Как я могу получить фрагменты результатов поиска Google на первой странице в Excel с помощью VBA

У меня есть список из 1000 ключевых слов в A1:A1000. Я хочу получить фрагменты результатов поиска Google на первой странице в соответствующих ячейках каждого ключевого слова. Пример: фрагменты результатов поиска из A1 ячейки должны находиться в B1...*1 и так далее. Буду признателен за любую оказанную помощь.


person sharathchandramandadi    schedule 04.03.2016    source источник
comment
Это всего 999 ключевых слов, а не 1000.   -  person    schedule 04.03.2016


Ответы (1)


Рассмотрим приведенный ниже пример:

Option Explicit
Const TargetItemsQty = 30 ' results for each keyword

Sub GWebSearchIECtl()

    Dim objSheet As Worksheet
    Dim objIE As Object
    Dim x As Long
    Dim y As Long
    Dim strSearch As String
    Dim lngFound As Long
    Dim st As String
    Dim colGItems As Object
    Dim varGItem As Variant
    Dim strHLink As String
    Dim strDescr As String
    Dim strNextURL As String

    Set objSheet = Sheets("Sheet1")
    Set objIE = CreateObject("InternetExplorer.Application")
    objIE.Visible = True ' for debug or captcha request cases
    y = 1 ' start searching for the keyword in the first row
    With objSheet
        .Select
        .Range(.Columns("B:B"), .Columns("B:B").End(xlToRight)).Delete ' clear previous results
        .Range("A1").Select
        Do Until .Cells(y, 1) = ""
            x = 2 ' start writing results from column B
            .Cells(y, 1).Select
            strSearch = .Cells(y, 1) ' current keyword
            With objIE
                lngFound = 0
                .Navigate "https://www.google.com/search?q=" & EncodeUriComponent(strSearch) ' go to first search results page
                Do
                    Do While .Busy Or Not .readyState = 4: DoEvents: Loop ' wait IE
                    Do Until .document.readyState = "complete": DoEvents: Loop ' wait document
                    Do While TypeName(.document.getElementById("res")) = "Null": DoEvents: Loop ' wait [#res] element
                    Set colGItems = .document.getElementById("res").getElementsByClassName("g") ' collection of search result [.g] items
                    For Each varGItem In colGItems ' process each item in collection
                        If varGItem.getElementsByTagName("a").Length > 0 And varGItem.getElementsByClassName("st").Length > 0 Then ' must have hyperlink and description
                            strHLink = varGItem.getElementsByTagName("a")(0).href ' get first hyperlink [a] found in current item
                            strDescr = GetInnerText(varGItem.getElementsByClassName("st")(0).innerHTML) ' get first description [span.st] found in current item
                            lngFound = lngFound + 1
                            With objSheet ' put result into cell
                                .Hyperlinks.Add .Cells(y, x), strHLink, , , strDescr
                                .Cells(y, x).WrapText = True
                                x = x + 1 ' next column
                            End With
                            If lngFound = TargetItemsQty Then Exit Do ' continue with next keyword - necessary quantity of the results for current keyword found
                        End If
                        DoEvents
                    Next
                    If TypeName(.document.getElementById("pnnext")) = "Null" Then Exit Do ' continue with next keyword - no [a#pnnext.pn] next page button exists
                    strNextURL = .document.getElementById("pnnext").href ' get next page url
                    .Navigate strNextURL ' go to next search results page
                Loop
            End With
            y = y + 1 ' next row
        Loop
    End With
    objIE.Quit

    ' google web search page contains the elements:
    ' [div#res] - main search results block
    ' [div.g] - each result item block within [div#res]
    ' [a] - hyperlink ancor(s) within each [div.g]
    ' [span.st] - description(s) within each [div.g]
    ' [a#pnnext.pn] - hyperlink ancor to the next search results page

End Sub

Function EncodeUriComponent(strText As String) As String
    Static objHtmlfile As Object

    If objHtmlfile Is Nothing Then
        Set objHtmlfile = CreateObject("htmlfile")
        objHtmlfile.parentWindow.execScript "function encode(s) {return encodeURIComponent(s)}", "jscript"
    End If
    EncodeUriComponent = objHtmlfile.parentWindow.encode(strText)
End Function

Function GetInnerText(strText As String) As String
    Static objHtmlfile As Object

    If objHtmlfile Is Nothing Then
        Set objHtmlfile = CreateObject("htmlfile")
        objHtmlfile.Open
        objHtmlfile.Write "<body></body>"
    End If
    objHtmlfile.body.innerHTML = strText
    GetInnerText = objHtmlfile.body.innerText
End Function
person omegastripes    schedule 06.03.2016