim data As Variant, Key As Variant, Value As Variant
Dim Accessor As String, ArrayAccessor As String
Dim n As Long
If TypeName(JSON) = "Collection" Then
For n = 1 To JSON.Count
Accessor = Prefix & "(" & n & ")"
If TypeName(JSON(n)) = "Dictionary" Or TypeName(JSON(n)) = "Collection" Then
PrintJSONAccessors JSON(n), Accessor
Else
Debug.Print Accessor
End If
Next
Else
For Each Key In JSON
If TypeName(Key) = "Dictionary" Or TypeName(Key) = "Collection" Then
PrintJSONAccessors Key, Prefix
ElseIf TypeName(JSON(Key)) = "Dictionary" Or TypeName(JSON(Key)) = "Collection" Then
Accessor = Prefix & "(" & Chr(34) & Key & Chr(34) & ")"
PrintJSONAccessors JSON(Key), Accessor
ElseIf TypeName(JSON(Key)) = "Dictionary" Then
Accessor = Prefix & "(" & Chr(34) & Key & Chr(34) & ")"
PrintJSONAccessors JSON(Key), Accessor
ElseIf TypeName(JSON(Key)) = "Variant()" Then
data = JSON(Key)
For n = LBound(data) To UBound(data)
Accessor = Prefix & "(" & Chr(34) & Key & Chr(34) & ")"
ArrayAccessor = Prefix & "(" & Chr(34) & Key & Chr(34) & ")" & "(" & n & ")"
If TypeName(data(n)) = "Dictionary" Then
PrintJSONAccessors data(n), ArrayAccessor
Else
Debug.Print ArrayAccessor
End If
Next
Else
Accessor = Prefix & "(" & Chr(34) & Key & Chr(34) & ")"
Debug.Print Accessor
End If
Next
End If
End Sub
Usage:
PrintJSONAccessors JSON, "?JSON"
It appears that the MSScriptControl.ScriptControl only works on 32 bit systems. I guess that is what SIM was alluding to in his comments. Although, my answer is IMO correct, you should ignore the next section of comments.
FYI: I posted a function that parses the JSON into Arrays and Dictionaries Function to Return a JSON Like Objects Using VBA Collections and Arrays on Code Review. It is not a replacement for JsonConverter or omegastripes's JSON.Bas. It demonstrates that you can add JScript code to CreateObject("MSScriptControl.ScriptControl") and use it to process the JSON.
Try the code:
Set json = JsonConverter.ParseJson(s)
For Each k In json(1)
Debug.Print k & vbTab & json(1)(k)
Next
UPDATE
Take a look at the below example. Import JSON.bas module into the VBA project for JSON processing.
Option Explicit
Sub Test()
Dim sJSONString As String
Dim vJSON
Dim sState As String
Dim aData()
Dim aHeader()
Dim vResult
' Read JSON sample from file C:\Test\sample.json
sJSONString = ReadTextFile("C:\Test\sample.json", 0)
' Parse JSON sample
JSON.Parse sJSONString, vJSON, sState
If sState = "Error" Then
MsgBox "Invalid JSON"
End
End If
' Get the 1st element from root [] array
Set vJSON = vJSON(0)
' Convert raw JSON to 2d array and output to worksheet #1
JSON.ToArray vJSON, aData, aHeader
With Sheets(1)
.Cells.Delete
.Cells.WrapText = False
OutputArray .Cells(1, 1), aHeader
Output2DArray .Cells(2, 1), aData
.Columns.AutoFit
End With
' Flatten JSON
JSON.Flatten vJSON, vResult
' Convert flattened JSON to 2d array and output to worksheet #2
JSON.ToArray vResult, aData, aHeader
With Sheets(2)
.Cells.Delete
.Cells.WrapText = False
OutputArray .Cells(1, 1), aHeader
Output2DArray .Cells(2, 1), aData
.Columns.AutoFit
End With
MsgBox "Completed"
End Sub
Sub OutputArray(oDstRng As Range, aCells As Variant)
With oDstRng
.Parent.Select
With .Resize(1, UBound(aCells) - LBound(aCells) + 1)
.NumberFormat = "#"
.Value = aCells
End With
End With
End Sub
Sub Output2DArray(oDstRng As Range, aCells As Variant)
With oDstRng
.Parent.Select
With .Resize( _
UBound(aCells, 1) - LBound(aCells, 1) + 1, _
UBound(aCells, 2) - LBound(aCells, 2) + 1)
.NumberFormat = "#"
.Value = aCells
End With
End With
End Sub
Function ReadTextFile(sPath As String, lFormat As Long) As String
' lFormat -2 - System default, -1 - Unicode, 0 - ASCII
With CreateObject("Scripting.FileSystemObject").OpenTextFile(sPath, 1, False, lFormat)
ReadTextFile = ""
If Not .AtEndOfStream Then ReadTextFile = .ReadAll
.Close
End With
End Function
BTW, the similar approach applied in other answers.
