vba,getElementsByClassName,HTMLSource的双引号没了

vba, getElementsByClassName, HTMLSource's double quotation marks are gone

我用 vba 抓取一些网站是为了好玩,我使用 VBA 作为工具。我使用 XMLHTTP 和 HTMLDocument(因为它比 internetExplorer.Application 更快)。

Public Sub XMLhtmlDocumentHTMLSourceScraper()

    Dim XMLHTTPReq As Object
    Dim htmlDoc As HTMLDocument

    Dim postURL As String

    postURL = "http://foodffs.tumblr.com/archive/2015/11"

        Set XMLHTTPReq = New MSXML2.XMLHTTP

        With XMLHTTPReq
            .Open "GET", postURL, False
            .Send
        End With

        Set htmlDoc = New HTMLDocument
        With htmlDoc
            .body.innerHTML = XMLHTTPReq.responseText
        End With

        i = 0

        Set varTemp = htmlDoc.getElementsByClassName("post_glass post_micro_glass")

        For Each vr In varTemp
            ''''the next line is important to solve this issue *1
            Cells(1, 1) = vr.outerHTML
            Set varTemp2 = vr.getElementsByTagName("SPAN class=post_date")
            Cells(i + 1, 3) = varTemp2.Item(0).innerText
            ''''the next line occur 438Error''''
            Set varTemp2 = vr.getElementsByClassName("hover_inner")
            Cells(i + 1, 4) = varTemp2.innerText

            i = i + 1

        Next vr
End Sub

我通过 *1 解决了这个问题 cells(1,1) 告诉我接下来的事情

<DIV class="post_glass post_micro_glass" title=""><A class=hover title="" href="http://foodffs.tumblr.com/post/134291668251/sugar-free-low-carb-coffee-ricotta-mousse-really" target=_blank>
<DIV class=hover_inner><SPAN class=post_date>...............

是的,所有 class 标签都丢失了“”。只有第一个函数的 class 有 " " 真不知道为什么会出现这种情况

//我可以通过 getElementsByTagName("span") 进行语法分析。但我更喜欢"class"标签.....

getElementsByClassName method本身不被认为是一个方法;只有父 HTMLDocument。如果您想使用它来定位 DIV 元素中的元素,您需要创建一个由该特定 DIV 元素的 .outerHtml 组成的子 HTMLDocument。

Public Sub XMLhtmlDocumentHTMLSourceScraper()

    Dim xmlHTTPReq As New MSXML2.XMLHTTP
    Dim htmlDOC As New HTMLDocument, divSUBDOC As New HTMLDocument
    Dim iDIV As Long, iSPN As Long, iEL As Long
    Dim postURL As String, nr As Long, i As Long

    postURL = "http://foodffs.tumblr.com/archive/2015/11"

    With xmlHTTPReq
        .Open "GET", postURL, False
        .Send
    End With

    'Set htmlDOC = New HTMLDocument
    With htmlDOC
        .body.innerHTML = xmlHTTPReq.responseText
    End With

    i = 0

    With htmlDOC
        For iDIV = 0 To .getElementsByClassName("post_glass post_micro_glass").Length - 1
            nr = Sheet1.Cells(Rows.Count, 3).End(xlUp).Offset(1, 0).Row
            With .getElementsByClassName("post_glass post_micro_glass")(iDIV)
                'method 1 - run through multiples in a collection
                For iSPN = 0 To .getElementsByTagName("span").Length - 1
                    With .getElementsByTagName("span")(iSPN)
                        Select Case LCase(.className)
                            Case "post_date"
                                Cells(nr, 3) = .innerText
                            Case "post_notes"
                                Cells(nr, 4) = .innerText
                            Case Else
                                'do nothing
                        End Select
                    End With
                Next iSPN
                'method 2 - create a sub-HTML doc to facilitate getting els by classname
                divSUBDOC.body.innerHTML = .outerHTML  'only the HTML from this DIV
                With divSUBDOC
                    If CBool(.getElementsByClassName("hover_inner").Length) Then 'there is at least 1
                        'use the first
                        Cells(nr, 5) = .getElementsByClassName("hover_inner")(0).innerText
                    End If
                End With
            End With
        Next iDIV
    End With

End Sub

虽然其他 .getElementsByXXXX 可以很容易地检索另一个元素中的集合,但 getElementsByClassName method 需要考虑它认为是整个 HTMLDocument 的内容,即使您愚弄它以为。

这是另一种方法。它与原始代码非常相似,但使用 querySelectorAll 来 select 相关的跨度元素。此方法的一个重点是必须将 vr 声明为特定元素类型,而不是 IHTMLElement 或通用对象:

Option Explicit

Public Sub XMLhtmlDocumentHTMLSourceScraper()

' Changed from generic Object to specific type - not
' strictly necessary to do this
Dim XMLHTTPReq As MSXML2.XMLHTTP60
Dim htmlDoc As HTMLDocument

' These declarations weren't included in the original code
Dim i As Integer
Dim varTemp As Object
' IMPORTANT: vr must be declared as a specific element type and not
' as an IHTMLElement or generic Object
Dim vr As HTMLDivElement
Dim varTemp2 As Object

Dim postURL As String

postURL = "http://foodffs.tumblr.com/archive/2015/11"

' Changed from XMLHTTP to XMLHTTP60 as XMLHTTP is equivalent
' to the older XMLHTTP30
Set XMLHTTPReq = New MSXML2.XMLHTTP60

With XMLHTTPReq
    .Open "GET", postURL, False
    .Send
End With

Set htmlDoc = New HTMLDocument
With htmlDoc
    .body.innerHTML = XMLHTTPReq.responseText
End With

i = 0

Set varTemp = htmlDoc.getElementsByClassName("post_glass post_micro_glass")

For Each vr In varTemp
   ''''the next line is important to solve this issue *1
   Cells(1, 1) = vr.outerHTML

   Set varTemp2 = vr.querySelectorAll("span.post_date")
   Cells(i + 1, 3) = varTemp2.Item(0).innerText

   Set varTemp2 = vr.getElementsByClassName("hover_inner")
   ' incorporating correction from Jeeped's comment (#56349646)
   Cells(i + 1, 4) = varTemp2.Item(0).innerText

   i = i + 1
Next vr

End Sub

备注:

  • XMLHTTP 等同于描述的 XMLHTTP30 here
  • 显然需要声明在 this question 中探索的特定元素类型,但是,与 getElementsByClassName 不同,querySelectorAll 在 IHTMLElement
  • 的任何版本中都不存在