ASP.NET實現抓取網頁中的鏈接
2024-07-10 12:55:05
供稿：網友
輸入一個地址，就可以把那個網頁中的鏈接提取出來，下面這段代碼可以輕松實現，主要的是用到了正則表達式。
geturl.aspx代碼如下：
<%@ page language="<a target="_blank">vb</a>" codebehind="geturl.aspx.vb" autoeventwireup="false" inherits="aspx<a target="_blank">web</a>.geturl" %>
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=gb2312">
</head>
<body>
<form id="form1" method="post" runat="server">
<p>
<asp:label id="label1" runat="server"></asp:label>
<asp:textbox id="urltextbox" runat="server" width="336px">
http://lucky_elove.www1.dotnetplayground.com/
</asp:textbox>
<asp:button onclick="scrapebutton_click" id="scrapebutton" runat="server"></asp:button>
</p>
<hr width="100%" size="1">
<p>
<asp:label id="tipresult" runat="server"></asp:label>
<asp:textbox id="resultlabel" runat="server" textmode="multiline"
width="100%" height="400"></asp:textbox>
</p>
</form>
</body>
</html>
后代碼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 " web 窗體設計器生成的代碼 "
'該調用是 web 窗體設計器所必需的。
<system.diagnostics.debuggerstepthrough()> private sub initializecomponent()
end sub
private sub page_init(byval sender as system.object, byval e as system.eventargs) handles mybase.init
'codegen: 此方法調用是 web 窗體設計器所必需的
'不要使用代碼編輯器修改它。
initializecomponent()
end sub
#end region
private sub page_load(byval sender as system.object, byval e as system.eventargs) handles mybase.load
'在此處放置初始化頁的用戶代碼
label1.text = "請輸入一個url地址："
scrapebutton.text = "分離href鏈接"
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( _
"/<a.+?href=['""](?!http/:////)(?!mailto/:)(?>foundanchor>[^'"">]+?)[^>]*?/>", _
regexoptions.multiline or regexoptions.ignorecase or regexoptions.ignorepatternwhitespace)
dim newwebpage as string = linksexpression.replace(webpage, mydelegate)
tipresult.text = "<h2>從 " & urltextbox.text & "分離出的href鏈接</h2>" & _
"<b>找到并整理" & countofmatches.tostring() & " 個鏈接</b><br><br>" & _
report.tostring().replace(environment.newline, "<br>")
tipresult.text &= "<h2>整理過的頁面</h2><script>window.document.title='抓取網頁中的鏈接'</script>"
resultlabel.text = newwebpage
end sub
public function matchhandler(byval m as match) as string
dim link as string = m.groups("foundanchor").value
dim rtol as new regex("^", 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( _
"link <b>{0}</b>, fixed at row: {1}, col: {2}{3}", _
server.htmlencode(m.groups(0).value), _
row, _
col, _
environment.newline _
)
dim newlink as string
if link.startswith("/") 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