I want the following html page to submit the embedded image rather than using file input offered by
<input type= file name="file1" name="file1"> to an asp uploader following the code below?!
<form name="Mine" id="Mine" enctype="multipart/form-data" action="upload1.asp" method="post">
which will post image data to the following asp uploader ( upload1.asp) which originally submit the file input but not an embedded image
<%
option explicit
Response.Write "<BR>Execution ended: " & now
' used to track various positions
dim PosB, PosBBound, PosEBound, PosEHead, PosBFld, PosEFld
' these handle the data
dim Boundary, BBoundary, PartBHeader, PartAHeader, PartContent, PartContent2, Binary
' for writing and converting
dim fso, fle, rst, DataString, FileName
' various other
dim I, Length, ContType, PartName, LastPart, BCrlf, PartContentLength
' ado constants
const adLongVarBinary = 205
const adLongVarchar = 201
' must be submitted using POST
If Request.ServerVariables("REQUEST_METHOD") = "POST" Then
ContType = Request.ServerVariables("HTTP_Content_Type")
' must be "multipart/form-data"
If LCase(Left(ContType, 19)) = "multipart/form-data" Then
PosB = InStr(LCase(ContType), "boundary=") 'get boundary
If PosB > 0 Then Boundary = Mid(ContType, PosB + 9) 'we have one
'bugfix IE5.01 - double header
PosB = InStr(LCase(ContType), "boundary=")
If PosB > 0 then
PosB = InStr(Boundary, ",")
If PosB > 0 Then Boundary = Left(Boundary, PosB - 1)
end if
Length = CLng(Request.ServerVariables("HTTP_Content_Length")) 'Get Content-Length header
End If
If Length > 0 And Boundary <> "" Then
Boundary = "--" & Boundary
' get request, binary
Binary = Request.BinaryRead(Length)
' convert boundry to binary
For I=1 to len(Boundary)
BBoundary = BBoundary & ChrB(Asc(Mid(Boundary,I,1)))
Next
' binary crlf
BCrlf = ChrB(Asc(vbCr)) & ChrB(Asc(vbLf))
' get begin and end of first boundary
PosBBound = InStrB(Binary, BBoundary)
PosEBound = InStrB(PosBBound + LenB(BBoundary), Binary, BBoundary, 0)
' keep doing until we had them all
Do While (PosBBound > 0 And PosEBound > 0)
' get position of the end of the header
PosEHead = InStrB(PosBBound + LenB(BBoundary), Binary, BCrlf & BCrlf)
' get content of header and convert to string
PartBHeader = MidB(Binary, PosBBound + LenB(BBoundary) + 2, PosEHead - PosBBound - LenB(BBoundary) - 2)
PartAHeader = ""
For I=1 to lenb(PartBHeader)
PartAHeader = PartAHeader & Chr(AscB(MidB(PartBHeader,I,1)))
Next
' make sure we end it with ;
If Right(PartAHeader,1) <> ";" Then PartAHeader = PartAHeader & ";"
' get content of this part
PartContent = MidB(Binary, PosEHead + 4, PosEBound - (PosEHead + 4) - 2)
' get name of part
PosBFld = Instr(lcase(PartAHeader),"name=")
If PosBFld > 0 Then
' name found
PosEFld = Instr(PosBFld,lcase(PartAHeader),";")
If PosEFld > 0 Then
' well-formed name header
PartName = Mid(PartAHeader,PosBFld+5,PosEFld-PosBFld-5)
end if
' chop of leading and trailing "'s
Do Until Left(PartName,1) <> """"
PartName = Mid(PartName,2)
Loop
Do Until Right(PartName,1) <> """"
PartName = Left(PartName,Len(PartName)-1)
Loop
end if
' get file name of part (if any)
PosBFld = Instr(lcase(PartAHeader),"filename=""")
If PosBFld > 0 Then
' content header found
PosEFld = Instr(PosBFld + 10,lcase(PartAHeader),"""")
If PosEFld > 0 Then
' well-formed content header
FileName = Mid(PartAHeader,PosBFld+10,PosEFld-PosBFld-10)
end if
' chop of leading and trailing "'s
Do Until Left(FileName,1) <> """"
FileName = Mid(FileName,2)
Loop
Do Until Right(FileName,1) <> """"
FileName = Left(FileName,Len(FileName)-1)
Loop
Else
FileName = ""
end if
' do conversion of binary to regular data
' at the end, datastring will contain 'readable' data
' is this wide-byte binary data?
