Конвертировать HTML-таблицу в Excel с помощью VBA

Чтобы получить табличные данные (сохраняя формат, как есть) с этой страницы, вы можете попробовать, как показано ниже:

 Sub Fetch_Data()
    Dim http As New XMLHTTP60, html As New HTMLDocument
    Dim posts As Object, post As Object, elem As Object
    Dim row As Long, col As Long

    With http
        .Open "GET", "https://rasmusrhl.github.io/stuff/", False
        .send
        html.body.innerHTML = .responseText
    End With

    Set posts = html.getElementsByClassName("gmisc_table")(0)

    For Each post In posts.Rows
        For Each elem In post.Cells
            col = col + 1: Cells(row + 1, col).NumberFormat = "@": Cells(row + 1, col) = elem.innerText
        Next elem
        col = 0
        row = row + 1
    Next post
End Sub

Ссылка на добавление в библиотеку:

1. Microsoft HTML Object Library
2. Microsoft XML, v6.0  'or whatever version you have

Вот как выглядит эта часть при анализе.

<style type=text/css>
    td {mso-number-format: '\@';}
</style>
<table ...

Полагая вышеописанное определение глобального стиля для ячеек (<td> s) на выходе, который вы генерируете с использованием R, или переписывании документа на стороне клиента, как показано ниже, просто работает.

Sub importhtml()
    '*********** HTML document rewrite process ***************
    Const TableUrl = "https://rasmusrhl.github.io/stuff"

    Const adTypeBinary = 1, adSaveCreateOverWrite = 2, TemporaryFolder = 2
    Dim tempFilePath, binData() As Byte

    With CreateObject("Scripting.FileSystemObject")
        tempFilePath = .BuildPath(.GetSpecialFolder(TemporaryFolder), .GetTempName() & ".html")
    End With

    'download HTML document
    With CreateObject("MSXML2.ServerXMLHTTP")
        .Open "GET", TableUrl, False
        .Send
        If .Status <> 200 Then Err.Raise 3, "importhtml", "200 expected"
        binData = .ResponseBody
    End With

    With CreateObject("Adodb.Stream")
        .Charset = "x-ansi"
        .Open
        .WriteText "<style type=text/css>td {mso-number-format:'\@';}</style>"
        .Position = 0 'move to start
        .Type = adTypeBinary 'change stream type
        .Position = .Size 'move to end
        .Write binData 'append binary data end of stream
        .SaveToFile tempFilePath, adSaveCreateOverWrite 'save temporary file
        .Close
    End With
    '*********** HTML document rewrite process ***************

    With ActiveSheet.QueryTables.Add(Connection:= _
        "URL;" & tempFilePath, Destination:=Range("$A$1"))
        'load HTML document from rewritten local copy

        .Name = "stuff"
        .FieldNames = True
        .RowNumbers = False
        .FillAdjacentFormulas = False
        .PreserveFormatting = False
        .RefreshOnFileOpen = False
        .BackgroundQuery = True
        .RefreshStyle = xlInsertDeleteCells
        .SavePassword = False
        .SaveData = True
        .AdjustColumnWidth = True
        .RefreshPeriod = 0
        .WebSelectionType = xlEntirePage
        .WebFormatting = xlWebFormattingAll
        .WebPreFormattedTextToColumns = True
        .WebConsecutiveDelimitersAsOne = True
        .WebSingleBlockTextImport = False
        .WebDisableDateRecognition = True
        .WebDisableRedirections = False
        .Refresh BackgroundQuery:=False

    End With

    Kill tempFilePath
End Sub

Вы можете попробовать попробовать, если вы получите желаемый результат...

Sub GetWebData()
Dim IE As Object
Dim doc As Object
Dim TRs As Object
Dim TR As Object
Dim Cell As Object
Dim r As Long, c As Long

Application.ScreenUpdating = False

Set IE = CreateObject("InternetExplorer.Application")
IE.Visible = False
IE.navigate "https://rasmusrhl.github.io/stuff/"
Do While IE.Busy Or IE.readyState <> 4
    DoEvents
Loop
Set doc = IE.document

Set TRs = doc.getElementsByTagName("tr")
Cells.Clear

For Each TR In TRs
    r = r + 1
    For Each Cell In TR.Children
        c = c + 1
        Cells(r, c).NumberFormat = "@"
        Cells(r, c) = Cell.innerText
    Next Cell
    c = 0
Next TR
IE.Quit
Columns.AutoFit
Application.ScreenUpdating = True
End Sub

Решение 2:

Чтобы заставить его работать, вам нужно добавить следующие две ссылки, перейдя в Инструменты (в редакторе VBA) → Ссылки, а затем найдите приведенные ниже ссылки и установите флажки для них и нажмите "ОК".

