首页
学习
活动
专区
圈层
工具
发布
首页
学习
活动
专区
圈层
工具
MCP广场
社区首页 >问答首页 >Excel vba在单元格中提取前5位google搜索结果URL

Excel vba在单元格中提取前5位google搜索结果URL
EN

Stack Overflow用户
提问于 2018-06-22 15:43:42
回答 1查看 3.4K关注 0票数 0

我有下面的VBA代码,它可以很好地获得第一个结果URL,但我希望修改它以获得前5名的结果URL。

我试了好几个小时,却找不出该怎么办:

任何帮助都将不胜感激。

代码语言:javascript
运行
复制
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的专业知识,但在我的最后一次尝试中,我尝试这样做,并在所有结果中获得相同的链接。

代码语言:javascript
运行
复制
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
EN

回答 1

Stack Overflow用户

回答已采纳

发布于 2018-06-22 17:05:47

明白了。谢谢吉普把我引向正确的方向。

代码语言:javascript
运行
复制
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

票数 0
EN
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接:

https://stackoverflow.com/questions/50991463

复制
相关文章

相似问题

领券
问题归档专栏文章快讯文章归档关键词归档开发者手册归档开发者手册 Section 归档