if vartype(PartContent) = 8 then
' need to do some conversion
Set rst = CreateObject("ADODB.Recordset")
PartContentLength = LenB(PartContent)
if PartContentLength > 0 then
' data, so add to recordset to speed up conversion
rst.Fields.Append "data", adLongVarBinary, PartContentLength
rst.Open
rst.AddNew
rst("data").AppendChunk PartContent & ChrB(0)
rst.Update
PartContent2 = rst("data").GetChunk(PartContentLength)
rst.close
set rst = nothing
else
' no data?
PartContent2 = ChrB(0)
End If
else
' no need for conversion
PartContent2 = PartContent
end if
PartContentLength = LenB(PartContent2)
if PartContentLength > 0 then
' we have data to convert
Set rst = CreateObject("ADODB.Recordset")
rst.Fields.Append "data", adLongVarChar, PartContentLength
rst.Open
rst.AddNew
rst("data").AppendChunk PartContent2
rst.Update
DataString = rst("data")
rst.close
set rst = nothing
Else
' nothing to convert
dataString = ""
End If
' conversion has been done, now what to do with it
If FileName <> "" Then
' we have a file, let's save it to disk
FileName = Mid(Filename,InstrRev(FileName,"\")+1)
' open a file (textstream)
set fso = Server.CreateObject("Scripting.Filesystemobject")
set fle = fso.CreateTextFile(server.MapPath(FileName))
' write the data
fle.write DataString
fle.close
' cleanup
set fle = nothing
set fso = nothing
' give notification
Response.Write "<BR>Uploaded file " & Partname & " - " & FileName & "(" & Len(Datastring) & " bytes)"
else
' some other type of field, let's just output this
Response.Write "<BR>Form field: " & Partname & " - " & Datastring
End If
LastPart = MidB(Binary, PosEBound + LenB(BBoundary), 2)
If LastPart = ChrB(Asc("-")) & ChrB(Asc("-")) Then
' don't look for others
PosBBound = 0
PosEBound = 0
else
' look for others
PosBBound = PosEBound
PosEBound = InStrB(PosBBound + LenB(BBoundary), Binary, BBoundary)
End If
loop
Response.Write "<P>End of form input, all fields processed"
else
Response.Write "<P>Invalid or empty request, no fields processed. Make sure that the content type is multipart/form-data"
end if
else
Response.Write "<P>Form must be submitted using the POST method"
end if
Response.Write "<BR>Execution ended: " & now
%>
I have a ms access table that is tracking 50 products with their daily sold volumes. I would like to export using vba 1 csv file (including headers) for each product showing the daily volumes from a recordset without saving the recordset to a permanent query. I am using the below code but I am stuck at the point of the actual export highlighted below in code.
Any assistance in fixing this is appreciated.
Dim rst As Recordset
Dim rstId As Recordset
SQLExportIds = "SELECT DISTINCT tblDailyVols.SecId FROM tblDailyVols WHERE tblDailyVols.IsDeleted=False"
Set rstId = CurrentDb.OpenRecordset(SQLExportIds)
If rstId.EOF = True Then
MsgBox "No Products Found"
Exit Sub
End If
Do While rstId.EOF = False
SecId = rstId.Fields("SecId")
SQLExportQuotes = " SELECT tblDailyVols.ID , tblDailyVols.TradedVolume, tblDailyVols.EffectiveDate FROM tblDailyVols "
SQLExportQuotes = SQLExportQuotes & " WHERE tblDailyVols.IsDeleted=False and tblDailyVols.ID = " & SecId
SQLExportQuotes = SQLExportQuotes & " ORDER BY tblDailyVols.EffectiveDate "
Set rst = CurrentDb.OpenRecordset(SQLExportQuotes)
If rst.EOF = True Then
MsgBox "No Quotes Found"
Exit Sub
End If
IDFound = rst.Fields("ID")
OutputPlace = “C:\Output” & IDFound & ".csv"
Set qdfTemp = CurrentDb.CreateQueryDef("", SQLExportQuotes)
**DoCmd.TransferText acExportDelim, , 1, OutputPlace, True** <--This Here Line Fails
Set rst = Nothing
rstId.MoveNext
Loop
Set rstId = Nothing
You will have to create an actual named QueryDef object for TransferText to work with, but then you can just delete it afterwards. Something like this:
Set qdfTemp = CurrentDb.CreateQueryDef("zzzTemp", SQLExportQuotes)
Set qdfTemp = Nothing
DoCmd.TransferText acExportDelim, , "zzzTemp", OutputPlace, True
DoCmd.DeleteObject acQuery, "zzzTemp"
You asked for a VBA solution, and I detect a preference for not creating new Access objects; you may well have good reasons for that, but the 'pure' VBA solution is a lot of work.
