Question

我正在抓取https://thepiratebay.se中的内容，并且我想知道如何获取搜索结果的总页数。

这是我的计划： thepiratebay scraper

正如您在左侧看到的那样，搜索结果显示出来，而右侧是对所选结果的评论（在这种情况下是最高结果）。在程序的底部，你可以看到它显示了它显示了多少结果，现在右边是页面。

我想以此格式{current page}/{total pages}显示结果的页数。我真的不想帮助查找current page，但我真的想得到total pages。

我还希望评论的这个功能（右边的列表）。

这可能有点太多了，但它不应该那么难，因为结果很容易。无法在Google上找到任何内容，因此非常感谢您的帮助。

编辑：刮痧结果：

Dim ResultCount, I As Integer
    Dim filenamelist, fileurllist, fileseeders, fileleechers, filemagneturl, filesize As New List(Of String)

    filenamelist.Clear()
    fileurllist.Clear()
    TreeView1.Nodes.Clear()

    Using WC As New System.Net.WebClient
        Source = WC.DownloadString("http://thepiratebay.se/search/" & TextBox1.Text.Replace(" "c, "%20") & "/0/7/")
        Link = Source
        If CheckBox6.Checked = True Then
            Source = Source & "600"
        End If
        If CheckBox5.Checked = True Then
            Source = Source & "500"
        End If
        If CheckBox7.Checked = True Then
            Source = Source & "400"
        End If
        If CheckBox4.Checked = True Then
            Source = Source & "300"
        End If
        If CheckBox3.Checked = True Then
            Source = Source & "200"
        End If
        If CheckBox2.Checked = True Then
            Source = Source & "100"
        End If
        If CheckBox1.Checked = True Then
            Source = Source & "0"
        End If

        If Source.Contains("No hits. Try adding an asterisk in you search phrase.") Then
            MessageBox.Show("Search returned 0 results.", "Error", MessageBoxButtons.OK, MessageBoxIcon.Stop)
        Else
            ResultCount = InstanceCount(Source, "vertTh")
            Dim Filename, FileUrl, Filemagnet, FS As String
            Dim FileSeed, FileLeech As Integer

            Do Until I = ResultCount
                Filename = GetBetween(Source, "title=" & Chr(34) & "Details for ", Chr(34) & ">", I)
                FileUrl = "http://thepiratebay.se/torrent/" & GetBetween(Source, "<a href=" & Chr(34) & "/torrent/", Chr(34) & " class=" & Chr(34) & "detLink" & Chr(34), I)
                FileSeed = GetBetween(Source, "<td align=" & Chr(34) & "right" & Chr(34) & ">", "</td>", I + I)
                FileLeech = GetBetween(Source, "<td align=" & Chr(34) & "right" & Chr(34) & ">", "</td>", I + I + 1)
                Filemagnet = "magnet:" & GetBetween(Source, "<a href=" & Chr(34) & "magnet:", Chr(34) & " title=" & Chr(34) & "Download this torrent using magnet", I)
                FS = GetBetween(Source, ", Size", ", ULed by ", I).Replace(" ", "").Replace("&nbsp;", " ")

                filemagneturl.Add(Filemagnet) 'add result to array
                filenamelist.Add(Filename) 'add result to array
                fileurllist.Add(FileUrl) 'add result to array
                fileseeders.Add(FileSeed) 'add result to array
                fileleechers.Add(FileLeech)
                filesize.Add(FS)
                I = I + 1 'increment i with 1 to get next result

            Loop
        End If
    End Using

    I = 0
    Do Until I = filenamelist.Count()
        Dim rootNode = TreeView1.Nodes.Add(filenamelist(I))
        rootNode.Nodes.Add("Seeders: " & fileseeders(I))
        rootNode.Nodes.Add("Leechers: " & fileleechers(I))
        rootNode.Nodes.Add(fileurllist(I))
        rootNode.Nodes.Add(filemagneturl(I))
        rootNode.Nodes.Add(filesize(I))
        I = I + 1
        LabelResults.Text = "Results: " & I
    Loop

对结果进行评论：

Try
        UsernameArr.Clear()
        PostArr.Clear()

        Using WC As New System.Net.WebClient
            Dim Source As String = WC.DownloadString(Link)
            Source = GetBetween(Source, "<div id=" & Chr(34) & "comments" & Chr(34) & ">", "<div class=" & Chr(34) & "ads" & Chr(34) & " id=" & Chr(34) & "sky-banner" & Chr(34) & ">", 0)
            Dim CommentCount As Integer = InstanceCount(Source, "byline")
            CommentCounter = CommentCount
            If CommentCount < 1 Then
                MessageBox.Show("This torrent has no comments")
            Else
                Dim itterator As Integer = 0

                Do Until itterator = CommentCount
                    Dim User As String = GetBetween(Source, "<a href=" & Chr(34) & "/user/", "/" & Chr(34) & " title=" & Chr(34) & "Browse ", itterator)
                    Dim Post As String = GetBetween(Source, "comment" & Chr(34) & ">", "</div>", itterator).Replace("<br />", " "c)
                    Dim DateStr As String = GetBetween(Source, "</a> at ", " CET:", itterator)

                    UsernameArr.Add(User)
                    postdatearr.Add(DateStr)
                    PostArr.Add(Post)

                    Dim rootNode = TreeView2.Nodes.Add(User)
                    rootNode.Nodes.Add(DateStr)
                    rootNode.Nodes.Add(Post)

                    itterator = itterator + 1
                Loop
            End If
        End Using

    Catch ex As Exception
        'do nothing
    End Try

在字符串之间获取文字：

Private Function GetBetween(ByVal input As String, ByVal str1 As String, ByVal str2 As String, ByVal index As Integer) As String
    Dim temp As String = Regex.Split(input, str1)(index + 1)
    Return Regex.Split(temp, str2)(0)
End Function

从网站上的搜索字词中抓取总页数

0 个答案: