抓取网页中的链接

最新推荐文章于 2024-11-03 09:29:19 发布

原创最新推荐文章于 2024-11-03 09:29:19 发布 · 692 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#textbox #string #function #asp #regex #正则表达式

抓取网页中的链接

作者：孟宪会出自：【孟宪会之精彩世界】发布日期：2003年5月1日 7点4分24秒

输入一个地址，就可以把那个网页中的链接提取出来，下面这段代码可以轻松实现，主要的是用到了正则表达式。

GetUrl.aspx代码如下：

&lt;%@ Page Language=&quot;vb&quot; CodeBehind=&quot;GetUrl.aspx.vb&quot; AutoEventWireup=&quot;false&quot; Inherits=&quot;aspxWeb.GetUrl&quot; %&gt;
            &lt;html&gt;
            &lt;head&gt;
            &lt;META http-equiv=&quot;content-type&quot; content=&quot;text/html; charset=gb2312&quot;&gt;
            &lt;/head&gt;
            &lt;body&gt;
            &lt;form id=&quot;Form1&quot; method=&quot;post&quot; runat=&quot;server&quot;&gt;
            &lt;P&gt;
            &lt;asp:Label id=&quot;Label1&quot; runat=&quot;server&quot;&gt;&lt;/asp:Label&gt;
            &lt;asp:TextBox id=&quot;urlTextBox&quot; runat=&quot;server&quot; Width=&quot;336px&quot;&gt;
            http://lucky_elove.www1.dotnetplayground.com/
            &lt;/asp:TextBox&gt;
            &lt;asp:Button OnClick=&quot;scrapeButton_Click&quot; id=&quot;scrapeButton&quot; runat=&quot;server&quot;&gt;&lt;/asp:Button&gt;
            &lt;/P&gt;
            &lt;HR width=&quot;100%&quot; SIZE=&quot;1&quot;&gt;
            &lt;P&gt;
            &lt;asp:Label id=&quot;TipResult&quot; runat=&quot;server&quot;&gt;&lt;/asp:Label&gt;
            &lt;asp:TextBox id=&quot;resultLabel&quot; runat=&quot;server&quot; TextMode=&quot;MultiLine&quot;
            Width=&quot;100%&quot; Height=&quot;400&quot;&gt;&lt;/asp:TextBox&gt;
            &lt;/P&gt;
            &lt;/form&gt;
            &lt;/body&gt;
            &lt;/html&gt;

后代码GetUrl.aspx.vb如下：

Imports System.IO
            Imports System.Net
            Imports System.Text
            Imports System.Text.RegularExpressions
            Imports System
            Public Class GetUrl
            Inherits System.Web.UI.Page
            Protected WithEvents Label1 As System.Web.UI.WebControls.Label
            Protected WithEvents urlTextBox As System.Web.UI.WebControls.TextBox
            Protected WithEvents scrapeButton As System.Web.UI.WebControls.Button
            Protected WithEvents TipResult As System.Web.UI.WebControls.Label
            Protected WithEvents resultLabel As System.Web.UI.WebControls.TextBox
            #Region &quot; Web 窗体设计器生成的代码 &quot;
            '该调用是 Web 窗体设计器所必需的。
            &lt;System.Diagnostics.DebuggerStepThrough()&gt; Private Sub InitializeComponent()
            End Sub
            Private Sub Page_Init(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles MyBase.Init
            'CODEGEN: 此方法调用是 Web 窗体设计器所必需的
            '不要使用代码编辑器修改它。
            InitializeComponent()
            End Sub
            #End Region
            Private Sub Page_Load(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles MyBase.Load
            '在此处放置初始化页的用户代码
            Label1.Text = &quot;请输入一个URL地址：&quot;
            scrapeButton.Text = &quot;分离Href链接&quot;
            End Sub
            Private report As New StringBuilder()
            Private webPage As String
            Private countOfMatches As Int32
            Public Sub scrapeButton_Click(ByVal sender As System.Object, ByVal e As System.EventArgs)
            webPage = GrabUrl()
            Dim myDelegate As New MatchEvaluator(AddressOf MatchHandler)
            Dim linksExpression As New Regex( _
            &quot;/&lt;a.+?href=['&quot;&quot;](?!http/:////)(?!mailto/:)(?&gt;foundAnchor&gt;[^'&quot;&quot;&gt;]+?)[^&gt;]*?/&gt;&quot;, _
            RegexOptions.Multiline Or RegexOptions.IgnoreCase Or RegexOptions.IgnorePatternWhitespace)
            Dim newWebPage As String = linksExpression.Replace(webPage, myDelegate)
            TipResult.Text = &quot;&lt;h2&gt;从 &quot; &amp; urlTextBox.Text &amp; &quot;分离出的Href链接&lt;/h2&gt;&quot; &amp; _
            &quot;&lt;b&gt;找到并整理&quot; &amp; countOfMatches.ToString() &amp; &quot; 个链接&lt;/b&gt;&lt;br&gt;&lt;br&gt;&quot; &amp; _
            report.ToString().Replace(Environment.NewLine, &quot;&lt;br&gt;&quot;)
            TipResult.Text &amp;= &quot;&lt;h2&gt;整理过的页面&lt;/h2&gt;&lt;script&gt;window.document.title='抓取网页中的链接'&lt;/script&gt;&quot;
            resultLabel.Text = newWebPage
            End Sub
            Public Function MatchHandler(ByVal m As Match) As String
            Dim link As String = m.Groups(&quot;foundAnchor&quot;).Value
            Dim rToL As New Regex(&quot;^&quot;, RegexOptions.Multiline Or RegexOptions.RightToLeft)
            Dim col, row As Int32
            Dim lineBegin As Int32 = rToL.Match(webPage, m.Index).Index
            row = rToL.Matches(webPage, m.Index).Count
            col = m.Index - lineBegin
            report.AppendFormat( _
            &quot;Link &lt;b&gt;{0}&lt;/b&gt;, fixed at row: {1}, col: {2}{3}&quot;, _
            Server.HtmlEncode(m.Groups(0).Value), _
            row, _
            col, _
            Environment.NewLine _
            )
            Dim newLink As String
            If link.StartsWith(&quot;/&quot;) Then
            newLink = link.Substring(1)
            Else
            newLink = link
            End If
            countOfMatches += 1
            Return m.Groups(0).Value.Replace(link, newLink)
            End Function
            Private Function GrabUrl() As String
            Dim wc As New WebClient()
            Dim s As Stream = wc.OpenRead(urlTextBox.Text)
            Dim sr As StreamReader = New StreamReader(s, System.Text.Encoding.Default)
            GrabUrl = sr.ReadToEnd
            s.Close()
            wc.Dispose()
            End Function
            End Class