A solution that implements encapsulating text fields in quotes is the bare minimum for a competent answer. After that, you need to address the three big issues:
Optimising away VBA's clunky string-handling;
The Byte Order Marker, which VBA embeds in every string it saves to
file, ensuring that some of the most common consumers of a csv file
cannot read it properly;
...And there's rarely any middle ground between writing the file
line-by-line, forever, and writing it in one big chunk that'll throw
an out-of-memory error on larger recordsets.
Beginners in VBA may find the string-optimisations difficult to understand: the biggest performance gain available in native VBA is to avoid string allocation and concatenation ( here's why: http://www.aivosto.com/vbtips/stringopt2.html#huge ) - so I use join, split, and replace instead of myString = MyString & MoreString
The trailing loop, with the RecordSet.GetRows() call at the very end, will raise eyebrows among coders with strong opinions about structured programming: but there are constraints on how you can order the code so that the 'chunks' are concatenated into the file without any missed bytes, out-of-register shifts in the byte order, or blank lines.
So here goes:
Public Function RecordsetToCSV(ByRef rst As ADODB.Recordset, _
ByRef OutputFile As String, _
Optional ByRef FieldList As Variant, _
Optional ByVal CoerceText As Boolean = True, _
Optional ByVal CleanupText As Boolean = True _
) As Long
' Output a recordset to a csv file and returns the row count.
' If the output file is locked, or specified in an inaccessible location, the
' 'ByRef' OutputFile parameter becomes a file in the user's local temp folder
' You can supply your own field list. This isn't a substituted file header of
' aliased field names: it is a subset of the field names, which ADO will read
' selectively from the recordset. Each item in the list matches a named field
' CoerceText=TRUE will encapsulate all items, numeric or not, in quote marks.
' CleanupText=TRUE strips quotes and linefeeds from the data: FALSE is faster
' You should only set them FALSE if you're confident that the data is 'clean'
' with no quote marks, commas or line breaks in any unencapsulated text field
' This code handles unicode, and outputs a file that can be read by Microsoft
' ODBC and OLEDB database drivers by removing the Byte Order Marker.
On Error Resume Next
' Coding note: we're not doing any string-handling in VBA.Strings: allocating
' deallocating and (especially!) concatenating are SLOW. We are using the VBA
' Join and Split functions ONLY. Feel free to optimise further by declaring a
' faster set of string functions from the Kernel if you want to.
'
' Other optimisations: type pun. Byte Arrays are interchangeable with strings
' Some of our loops through these arrays have a 'step' of 2. This optimises a
' search-and-replace for ANSI chars in an array of 2-byte unicodes. Note that
' it's only used to remove known ANSI 'Latin' characters with a 'low' byte of
' zero: any other use of the two-byte 'step' will fail on non-Latin unicodes.
