Question

我正在尝试创建一个Windows桌面应用程序，该应用程序将转到指定的站点并从该站点获取HTML。我发现了很多这样做的示例，但由于某些原因，它不适用于传统的Google协作平台网页。该计划需要在Google协作平台页面的正文中找到简单的文字。当您“查看页面来源”时，它不会显示Google Chrome显示的相同代码。怎么了？

Public Sub Scrape(strURL)
    Try

        Dim wrResponse As WebResponse
        Dim wrRequest As WebRequest = HttpWebRequest.Create(strURL)

        textScrape = "Extracting..." & Environment.NewLine

        wrResponse = wrRequest.GetResponse()

        Using sr As New StreamReader(wrResponse.GetResponseStream())
            strOutput = sr.ReadToEnd()
            ' Close and clean up the StreamReader
            sr.Close()
        End Using

        textScrape = strOutput

        'Formatting Techniques

        ' Remove Doctype ( HTML 5 )
        strOutput = Regex.Replace(strOutput, "<!(.|\s)*?>", "")

        ' Remove HTML Tags
        ' strOutput = Regex.Replace(strOutput, "</?[a-z][a-z0-9]*[^<>]*>", "")

        ' Remove HTML Comments
        ' strOutput = Regex.Replace(strOutput, "<!--(.|\s)*?-->", "")

        ' Remove Script Tags
        ' strOutput = Regex.Replace(strOutput, "<script.*?</script>", "", RegexOptions.Singleline Or RegexOptions.IgnoreCase)

        ' Remove Stylesheets
        ' strOutput = Regex.Replace(strOutput, "<style.*?</style>", "", RegexOptions.Singleline Or RegexOptions.IgnoreCase)

        scrapeFormatted = strOutput 'write Formatted Output To Separate TB

        Form2.Show()

    Catch ex As Exception

        ErrorMsg("", "")

    End Try
End Sub

Answer 1

没关系，明白了。对于正在寻找相关信息的人来说，上面的代码非常有效。确保将正确的链接插入＆＃34; strURL＆＃34;变量。这对我来说是一个非常愚蠢的错误。

Public Sub Scrape(strURL)
Try

    Dim wrResponse As WebResponse
    Dim wrRequest As WebRequest = HttpWebRequest.Create(strURL)

    textScrape = "Extracting..." & Environment.NewLine

    wrResponse = wrRequest.GetResponse()

    Using sr As New StreamReader(wrResponse.GetResponseStream())
        strOutput = sr.ReadToEnd()
        ' Close and clean up the StreamReader
        sr.Close()
    End Using

    textScrape = strOutput

    'Formatting Techniques

    ' Remove Doctype ( HTML 5 )
    strOutput = Regex.Replace(strOutput, "<!(.|\s)*?>", "")

    ' Remove HTML Tags
    ' strOutput = Regex.Replace(strOutput, "</?[a-z][a-z0-9]*[^<>]*>", "")

    ' Remove HTML Comments
    ' strOutput = Regex.Replace(strOutput, "<!--(.|\s)*?-->", "")

    ' Remove Script Tags
    ' strOutput = Regex.Replace(strOutput, "<script.*?</script>", "", RegexOptions.Singleline Or RegexOptions.IgnoreCase)

    ' Remove Stylesheets
    ' strOutput = Regex.Replace(strOutput, "<style.*?</style>", "", RegexOptions.Singleline Or RegexOptions.IgnoreCase)

    scrapeFormatted = strOutput 'write Formatted Output To Separate TB

    Form2.Show()

Catch ex As Exception

    ErrorMsg("", "")

End Try

End Sub

从网页上抓取HTML？ - VB.NET

1 个答案: