excel批量提取网页标题

最近时间比较忙，有时候很多网页需要临时保存，以便空闲的时候查看。单纯的保存网页链接会让人很枯燥，所以需要自动批量提取标题。

为了这个小功能去写个小程序有点不划算，所以就利用excel实现了这个功能。

先上图：

代码如下：

Option Explicit


Public Function GetTitle(url As String)
    Dim xmlHttp As Object
    Dim strHtml As String
    
    url = Trim(url)
    
    If LCase(Left(url, 5)) = "https" Then
    
        GetTitle = "暂不支持https协议"
        Exit Function
    End If
    
    
    '都不能构成完整的http协议，起码也得 a.cc
    If Len(url) < 5 Then
        Exit Function
    End If
    
    
    url = "http://" & Replace(Trim(url), "http://", "")
    
    Set xmlHttp = CreateObject("Microsoft.XMLHTTP")
    xmlHttp.Open "GET", url, True
    xmlHttp.send (Null)
    While xmlHttp.ReadyState <> 4
        DoEvents
    Wend
    strHtml = LCase(BytesToBstr(xmlHttp.responseBody))
    GetTitle = Split(Split(strHtml, "<title>")(1), "</title>")(0)
    Set xmlHttp = Nothing
End Function

Private Function BytesToBstr(Bytes)
    Dim Unicode As String
    If IsUTF8(Bytes) Then '如果不是UTF-8编码则按照GB2312来处理
        Unicode = "UTF-8"
    Else
        Unicode = "GB2312"
    End If

    Dim objstream As Object
    Set objstream = CreateObject("ADODB.Stream")
    With objstream
        .Type = 1
        .Mode = 3
        .Open
        .Write Bytes
        .Position = 0
        .Type = 2
        .Charset = Unicode
        BytesToBstr = .ReadText
       .Close
    End With
    Set objstream = Nothing
End Function

 '判断网页编码函数
Private Function IsUTF8(Bytes) As Boolean
        Dim i As Long, AscN As Long, Length As Long
        Length = UBound(Bytes) + 1
       
        If Length < 3 Then
            IsUTF8 = False
            Exit Function
        ElseIf Bytes(0) = &HEF And Bytes(1) = &HBB And Bytes(2) = &HBF Then
            IsUTF8 = True
            Exit Function
        End If

        Do While i <= Length - 1
            If Bytes(i) < 128 Then
                i = i + 1
                AscN = AscN + 1
            ElseIf (Bytes(i) And &HE0) = &HC0 And (Bytes(i + 1) And &HC0) = &H80 Then
                i = i + 2

            ElseIf i + 2 < Length Then
                If (Bytes(i) And &HF0) = &HE0 And (Bytes(i + 1) And &HC0) = &H80 And (Bytes(i + 2) And &HC0) = &H80 Then
                     i = i + 3
                Else
                    IsUTF8 = False
                    Exit Function
                End If
            Else
                IsUTF8 = False
                Exit Function
            End If
        Loop
               
        If AscN = Length Then
            IsUTF8 = False
        Else
            IsUTF8 = True
        End If

End Function

【说明】：因为目前保存的网页都是文章类型，所以就直接避免处理https安全连接了。

相关知识点：excel批量提取网页标题,excel自动提取网页标题,vb自动识别网页编码,vb字符串utf8转gbk