簡體   English   中英

使用XMLHTTP使用vba進行Web抓取

[英]web scraping with vba using XMLHTTP

我想從網頁http://www.eex.com/en/market-data/power/derivatives-market/phelix-futures獲取一些數據。

如果我使用舊的InternetExplorer對象(下面的代碼),我可以瀏覽HTML文檔。 但我想使用XMLHTTP對象(第二個代碼)。

Sub IEZagon() 
     'we define the essential variables
    Dim ie As Object 
    Dim TDelement, TDelements 
    Dim AnhorLink, AnhorLinks 

     'add the "Microsoft Internet Controls" reference in your VBA Project indirectly
    Set ie = CreateObject("InternetExplorer.Application") 
    With ie 
        .Visible = True 
        .navigate ("[URL]http://www.eex.com/en/market-data/power/derivatives-market/phelix-futures[/URL]") 
        While ie.ReadyState <> 4 
            DoEvents 
        Wend 
        Set AnhorLinks = .document.getElementsbytagname("a") 
        Set TDelements = .document.getElementsbytagname("td") 
        For Each AnhorLink In AnhorLinks 
            Debug.Print AnhorLink.innertext 
        Next 
        For Each TDelement In TDelements 
            Debug.Print TDelement.innertext 
        Next 
    End With 
    Set ie = Nothing 
End Sub

使用XMLHTTP對象的代碼:

Sub FuturesScrap(ByVal URL As String) 
    Dim XMLHttpRequest As XMLHTTP 
    Dim HTMLDoc As New HTMLDocument 

    Set XMLHttpRequest = New MSXML2.XMLHTTP 
    XMLHttpRequest.Open "GET", URL, False 
    XMLHttpRequest.send 
    While XMLHttpRequest.readyState <> 4 
        DoEvents 
    Wend 

    Debug.Print XMLHttpRequest.responseText 
    HTMLDoc.body.innerHTML = XMLHttpRequest.responseText 

    With HTMLDoc.body 
        Set AnchorLinks = .getElementsByTagName("a") 
        Set TDelements = .getElementsByTagName("td") 

        For Each AnchorLink In AnchorLinks 
            Debug.Print AnhorLink.innerText 
        Next 

        For Each TDelement In TDelements 
            Debug.Print TDelement.innerText 
        Next 
    End With 
End Sub 

我只得到基本的HTML:

<html> 
<head> 
<title>Resource Not found</title> 
<link rel= 'stylesheet' type='text/css' href='/blueprint/css/errorpage.css'/>
</head> 
<body> 
<table class="header"> 
<tr> 
<td class="CMTitle CMHFill"><span class="large">Resource Not found</span></td> 
</tr> 
</table> 
<div class="body"> 
<p style="font-weight:bold;">The requested resource does Not exist.</p> 
</div> 
<table class="footer"> 
<tr> 
<td class="CMHFill"> </td> 
</tr> 
</table> 
</body> 
</html>

我想瀏覽表格和相應的數據......最后我想選擇年份到月份的不同時間間隔:

我真的很感激任何幫助! 謝謝!

我可以確認在運行代碼時(無論是否包含url標記),我都會獲得與您相同的HTML。 我在這里發現了一個有用的帖子 我已經使用在那里找到的方法修改了你的代碼,它現在似乎已經下載了正確的信息。

Sub test()
    Call FuturesScrap1("http://www.eex.com/en/market-data/power/derivatives-market/phelix-futures")
End Sub

我包含了調用sub,因為url標記似乎導致MSXML請求出錯。

Sub FuturesScrap1(ByVal URL As String)
    Dim HTMLDoc As New HTMLDocument
    Dim oHttp As MSXML2.XMLHTTP
    Dim sHTML As String
    Dim AnchorLinks As Object
    Dim TDelements As Object
    Dim TDelement As Object
    Dim AnchorLink As Object