' ** THIS CODE IS IN THE PUBLIC DOMAIN **
' Nigel Heffernan Excellerando.Blogspot.com
Const FETCH_ROWS As Long = 4096
Dim COMMA As String * 1
Dim BLANK As String * 4
Dim EOROW As String * 2
COMMA = ChrW$(44)
BLANK = ChrW$(13) & ChrW$(10) & ChrW$(13) & ChrW$(10)
EOROW = ChrW$(13) & ChrW$(10)
Dim FetchArray As Variant
Dim i As Long ' i for rows in the output file, records in the recordset
Dim j As Long ' j for columns in the output file, fields in the recordset
Dim k As Long ' k for all other loops: bytes in individual data items
Dim i_Offset As Long
Dim i_LBound As Long
Dim i_UBound As Long
Dim j_LBound As Long
Dim j_UBound As Long
Dim k_lBound As Long
Dim k_uBound As Long
Dim hndFile As Long
Dim varField As Variant
Dim iRowCount As Long
Dim arrBytes() As Byte
Dim arrTemp1() As String
Dim arrTemp2() As String
Dim arrTemp3(0 To 2) As String
Dim boolNumeric As Boolean
Dim strHeader As String
Dim arrHeader() As Byte
Dim strFile As String
Dim strPath As String
Dim strExtn As String
strFile = FileName(OutputFile)
strPath = FilePath(OutputFile)
strExtn = FileExtension(strFile)
If rst Is Nothing Then Exit Function
If rst.State <> 1 Then Exit Function
If strExtn = "" Then
strExtn = ".csv"
End If
With FSO
If strFile = "" Then
strFile = .GetTempName
strFile = Left(strFile, Len(strFile) - Len(".tmp"))
strFile = strFile & strExtn
End If
If strPath = "" Then
strPath = TempSQLFolder
End If
If Right(strPath, 1) <> "\" Then
strPath = strPath & "\"
End If
strExtn = FileExtension(strFile)
If strExtn = "" Then
strExtn = ".csv"
strFile = strFile & strExtn
End If
OutputFile = strPath & strFile
End With
If FileName(OutputFile) <> "" Then
If Len(VBA.FileSystem.Dir(OutputFile, vbNormal)) <> 0 Then
Err.Clear
VBA.FileSystem.Kill OutputFile ' do it now, and reduce wait for deletion
If Err.Number = 70 Then ' permission denied: change the output file name
OutputFile = FileStripExtension(OutputFile) & "_" & FileStripExtension(FSO.GetTempName) & FileExtension(OutputFile)
End If
End If
End If
' ChrW$() gives a 2-byte 'Wide' char. This coerces all subsequent operations to UTF16
arrTemp3(0) = ChrW$(34) ' Encapsulating quote
arrTemp3(1) = vbNullString ' The field value will go here
arrTemp3(2) = ChrW$(34) ' Encapsulating quote
If rst.EOF And rst.BOF Then
FetchArray = Empty
ElseIf rst.EOF Then
rst.MoveFirst
End If
' An empty recordset must still write a header row of field names: we put this in the
' output buffer and write it to the file before we start looping through the records.
ReDim FetchArray(0 To rst.Fields.Count, 0 To 0)
i_LBound = 0
i_UBound = 0
If IsMissing(FieldList) Then
For j = LBound(FetchArray, 1) To UBound(FetchArray, 1) - 1 Step 1
FetchArray(j, i_UBound) = rst.Fields(j).Name
Next j
Else
j = 0
For Each varField In FieldList
j_UBound = j_UBound + 1
Next varField
ReDim arrTemp2(j_LBound To j_UBound)
For Each varField In FieldList
FetchArray(j, i_UBound) = CStr(varField)
j = j + 1
Next varField
End If
ReDim arrTemp1(i_LBound To i_UBound) ' arrTemp1 is the rowset we write to file
ReDim arrTemp2(j_LBound To j_UBound) ' arrTemp2 represents a single record
Do Until IsEmpty(FetchArray)
i_LBound = LBound(FetchArray, 2)
i_UBound = UBound(FetchArray, 2)
j_LBound = LBound(FetchArray, 1)
j_UBound = UBound(FetchArray, 1)
If UBound(arrTemp1) <> i_UBound + 1 Then
ReDim arrTemp1(i_LBound To i_UBound + 1)
arrTemp1(i_UBound + 1) = vbNullString ' The 'Join' operation will insert a trailing row
End If ' delimiter here (Not required by the last chunk)
If UBound(arrTemp2) <> j_UBound Then
ReDim arrTemp2(j_LBound To j_UBound)
End If
' Data body. This is heavily optimised to avoid VBA String functions with allocations
For i = i_LBound To i_UBound Step 1
' If this is confusing... Were you expecting FetchArray(i,j)? i for row, j for column?
' FetchArray comes from RecordSet.GetRows(), which returns a TRANSPOSED array: i and j
' are still the field and record ordinals, row(i) and column(j) in the output file.