1) Microsoft XML, v6.0 (найти доступную максимальную версию)

2) Библиотека объектов Microsoft HTML

Sub GetWebData2()
Dim XMLpage As New MSXML2.XMLHTTP60
Dim doc As New MSHTML.HTMLDocument
Dim TRs As IHTMLElementCollection
Dim TR As IHTMLElement
Dim Cell As IHTMLElement
Dim r As Long, c As Long

Application.ScreenUpdating = False

Set XMLpage = CreateObject("MSXML2.XMLHTTP")

XMLpage.Open "GET", "https://rasmusrhl.github.io/stuff/", False
XMLpage.send
doc.body.innerhtml = XMLpage.responsetext
Set TRs = doc.getElementsByTagName("tr")
Set TRs = doc.getElementsByTagName("tr")
Cells.Clear

For Each TR In TRs
    r = r + 1
    For Each Cell In TR.Children
        c = c + 1
        Cells(r, c).NumberFormat = "@"
        Cells(r, c) = Cell.innerText
    Next Cell
    c = 0
Next TR
Columns.AutoFit
Application.ScreenUpdating = True
End Sub

Это работает с временным файлом.

Что он делает: загрузка данных локально. Затем он заменяет "(" на "\", а затем импортирует данные. Форматирует данные как текст (чтобы мы могли изменить его без ошибок). Затем изменяется текст. Этого нельзя сделать с помощью Range.Replace потому что это переформатирует содержимое ячейки.

' Local Variables
Public FileName As String ' Temp File Path
Public FileUrl As String ' Url Formatted Temp File Path
Public DownloadUrl As String ' Where We're Going to Download From

' Declares Have to Be At Top
Private Declare Function GetTempPath Lib "kernel32" _
  Alias "GetTempPathA" _
  (ByVal nBufferLength As Long, _
  ByVal lpBuffer As String) As Long
Private Declare Function GetTempFileName Lib "kernel32" _
  Alias "GetTempFileNameA" _
  (ByVal lpszPath As String, _
  ByVal lpPrefixString As String, _
  ByVal wUnique As Long, _
  ByVal lpTempFileName As String) As Long

' Loads the HTML Content Without Bug
Sub ImportHtml()

    ' Set Our Download URL
    DownloadUrl = "https://rasmusrhl.github.io/stuff"

    ' Sets the Temporary File Path
    SetFilePath

    ' Downloads the File
    DownloadFile

    ' Replaces the "(" in the File With "\(", We Will Later Put it Back
    ' This Ensures Formatting of Content Isn't Modified!!!
    ReplaceStringInFile


    ' Our Query Table is Now Coming From the Local File, Instead
    Dim s As QueryTable
    Set s = ActiveSheet.QueryTables.Add(Connection:=("FINDER;file://" + FileUrl), Destination:=Range("$A$1"))

    With s

        .Name = "stuff"
        .FieldNames = True
        .RowNumbers = False
        .FillAdjacentFormulas = False
        .PreserveFormatting = False
        .RefreshOnFileOpen = False
        .BackgroundQuery = True
        .RefreshStyle = xlInsertDeleteCells
        .SavePassword = False
        .SaveData = True
        .AdjustColumnWidth = True
        .RefreshPeriod = 0
        .WebSelectionType = xlEntirePage
        .WebFormatting = xlWebFormattingAll
        .WebPreFormattedTextToColumns = True
        .WebConsecutiveDelimitersAsOne = True
        .WebSingleBlockTextImport = False
        .WebDisableDateRecognition = True
        .WebDisableRedirections = False
        .Refresh BackgroundQuery:=False

        ' Sets Formatting So When We Change Text the Data Doesn't Change
        .ResultRange.NumberFormat = "@"

        ' Loop Through Cells in Range
        ' If You Do Excel Replace, Instead It Will Change Cell Format
        Const myStr As String = "\(", myReplace As String = "("
        For Each c In .ResultRange.Cells
            Do While c.Value Like "*" & myStr & "*"
                c.Characters(InStr(1, c.Value, myStr), Len(myStr)).Text = myReplace
            Loop
        Next


    End With
End Sub

' This function replaces the "(" in the file with "\("
Sub ReplaceStringInFile()

    Dim sBuf As String
    Dim sTemp As String
    Dim iFileNum As Integer
    Dim sFileName As String

