Question

我正在尝试让Excel从搜索引擎中检索数据（torrentz.eu/search?q=abc）

应该获取第一个链接的这些信息并将其显示在Excel上：

Cell A1：MyQuery

单元格A2：LinkTitle

单元格A3：网址

Cell A4：LinkDate。

似乎我无法使用getelementbyid，因为该页面几乎不使用id标记。

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

Answer 1

如果我理解你的后续行为，这应该会让你接近

    your code
    *
    *
    *
    Set html = CreateObject("htmlfile")
    html.body.innerHTML = XMLHTTP.ResponseText

    link_title = html.body.getElementsByTagName("dl")(3).getElementsByTagName("a")(0).innerhtml
    link_title = Replace(link_title, "<B>", "", 1, -1, vbTextCompare)
    link_title = Replace(link_title, "</B>", "", 1, -1, vbTextCompare)
    Debug.Print link_title

    link_url = html.body.getElementsByTagName("dl")(3).getElementsByTagName("a")(0).getAttribute("href")
    link_url = Replace(link_url, "about:", "http://torrentz.eu", 1, -1, vbTextCompare)
    Debug.Print link_url

    link_date = html.body.getElementsByTagName("dl")(3).getElementsByTagName("span")(1).innerhtml
    link_date = Replace(link_date, "<SPAN title=""", "", 1, -1, vbTextCompare)
    targ = InStr(1, link_date, """", vbTextCompare)
    link_date = Left(link_date, -1 + targ)
    Debug.Print link_date

    continue your code

如何使用XMLHTTP从网页获取信息

1 个答案: