【发布时间】:2014-04-30 22:46:40
【问题描述】:
我正在尝试让 Excel 从搜索引擎中检索数据 (torrentz.eu/search?q=abc)
应该是获取第一个链接的这个信息并在Excel上显示:
单元格 A1:我的查询
单元格 A2:链接标题
单元格 A3:网址
单元格 A4:链接日期。
似乎我不能使用getelementbyid,因为页面几乎不使用id标签。
到目前为止我所拥有的:
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 = "http://www.torrentz.eu/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.getElementBy????
Set objH3 = objResultDiv.getElementBytagname("d1")(0)
Set link = objH3.getelementsbytagname("/d1")(0)
str_text = Replace(link.innerHTML, "<dt>", "")
str_text = Replace(str_text, "</dt>", "")
Cells(i, 2) = str_text
Cells(i, 3) = link.href
Cells(i, 4) = link.date????
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
【问题讨论】: