Excel VBA在单元格中提取前5个Google搜索结果URL

时间:2018-06-22 15:43:42

标签: excel vba

我有下面的VBA代码,可以很好地获取第一个结果URL,但是我希望对其进行修改以获取前5个结果URL。

我正在尝试几个小时,但无法找出要做什么:(

任何帮助将不胜感激。

Sub XMLHTTP()

Dim URL As String, lastRow As Long
Dim XMLHTTP As Object, html As Object, objResultDiv As Object, objH3 As Object, link As Object
Dim start_time As Date
Dim end_time As Date

lastRow = Range("A" & Rows.Count).End(xlUp).Row

Dim cookie As String
Dim result_cookie As String

start_time = Time
Debug.Print "start_time:" & start_time

For i = 2 To lastRow

    URL = "https://www.google.co.in/search?q=" & Cells(i, 1) & "&rnd=" & WorksheetFunction.RandBetween(1, 10000)

    Set XMLHTTP = CreateObject("MSXML2.serverXMLHTTP")
    XMLHTTP.Open "GET", URL, False
    XMLHTTP.setRequestHeader "Content-Type", "text/xml"
    XMLHTTP.setRequestHeader "User-Agent", "Mozilla/5.0 (Windows NT 6.1; rv:25.0) Gecko/20100101 Firefox/25.0"
    XMLHTTP.send

        Set html = CreateObject("htmlfile")
    html.body.innerHTML = XMLHTTP.ResponseText
    Set objResultDiv = html.getelementbyid("rso")
    Set objH3 = objResultDiv.getElementsByTagName("H3")(0)
    Set link = objH3.getElementsByTagName("a")(0)

    str_text = Replace(link.innerHTML, "<EM>", "")
    str_text = Replace(str_text, "</EM>", "")
    Cells(i, 2) = str_text
    Cells(i, 3) = link.href
    DoEvents
Next

end_time = Time
Debug.Print "end_time:" & end_time

Debug.Print "done" & "Time taken : " & DateDiff("n", start_time, end_time)
MsgBox "done" & "Time taken : " & DateDiff("n", start_time, end_time)End Sub

我没有VBA专业知识,但是在上一次尝试中,我尝试这样做并在所有结果中获得相同的链接

Set objH3 = objResultDiv.getElementsByTagName("H3")(0)
    Set link = objH3.getElementsByTagName("a")(0)

    str_text = Replace(link.innerHTML, "<EM>", "")
    str_text = Replace(str_text, "</EM>", "")
    Cells(i, 2) = str_text
    Cells(i, 3) = link.href
    Set link2 = objH3.getElementsByTagName("a")(0)
    str_text = Replace(link2.innerHTML, "<EM>", "")
    Cells(i, 4) = link2.href
    Set link3 = objH3.getElementsByTagName("a")(0)
    str_text = Replace(link3.innerHTML, "<EM>", "")
    Cells(i, 5) = link3.href
    Set link4 = objH3.getElementsByTagName("a")(0)
    str_text = Replace(link4.innerHTML, "<EM>", "")
    Cells(i, 6) = link4.href

1 个答案:

答案 0 :(得分:0)

知道了。谢谢吉普(Jeeped)向我指出正确的方向。

Sub XMLHTTP()

Dim URL As String, lastRow As Long
Dim XMLHTTP As Object, html As Object, objResultDiv As Object, objH3 As Object, link As Object
Dim start_time As Date
Dim end_time As Date

lastRow = Range("A" & Rows.Count).End(xlUp).Row

Dim cookie As String
Dim result_cookie As String

start_time = Time
Debug.Print "start_time:" & start_time

For i = 2 To lastRow

    URL = "https://www.google.co.in/search?q=" & Cells(i, 1) & "&rnd=" & WorksheetFunction.RandBetween(1, 10000)

    Set XMLHTTP = CreateObject("MSXML2.serverXMLHTTP")
    XMLHTTP.Open "GET", URL, False
    XMLHTTP.setRequestHeader "Content-Type", "text/xml"
    XMLHTTP.setRequestHeader "User-Agent", "Mozilla/5.0 (Windows NT 6.1; rv:25.0) Gecko/20100101 Firefox/25.0"
    XMLHTTP.send

        Set html = CreateObject("htmlfile")
    html.body.innerHTML = XMLHTTP.ResponseText
    Set objResultDiv = html.getelementbyid("rso")
    Set objH3 = objResultDiv.getElementsByTagName("H3")(0)
    Set link = objH3.getElementsByTagName("a")(0)

    str_text = Replace(link.innerHTML, "<EM>", "")
    str_text = Replace(str_text, "</EM>", "")
    Cells(i, 2) = link.href
    Set objH3 = objResultDiv.getElementsByTagName("H3")(1)
    Set link = objH3.getElementsByTagName("a")(0)
    str_text = Replace(link.innerHTML, "<EM>", "")
    str_text = Replace(str_text, "</EM>", "")
    Cells(i, 3) = link.href
    Set objH3 = objResultDiv.getElementsByTagName("H3")(2)
    Set link = objH3.getElementsByTagName("a")(0)
    str_text = Replace(link.innerHTML, "<EM>", "")
    str_text = Replace(str_text, "</EM>", "")
    Cells(i, 4) = link.href
    Set objH3 = objResultDiv.getElementsByTagName("H3")(3)
    Set link = objH3.getElementsByTagName("a")(0)
    str_text = Replace(link.innerHTML, "<EM>", "")
    str_text = Replace(str_text, "</EM>", "")
    Cells(i, 5) = link.href
    Set objH3 = objResultDiv.getElementsByTagName("H3")(4)
    Set link = objH3.getElementsByTagName("a")(0)
    str_text = Replace(link.innerHTML, "<EM>", "")
    str_text = Replace(str_text, "</EM>", "")
    Cells(i, 6) = link.href
    
    DoEvents
Next

end_time = Time
Debug.Print "end_time:" & end_time

Debug.Print "done" & "Time taken : " & DateDiff("n", start_time, end_time)
MsgBox "done" & "Time taken : " & DateDiff("n", start_time, end_time)
End Sub

谢谢