For j = j_LBound To j_UBound
If IsNull(FetchArray(j, i)) Then
arrTemp2(j) = ""
Else
arrTemp2(j) = FetchArray(j, i) ' confused? see he note above
End If
If CleanupText Or (i_UBound = 0) Then ' (i_UBound=0): always clean up field names
arrBytes = arrTemp2(j) ' Integer arithmetic is faster than string-handling for
' this: all VBA string operations require an allocation
For k = LBound(arrBytes) To UBound(arrBytes) Step 2
Select Case arrBytes(k)
Case 10, 13, 9, 160
If arrBytes(k + 1) = 0 Then
arrBytes(k) = 32 ' replaces CR, LF, Tab, and non-breaking
End If ' spaces with the standard ANSI space
Case 44
If Not CoerceText Then
If arrBytes(k + 1) = 0 Then
arrBytes(k) = 32 ' replace comma with the ANSI space
End If
End If
Case 34
If arrBytes(k + 1) = 0 Then
arrBytes(k) = 39 ' replaces double-quote with single quote
End If
End Select
Next k
arrTemp2(j) = arrTemp2(j)
End If ' cleanup
If CoerceText Then ' encapsulate all fields in quotes, numeric or not
arrTemp3(1) = arrTemp2(j)
arrTemp2(j) = Join$(arrTemp3, vbNullString)
ElseIf (i = 0) And (i = i_UBound) Then ' always encapsulate field names
arrTemp3(1) = arrTemp2(j)
arrTemp2(j) = Join$(arrTemp3, vbNullString)
Else ' selective encapsulation, leaving numeric fields unencapsulated:
' we *could* do this by reading the ADODB field types: but that's
' slower, and you may be 'caught out' by provider-specific types.
arrBytes = arrTemp2(j)
boolNumeric = True
For k = LBound(arrBytes) To UBound(arrBytes) Step 2
If arrBytes(k) < 43 Or arrBytes(k) > 57 Then
If arrBytes(k) <> 69 Then
boolNumeric = False
Exit For
Else
If k > UBound(arrBytes) - 5 Then
boolNumeric = False
Exit For
ElseIf arrBytes(k + 2) = 45 Then
' detect "1.234E-05"
ElseIf arrBytes(k + 2) = 43 Then
' detect "1.234E+05"
Else
boolNumeric = False
Exit For
End If
End If
End If
Next k
If boolNumeric Then
For k = 1 + LBound(arrBytes) To UBound(arrBytes) Step 2
If arrBytes(k) <> 0 Then
boolNumeric = False
Exit For
End If
Next k
End If
arrBytes = vbNullString
If Not boolNumeric Then ' text field, encapsulate it
arrTemp3(1) = arrTemp2(j)
arrTemp2(j) = Join(arrTemp3, vbNullString)
End If
End If ' CoerceText
Next j
arrTemp1(i) = Join(arrTemp2, COMMA)
Next i
iRowCount = iRowCount + i - 2
' **** WHY WE 'PUT' A BYTE ARRAY INSTEAD OF A VBA STRING VARIABLE **** ****
'
' Put #hndFile, , StrConv(Join(arrTemp1, EOROW), vbUnicode)
' Put #hndFile, , Join(arrTemp1, EOROW)
'
' If you pass unicode, Wide or UTF-16 string variables to PUT, it prepends a
' Unicode Byte Order Mark to the data which, when written to your file, will
' render the field names illegible to Microsoft's JET ODBC and ACE-OLEDB SQL
' drivers (which can actually read unicode field names, if the helpful label
' isn't in the way). The primeval 'PUT' statement writes a Byte array as-is.