    ' Edit as needed
    sFileName = FileName

    iFileNum = FreeFile
    Open sFileName For Input As iFileNum

    Do Until EOF(iFileNum)
        Line Input #iFileNum, sBuf
        sTemp = sTemp & sBuf & vbCrLf
    Loop
    Close iFileNum

    sTemp = Replace(sTemp, "(", "\(")

    iFileNum = FreeFile
    Open sFileName For Output As iFileNum
    Print #iFileNum, sTemp
    Close iFileNum

End Sub

' This function sets file paths because we need a temp file
Function SetFilePath()

    If FileName = "" Then
        FileName = GetTempHtmlName
        FileUrl = Replace(FileName, "\", "/")
    End If

End Function

' This subroutine downloads the file from the specified URL
' The download is necessary because we will be editing the file
Sub DownloadFile()

    Dim myURL As String
    myURL = "https://rasmusrhl.github.io/stuff"

    Dim WinHttpReq As Object
    Set WinHttpReq = CreateObject("Microsoft.XMLHTTP")
    WinHttpReq.Open "GET", DownloadUrl, False, "username", "password"
    WinHttpReq.send

    myURL = WinHttpReq.responseBody
    If WinHttpReq.Status = 200 Then
        Set oStream = CreateObject("ADODB.Stream")
        oStream.Open
        oStream.Type = 1
        oStream.Write WinHttpReq.responseBody
        oStream.SaveToFile FileName, 2 ' 1 = no overwrite, 2 = overwrite
        oStream.Close
    End If

End Sub

'''''''''''''''''''''''''''''
' THIS BLOCK OF CODE GETS A TEMPORARY FILE PATH USING THE GetTempHtmlName Function
'''''''''''''''''''''''''''''


Public Function GetTempHtmlName( _
  Optional sPrefix As String = "VBA", _
  Optional sExtensao As String = "") As String
  Dim sTmpPath As String * 512
  Dim sTmpName As String * 576
  Dim nRet As Long
  Dim F As String
  nRet = GetTempPath(512, sTmpPath)
  If (nRet > 0 And nRet < 512) Then
    nRet = GetTempFileName(sTmpPath, sPrefix, 0, sTmpName)
    If nRet <> 0 Then F = Left$(sTmpName, InStr(sTmpName, vbNullChar) - 1)
    If sExtensao > "" Then
      Kill F
      If Right(F, 4) = ".tmp" Then F = Left(F, Len(F) - 4)
      F = F & sExtensao
    End If
    F = Replace(F, ".tmp", ".html")
    GetTempHtmlName = F
  End If
End Function

'''''''''''''''''''''''''''''
' End - GetTempHtmlName
'''''''''''''''''''''''''''''

Обработка HTML, а затем копирование и вставка в Excel

Вот шаги, которые я использовал:

• CreateObject("MSXML2.XMLHTTP"): получить URL responseText
• CreateObject("HTMLFile"): создать HTML-документ из responseText
• Заменить серый цвет черным, чтобы затемнить границы
• Префиксные столбцы s1 и s2 с @ для сохранения форматирования
• Скопируйте HTML в буфер обмена Windows
  • Примечание. HTML должен быть заключен в теги HTML и Body для правильной вставки
• Настройка рабочего листа назначения
• Вставьте HTML-код в рабочий лист
• Замените знак @ на '
  • Примечание. Это сохраняет форматирование, сохраняя данные как текст.
• Завершить форматирование рабочего листа

Sub LoadTable()
    Const URL = "https://rasmusrhl.github.io/stuff/"
    Dim x As Long
    Dim doc As Object, tbl As Object, rw As Object
    With CreateObject("MSXML2.XMLHTTP")
        .Open "GET", URL, False
        .send
        If .readyState = 4 And .Status = 200 Then
            Set doc = CreateObject("HTMLFile")
            doc.body.innerHTML = .responseText
            doc.body.innerHTML = Replace(doc.body.innerHTML, "grey", "black")
            Set tbl = doc.getElementsByTagName("TABLE")(0)

            For x = 0 To tbl.Rows.Length - 1
                Set rw = tbl.Rows(x)

                If rw.Cells.Length = 14 Then
                    'If InStr(rw.Cells(12).innerText, "-") Or InStr(rw.Cells(12).innerText, "/") Then
                    rw.Cells(12).innerText = "@" & rw.Cells(12).innerText
                    rw.Cells(13).innerText = "@" & rw.Cells(13).innerText
                End If
            Next

            With CreateObject("new:{1C3B4210-F441-11CE-B9EA-00AA006B1A69}")
                .SetText "<html><body>" & doc.body.innerHTML & "</body></html>"
                .PutInClipboard
            End With