    On Error Resume Next
    Set oHttp = New MSXML2.XMLHTTP
    If Err.Number <> 0 Then
        Set oHttp = CreateObject("MSXML.XMLHTTPRequest")
        MsgBox "Error 0 has occured while creating a MSXML.XMLHTTPRequest object"
    End If
    On Error GoTo 0
    If oHttp Is Nothing Then
        MsgBox "For some reason I wasn't able to make a MSXML2.XMLHTTP object"
        Exit Sub
    End If

    'Open the URL in browser object
    oHttp.Open "GET", URL, False
    oHttp.send
    sHTML = oHttp.responseText

    Debug.Print oHttp.responseText

    HTMLDoc.body.innerHTML = oHttp.responseText

    With HTMLDoc.body
        Set AnchorLinks = .getElementsByTagName("a")
        Set TDelements = .getElementsByTagName("td")

        For Each AnchorLink In AnchorLinks
            Debug.Print AnchorLink.innerText
        Next

        For Each TDelement In TDelements
            Debug.Print TDelement.innerText
        Next
    End With

End Sub

編輯以下評論:

我無法使用MSXML2對象找到表元素,源代碼似乎不包含它們。 在firebug中存在td標記,因此我認為該表是由JavaScript代碼生成的。 我不知道MSXML2是否可以運行JavaScript所以我修改了sub以使用Internet Explorer,它不是快速代碼,但它確實找到了td元素並允許單擊選項卡。 我發現td元素可能需要一些時間才能使用(可能是因為IE必須運行JavaScript)所以我在下載數據之前已經進行了幾個步驟xl等待。

我已經添加了一些將td元素的內容下載到活動工作表中的代碼,如果在包含有用數據的工作簿中運行它,請小心。

Sub FuturesScrap3(ByVal URL As String)

    Dim HTMLDoc As New HTMLDocument
    Dim AnchorLinks As Object
    Dim tdElements As Object
    Dim tdElement As Object
    Dim AnchorLink As Object
    Dim lRow As Long
    Dim oElement As Object

    Dim oIE As InternetExplorer

    Set oIE = New InternetExplorer

    oIE.navigate URL
    oIE.Visible = True

    Do Until (oIE.readyState = 4 And Not oIE.Busy)
        DoEvents
    Loop

    'Wait for Javascript to run
    Application.Wait (Now + TimeValue("0:01:00"))

    HTMLDoc.body.innerHTML = oIE.document.body.innerHTML

    With HTMLDoc.body
        Set AnchorLinks = .getElementsByTagName("a")
        Set tdElements = .getElementsByTagName("td") '

        For Each AnchorLink In AnchorLinks
            Debug.Print AnchorLink.innerText
        Next AnchorLink

    End With

    lRow = 1
    For Each tdElement In tdElements
        Debug.Print tdElement.innerText
        Cells(lRow, 1).Value = tdElement.innerText
        lRow = lRow + 1
    Next

    'Clicking the Month tab
    For Each oElement In oIE.document.all
        If Trim(oElement.innerText) = "Month" Then
            oElement.Focus
            oElement.Click
        End If
    Next oElement

    Do Until (oIE.readyState = 4 And Not oIE.Busy)
        DoEvents
    Loop

    'Wait for Javascript to run
    Application.Wait (Now + TimeValue("0:01:00"))

    HTMLDoc.body.innerHTML = oIE.document.body.innerHTML

    With HTMLDoc.body
        Set AnchorLinks = .getElementsByTagName("a")
        Set tdElements = .getElementsByTagName("td") '

        For Each AnchorLink In AnchorLinks
            Debug.Print AnchorLink.innerText
        Next AnchorLink
    End With

    lRow = 1
    For Each tdElement In tdElements
        Debug.Print tdElement.innerText
        Cells(lRow, 2).Value = tdElement.innerText
        lRow = lRow + 1
    Next tdElement

End sub

暫無
暫無

聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.

 
粵ICP備18138465號  © 2020-2024 STACKOOM.COM