【问题标题】:Excel vba extract top 5 google search results URL in cellExcel vba 在单元格中提取前 5 个谷歌搜索结果 URL
【发布时间】:2020-06-14 16:30:59
【问题描述】:

我有下面的 VBA 代码,它可以很好地获取第一个结果 URL,但我希望它修改以获得前 5 个结果 URL。

我尝试了几个小时,但不知道该怎么做:(

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,但在最后一次尝试中,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

【问题讨论】:

  • 所以你'尝试了几个小时'来编写一个循环,将 .getElementsByTagName("H3")(0) 中的 0 从 0 更改为 4?请edit您的问题包括您的最后一次尝试。
  • 我已经更新了请看一下

标签: excel vba


【解决方案1】:

知道了。感谢 Jeeped 为我指明了正确的方向。

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

谢谢你

【讨论】:

    猜你喜欢
    • 2011-05-21
    • 2015-11-26
    • 2011-07-18
    • 2012-10-19
    • 2019-04-10
    • 1970-01-01
    • 1970-01-01
    • 2012-04-10
    • 1970-01-01
    相关资源
    最近更新 更多