vb.net用来获取网页的类

最新推荐文章于 2023-11-16 15:06:52 发布

转载最新推荐文章于 2023-11-16 15:06:52 发布 · 1k 阅读

文章标签：

#vb.net #function #string #cookies #url #class

VB 同时被 2 个专栏收录

12 篇文章

订阅专栏

vb.net

11 篇文章

订阅专栏

本文介绍了一种使用C#实现的HTTP请求类，能够支持GET、POST方法，处理Cookie和Referer头，以及不同编码方式的网页抓取。详细解释了类的各个函数作用及用法，包括基本的网页获取、包含Cookie的网页获取、参数化获取等，同时提供了简化版的网页获取函数。此外，还展示了如何通过UserAgent类结合HTTPDriver类，实现访问包含Cookie的网页并支持Referer功能。

Imports System.Net
Imports System.IO

Public Class HttpDriverClass HttpDriver

    Public Function GetPage()Function GetPage(ByVal url As String, Optional ByRef postPara As String = "", Optional ByRef encType As String = "GB2312") As String
        Return GetPage(url, postPara, Nothing, False, encType)
    End Function

    Public Function GetPage()Function GetPage(ByVal url As String, ByRef postPara As System.Collections.Hashtable, Optional ByRef encType As String = "GB2312") As String
        Return GetPage(url, ColToStr(postPara), encType)
    End Function

    Public Function GetPage()Function GetPage(ByVal url As String, ByRef postPara As String, ByRef cookies As CookieCollection, ByVal hasCookie As Boolean, Optional ByRef encType As String = "GB2312", Optional ByRef refer As String = "") As String
        If (url.StartsWith("http://") = False) Then
            url = "http://" & url
        End If
        Dim hRqst As HttpWebRequest = HttpWebRequest.Create(url)
        If (hasCookie = True AndAlso (Not cookies Is Nothing)) Then
            hRqst.CookieContainer = New CookieContainer
            hRqst.CookieContainer.Add(cookies)
        End If

        hRqst.ContentType = "application/x-www-form-urlencoded"
        hRqst.Headers.Add("Accept-Language", "zh-cn")
        Dim streamData As Stream
        Dim bt() As Byte
        If (postPara = "") Then
            hRqst.Method = "GET"
        Else
            hRqst.Method = "POST"
            hRqst.AllowWriteStreamBuffering = True
            bt = System.Text.Encoding.ASCII.GetBytes(postPara)
            hRqst.ContentLength = bt.Length
            hRqst.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0)"
            hRqst.Referer = refer
            hRqst.KeepAlive = False
            hRqst.Timeout = 20000
            streamData = hRqst.GetRequestStream()
            streamData.Write(bt, 0, bt.Length)
            streamData.Close()
        End If
        Dim hRsp As HttpWebResponse
        hRsp = hRqst.GetResponse()
        streamData = hRsp.GetResponseStream()
        If (hasCookie = True AndAlso (Not hRsp.Cookies Is Nothing)) Then
            cookies.Add(hRsp.Cookies)
        End If
        If (encType = "") Then
            encType = "GB2312"
        End If
        Dim readStream As New IO.StreamReader(streamData, System.Text.Encoding.GetEncoding(encType))
        GetPage = readStream.ReadToEnd()
        streamData.Close()
    End Function

    Public Function GetPage()Function GetPage(ByVal url As String, ByRef postPara As System.Collections.Hashtable, ByRef cookies As CookieCollection, ByVal hasCookie As Boolean, Optional ByRef encType As String = "GB2312") As String
        Return GetPage(url, ColToStr(postPara), cookies, True, encType)
    End Function

    Public Function GetPage()Function GetPage(ByVal url As String, ByRef cookies As CookieCollection, ByVal hasCookie As Boolean, Optional ByRef encType As String = "GB2312") As String
        Return GetPage(url, "", cookies, True, encType)
    End Function

    ’该函数用于转换表单项集合为字符串
    Public Shared Function ColToStr()Function ColToStr(ByRef ht As System.Collections.Hashtable, Optional ByRef encType As String = "GB2312") As String
        Dim str As String
        Dim para As DictionaryEntry
        For Each para In ht
            str &= System.Web.HttpUtility.UrlEncode(CType(para.Key, String), Text.Encoding.GetEncoding(encType))
            str &= "="
            str &= System.Web.HttpUtility.UrlEncode(CType(para.Value, String), Text.Encoding.GetEncoding(encType))
            str &= "&"
        Next
        str = str.Substring(0, str.Length - 1)
        Return str
    End Function

End Class

如果需要支持cookie，并支持refer，可以通过下面这个类来使用上面的httpdriver。

’该类用于访问含有cookie的页面
Imports System.IO

Public Class UserAgentClass UserAgent
    Private m_cookies As New System.Net.CookieCollection
    Private refer As String
    Private hd As New HttpDriver

    Public Function GetPage()Function GetPage(ByVal url As String, Optional ByRef postPara As String = "", Optional ByRef encType As String = "GB2312") As String
        GetPage = hd.GetPage(url, postPara, m_cookies, True, encType, refer)
        refer = url
    End Function

    Public Function GetPage()Function GetPage(ByVal url As String, ByRef postPara As Hashtable, Optional ByRef encType As String = "GB2312") As String
        Return GetPage(url, hd.ColToStr(postPara), encType)
    End Function

    Public Function SetCookie()Function SetCookie(ByVal cookies As System.Net.CookieCollection)
        m_cookies = cookies
    End Function

    Public Function GetCookie()Function GetCookie() As System.Net.CookieCollection
        Return m_cookies
    End Function
End Class

轻量的get网页的函数

Public Function GetPage()Function GetPage(ByVal url As String) As String
Dim hRqst As HttpWebRequest = HttpWebRequest.Create(url)

    hRqst.ContentType = "application/x-www-form-urlencoded"
    hRqst.Method = "GET"
    Dim streamData As Stream

Dim hRsp As HttpWebResponse = hRqst.GetResponse()
streamData = hRsp.GetResponseStream()

    Dim readStream As New IO.StreamReader(streamData, System.Text.Encoding.GetEncoding("GB2312"))
    GetPage = readStream.ReadToEnd()
    streamData.Close()
End Function

Get方法：

Dim ua as New UserAgent
Dim content as String
Dim url as String
url = "www.sina.com.cn"
content = ua.GetPage(url)

Post方法：

Dim ua as New UserAgent
Dim content as String
Dim url as String
Dim ht as New HashTable

url = "mail.sina.com.cn"
ht.Add("username", "用户名")
ht.Add("password", "密码")
content = ua.GetPage(url, ht)