'
' **** **** **** **** **** **** **** **** **** **** **** **** **** **** ****
arrBytes = Join$(arrTemp1, vbCrLf)
If hndFile = 0 Then
i_Offset = 1
If Len(Dir(OutputFile)) > 0 Then
VBA.FileSystem.Kill OutputFile
End If
WaitForFileDeletion OutputFile
hndFile = FreeFile
Open OutputFile For Binary Access Write As #hndFile
End If
Put #hndFile, i_Offset, arrBytes
i_Offset = i_Offset + 1 + UBound(arrBytes)
Erase arrBytes
If rst.EOF Then
Erase FetchArray
FetchArray = Empty
Else
If IsMissing(FieldList) Then
FetchArray = rst.GetRows(FETCH_ROWS)
Else
FetchArray = rst.GetRows(FETCH_ROWS, , FieldList)
End If
End If
Loop ' until isempty(FetchArray)
If iRowCount < 1 Then '
iRowCount = 0 ' Row Count excludes the header
End If
RecordsetToCSV = iRowCount
ExitSub:
On Error Resume Next
If hndFile <> 0 Then
Close #hndFile
End If
Erase arrBytes
Erase arrTemp1
Erase arrTemp2
Exit Function
ErrSub:
Resume ExitSub
End Function
Public Function FilePath(Path As String) As String
' Strip the filename from a path, leaving only the path to the folder
' The last char of this path will be the backslash
' This does not check for the existence or accessibility of the file:
' all we're doing here is string-handling
Dim strPath As String
Dim arrPath() As String
Const BACKSLASH As String * 1 = "\"
strPath = Trim(Path)
If strPath = "" Then Exit Function
If Right$(strPath, 1) = BACKSLASH Then Exit Function
arrPath = Split(strPath, BACKSLASH)
If UBound(arrPath) = 0 Then ' does not contain "\"
FilePath = ""
Else
arrPath(UBound(arrPath)) = vbNullString
FilePath = Join$(arrPath, BACKSLASH)
End If
Erase arrPath
End Function
Public Function FileName(Path As String) As String
' Strip the folder and path from a file's path string, leaving only the file name
' This does not check for the existence or accessibility of the file:
' all we're doing here is string-handling
Dim strPath As String
Dim arrPath() As String
Const BACKSLASH As String * 1 = "\"
strPath = Trim(Path)
If strPath = "" Then Exit Function
If Right$(strPath, 1) = BACKSLASH Then Exit Function
arrPath = Split(strPath, BACKSLASH)
If UBound(arrPath) = 0 Then ' does not contain "\"
FileName = Path
Else
FileName = arrPath(UBound(arrPath))
End If
Erase arrPath
End Function
Public Function FileExtension(Path As String) As String
' Return the extension of the file
' This is just string-handling: no file or path validation is attempted
' The file extension is deemed to be whatever comes after the final '.'
' The extension is returned with the dot, eg: ".txt" not "txt"
' If no extension is detected, FileExtension returns an empty string
Dim strFile As String
Dim arrFile() As String
Const DOT_EXT As String * 1 = "."
strFile = FileName(Path)
strFile = Trim(strFile)
If strFile = "" Then Exit Function
If Right$(strFile, 1) = DOT_EXT Then Exit Function
arrFile = Split(strFile, DOT_EXT)
If UBound(arrFile) = 0 Then ' does not contain "\"
FileExtension = vbNullString
Else
FileExtension = arrFile(UBound(arrFile))
FileExtension = Trim(FileExtension)
If Len(FileExtension) > 0 Then
FileExtension = DOT_EXT & FileExtension
End If
End If
Erase arrFile
End Function
Public Function FileStripExtension(Path As String) As String
' Return the filename, with the extension removed
' This is just string-handling: no file validation is attempted
' The file extension is deemed to be whatever comes after the final '.'
' Both the dot and the extension are removed
Dim strFile As String
Dim arrFile() As String
Const DOT_EXT As String * 1 = "."
strFile = FileName(Path)
If strFile = "" Then Exit Function
If Right$(strFile, 1) = DOT_EXT Then Exit Function
strFile = Trim(strFile)
arrFile = Split(strFile, DOT_EXT)
If UBound(arrFile) = 0 Then ' does not contain "\"
FileStripExtension = vbNullString
Else
ReDim Preserve arrFile(LBound(arrFile) To UBound(arrFile) - 1)
FileStripExtension = Join$(arrFile, DOT_EXT)
End If
Erase arrFile
End Function
You'll also need the three path-and-file-name utility functions, if you don't have your own versions already:
FileName()
FilePath()
FileStripExtension()
There's room for improvement in the string-encapsulation logic: the correct approach is to look up the recordset's field types and apply quote marks accordingly, and it may well turn out to be faster than my clunky byte-counting.
However, my approach is all about the file consumers and what they expect to see; and that doesn't always line up with what they ought to accept.
If you succeed in coding a faster and more robust version do, please, let me know: if I'm asked to, I may well code up encapsulation by field type myself.
just thought I would toss in; macros offer this feature - and it is quite simple to set up;
select the export macro, select the query to export, select the format.... if you leave the destination selector blank it will launch the standard Windows file picker....
after a decade+ of coding in vba - macros have won me over for this particular function.....
I have a bunch of text files that I need to import into MS Access (thousands) - can use 2007 or 2010. The text files have categories that are identified in square brackets and have relevant data between the categories - for example:
[Location]Tenessee[Location][Model]042200[Model][PartNo]113342A69447B6[PartNo].
I need to capture both the categories and the data between them and import them into Access - the categories to one table, the data to another. There are hundreds of these categories in a single file and the text file has no structure - they are all run together as in the example above. The categories in the brackets are the only clear delimiters.
Through research on the web I have come up with a script for VBS (I am not locked into VBS, willing to use VBA or another method), but when I run it, I am getting a VBS info window with nothing displaying in it. Any advice or guidance would be most gratefully appreciated (I do not tend to use VBS and VBA) and I thank you.
The Script:
Const ForReading = 1
Set objFSO = CreateObject("Scripting.FileSystemObject")
Set objFile = objFSO.OpenTextFile("C:\Users\testGuy\Documents\dmc_db_test\DMC-TEST-A-00-00-00-00A-022A-D_000 - Copy01.txt", ForReading)
strContents = objFile.ReadAll
objFile.Close
Set objRegEx = CreateObject("VBScript.RegExp")
objRegEx.Global = True
objRegEx.Pattern = "\[.{0,}\]"
Set colMatches = objRegEx.Execute(strContents)
If colMatches.Count > 0 Then
For Each strMatch in colMatches
strMatches = strMatches & strMatch.Value
Next
End If
strMatches = Replace(strMatches, "]", vbCrlf)
strMatches = Replace(strMatches, "[", "")
Wscript.Echo strMatches
Regular expressions are wonderful things, but in your case it looks like they might be overkill. The following code uses plain old InStr() to find the [Tags] and parses the file(s) out to a single CSV file. That is, for input files
testfile1.txt:
[Location]Tennessee[Location][Model]042200[Model][PartNo]113342A69447B6[PartNo]
[Location]Mississippi[Location][Model]042200[Model][SerialNo]3212333222355[SerialNo]
and testfile2.txt:
[Location]Missouri[Location][Model]042200[Model][PartNo]AAABBBCCC111222333[PartNo]
...the code will write the following output file...
"FileName","LineNumber","ItemNumber","FieldName","FieldValue"
"testfile1.txt",1,1,"Location","Tennessee"
"testfile1.txt",1,2,"Model","042200"
"testfile1.txt",1,3,"PartNo","113342A69447B6"
"testfile1.txt",2,1,"Location","Mississippi"
"testfile1.txt",2,2,"Model","042200"
"testfile1.txt",2,3,"SerialNo","3212333222355"
"testfile2.txt",1,1,"Location","Missouri"
"testfile2.txt",1,2,"Model","042200"
"testfile2.txt",1,3,"PartNo","AAABBBCCC111222333"
...which you can then import into Access (or whatever) and proceed from there. This is VBA code, but it could easily be tweaked to run as a VBScript.
Sub ParseSomeFiles()
Const InFolder = "C:\__tmp\parse\in\"
Const OutFile = "C:\__tmp\parse\out.csv"
Dim fso As FileSystemObject, f As File, tsIn As TextStream, tsOut As TextStream
Dim s As String, Lines As Long, Items As Long, i As Long
Set fso = New FileSystemObject
Set tsOut = fso.CreateTextFile(OutFile, True)
tsOut.WriteLine """FileName"",""LineNumber"",""ItemNumber"",""FieldName"",""FieldValue"""
For Each f In fso.GetFolder(InFolder).Files
Debug.Print "Parsing """ & f.Name & """..."
Set tsIn = f.OpenAsTextStream(ForReading)
Lines = 0
Do While Not tsIn.AtEndOfStream
s = Trim(tsIn.ReadLine)
Lines = Lines + 1
Items = 0
Do While Len(s) > 0
Items = Items + 1
tsOut.Write """" & f.Name & """," & Lines & "," & Items
i = InStr(1, s, "]", vbBinaryCompare)
' write out FieldName
tsOut.Write ",""" & Replace(Mid(s, 2, i - 2), """", """""", 1, -1, vbBinaryCompare) & """"
s = Mid(s, i + 1)
i = InStr(1, s, "[", vbBinaryCompare)
' write out FieldValue
tsOut.Write ",""" & Replace(Mid(s, 1, i - 1), """", """""", 1, -1, vbBinaryCompare) & """"
s = Mid(s, i)
i = InStr(1, s, "]", vbBinaryCompare)
' (no need to write out ending FieldName tag)
s = Mid(s, i + 1)
tsOut.WriteLine
Loop
Loop
tsIn.Close
Set tsIn = Nothing
Next
Set f = Nothing
tsOut.Close
Set tsOut = Nothing
Set fso = Nothing
Debug.Print "Done."
End Sub