            With Worksheets("Sheet1")
                .Cells.Clear
                .Range("A1").PasteSpecial
                .Cells.Interior.Color = vbWhite
                .Cells.WrapText = False
                .Columns.AutoFit
                .Columns("M:N").Replace What:="@", Replacement:="'"
            End With

        Else
            MsgBox "URL:  " & vbCrLf & "Ready state: " & .readyState & vbCrLf & "HTTP request status: " & .Status, vbInformation, "URL Not Responding"
        End If
    End With
End Sub

Попробуйте это, чтобы импортировать данные в виде таблицы:

Sub ImportDataAsTable()
    ActiveWorkbook.Queries.Add Name:="Table 0", Formula:= _
        "let" & Chr(13) & "" & Chr(10) & "    Source = Web.Page(Web.Contents(""https://rasmusrhl.github.io/stuff/""))," & Chr(13) & "" & Chr(10) & "    Data0 = Source{0}[Data]," & Chr(13) & "" & Chr(10) & "    #""Changed Type"" = Table.TransformColumnTypes(Data0,{{""tailnum"", type text}, {"""", type text}, {""Some text goes here. It is long and does not break Machine type (make) year"", type text}, {""Some text goes here. It is long and does not break Mach" & _
        "ine type (make) type"", type text}, {""Some text goes here. It is long and does not break Machine type (make) manufacturer"", type text}, {""Some text goes here. It is long and does not break"", type text}, {""Some text goes here. It is long and does not break Specification of machine model"", type text}, {""Some text goes here. It is long and does not break Specifi" & _
        "cation of machine engines"", type text}, {""Some text goes here. It is long and does not break Specification of machine seats"", type text}, {""Some text goes here. It is long and does not break Specification of machine speed"", type text}, {""Some text goes here. It is long and does not break Specification of machine engine"", type text}, {""2"", type text}, {""Oth" & _
        "er text goes here Other variables s1"", type text}, {""Other text goes here Other variables s2"", type text}})" & Chr(13) & "" & Chr(10) & "in" & Chr(13) & "" & Chr(10) & "    #""Changed Type"""
    ActiveWorkbook.Worksheets.Add
    With ActiveSheet.ListObjects.Add(SourceType:=0, Source:= _
        "OLEDB;Provider=Microsoft.Mashup.OleDb.1;Data Source=$Workbook$;Location=""Table 0"";Extended Properties=""""" _
        , Destination:=Range("$A$1")).QueryTable
        .CommandType = xlCmdSql
        .CommandText = Array("SELECT * FROM [Table 0]")
        .RowNumbers = False
        .FillAdjacentFormulas = False
        .PreserveFormatting = True
        .RefreshOnFileOpen = False
        .BackgroundQuery = True
        .RefreshStyle = xlInsertDeleteCells
        .SavePassword = False
        .SaveData = True
        .AdjustColumnWidth = True
        .RefreshPeriod = 0
        .PreserveColumnInfo = True
        .ListObject.DisplayName = "Table_0"
        .Refresh BackgroundQuery:=False
    End With
End Sub

На основе документации из Microsoft MSDN Library: свойство WebFormatting вы можете попробовать изменить ниже код:

 .WebFormatting = xlWebFormattingNone

Это может позволить копировать данные без форматирования чисел - тогда вы можете установить свой собственный формат номера для этих ячеек (используя свойство MSDN: Excel VBA NumberFormat)

Аналогичное решение должно решить проблему с усечением или округлением чисел - установите десятичные точки для затронутых ячеек в вашем целевом диапазоне...

С URL-адресом https://rasmusrhl.github.io/stuff, по счастью, Excel может просто просто открыть его напрямую и сохранить как.xlsx (почему никто не пробовал это до утомительного процесса). Если прямой открытый сбой, все остальные методы здесь являются отличным вариантом!

Option Explicit

Sub OpenWebFile()
    Const URL As String = "https://rasmusrhl.github.io/stuff"
    Dim oWB As Workbook
    On Error Resume Next
    Set oWB = Workbooks.Open(Filename:=URL, ReadOnly:=True)
    If oWB Is Nothing Then
        MsgBox "Cannot open the url " & URL, vbExclamation + vbOKOnly, "ERR " & Err.Number & ":" & Err.Description
        Err.Clear
    Else
        ' Change to your desired path and filename
        oWB.SaveAs Filename:="C:\Test\stuff.xlsx", FileFormat:=xlOpenXMLWorkbook
        Set oWB = Nothing
    End If
End Sub