如果您使用Excel VBA，请在参考菜单中为MSHTML库（标题为 Microsoft HTML对象库）设置引用（工具 - 引用））

  Sub ScrapeDateAbbr（）

 Dim hDoc As MSHTML.HTMLDocument 
 Dim hElem As MSHTML.HTMLGenericElement 
 Dim sFile As String，lFile As Long 
 Dim sHtml As String 

'在文件中读取
 lFile = FreeFile 
 sFile =C：/ Users / dick /文件/我的Dropbox / Excel / Testabbr.html
打开sFile输入为lFile 
 sHtml =输入$（LOF（lFile），lFile）

'放入htmldocument对象
设置hDoc =新的MSHTML.HTMLDocument 
 hDoc.body.innerHTML = sHtml 

'循环通过abbr标签
对于每个hElem在hDoc.getElementsByTagName（abbr）
'只有那些具有data-utime属性
如果Len（hElem。 getAttribute（data-utime））> 0然后
'获取标题属性
 Debug.Print hElem.getAttribute（title）
如果
结束hElem 

 End Sub 
 

我假定该文件是本地的，因为您调用了源文件。如果您需要先下载它，则需要另外参考MSXML和此代码

  Sub ScrapeDateAbbrDownload（）

 Dim xHttp As MSXML2.XMLHTTP 
 Dim hDoc As MSHTML.HTMLDocument 
 Dim hElem As MSHTML.HTMLGenericElement 

设置xHttp =新建MSXML2.XMLHTTP 
 xHttp.OpenGET，file：/// C：/Users/dick/Documents/My%20Dropbox/Excel/Testabbr.html
 xHttp.send 

 Do 
 DoEvents 
循环直到xHttp.readyState = 4 

'放入一个htmldocument对象
设置hDoc =新的MSHTML.HTMLDocument 
 hDoc.body.innerHTML = xHttp .responseText 

'循环通过abbr标签
对于每个hElem在hDoc.getElementsByTagName（abbr）
'只有那些具有data-utime属性
如果Len（hElem.getAttribute（data-utime））> 0然后
'获取标题属性
 Debug.Print hElem.getAttribute（title）
如果
结束hElem 

 End Sub 
 

I have a file that I want to extract dates from, it's a HTML source file so it's full of code and phrases I don't need. I need to extract every instance of a date that's wrapped in a specific HTML tag:

abbr title="((this is the text I need))" data-utime="

What's the easiest way to achieve this?

If you're using Excel VBA, set a reference (Tools - References) to the MSHTML library (entitled Microsoft HTML Object Library in the reference menu)

Sub ScrapeDateAbbr()

    Dim hDoc As MSHTML.HTMLDocument
    Dim hElem As MSHTML.HTMLGenericElement
    Dim sFile As String, lFile As Long
    Dim sHtml As String

    'read in the file
    lFile = FreeFile
    sFile = "C:/Users/dick/Documents/My Dropbox/Excel/Testabbr.html"
    Open sFile For Input As lFile
    sHtml = Input$(LOF(lFile), lFile)

    'put into an htmldocument object
    Set hDoc = New MSHTML.HTMLDocument
    hDoc.body.innerHTML = sHtml

    'loop through abbr tags
    For Each hElem In hDoc.getElementsByTagName("abbr")
        'only those that have a data-utime attribute
        If Len(hElem.getAttribute("data-utime")) > 0 Then
            'get the title attribute
            Debug.Print hElem.getAttribute("title")
        End If
    Next hElem

End Sub

I assumed the file was local since you called in a source file. If you need to download it first, you'd need another reference to MSXML and this code

Sub ScrapeDateAbbrDownload()

    Dim xHttp As MSXML2.XMLHTTP
    Dim hDoc As MSHTML.HTMLDocument
    Dim hElem As MSHTML.HTMLGenericElement

    Set xHttp = New MSXML2.XMLHTTP
    xHttp.Open "GET", "file:///C:/Users/dick/Documents/My%20Dropbox/Excel/Testabbr.html"
    xHttp.send

    Do
        DoEvents
    Loop Until xHttp.readyState = 4

    'put into an htmldocument object
    Set hDoc = New MSHTML.HTMLDocument
    hDoc.body.innerHTML = xHttp.responseText

    'loop through abbr tags
    For Each hElem In hDoc.getElementsByTagName("abbr")
        'only those that have a data-utime attribute
        If Len(hElem.getAttribute("data-utime")) > 0 Then
            'get the title attribute
            Debug.Print hElem.getAttribute("title")
        End If
    Next hElem

End Sub