📄 从网上抓取指定url源码的方案.htm
字号:
</table>
<table width="100%" border="0" cellpadding="0" cellspacing="0">
<tr bgcolor="#666666">
<td width="27%" align="center" bgcolor="#666666"><font color="#FFFFFF"><strong>做最专业的JSP中文网站</strong></font></td>
<td width="71%" align="left" bgcolor="#666666"><a href="http://www.jspcn.net"><font color="#FFFFFF"><strong>当前位置:<a href="http://www.jspcn.net"><font color="#FFFFFF"><strong>首页</strong></font></a>--<a href="../moreNews.html"><font color="#FFFFFF"><strong>文章分类</strong></font></a>--<a href="../moreNews.html"><font color="#FFFFFF"><strong>程序代码</strong></font></a>--<a href="B1097670330235.html"><font color="#FFFFFF"><strong>代码收集</strong></font></a></strong></font></a></td>
<td width="2%"> </td>
</tr>
</table> </td>
</tr>
<tr>
<td height="300" valign="top">
<table width="100%" height="631" border="0" cellpadding="0" cellspacing="0" bgcolor="#FFFFFF">
<tr>
<td width="26%" height="631" valign="top" bgcolor="#FFFFFF">
<form name="form1" method="post" action="../search.jsp">
<table width="100%" height="40" border="0" cellpadding="2" cellspacing="0" bgcolor="#FFFFFF">
<tr align="center">
<td height="30" colspan="3"> <strong>文章搜索:</strong>
<input name="strSearchWord" type="text" size="15" class=inputCls value="">
</td>
</tr>
<tr align="left">
<td width="35%" height="32">
<input type="radio" name="strSearchType" value="keywordSearch" checked>
关键字 </td>
<td width="31%"> <input type="radio" name="strSearchType" value="titleSearch">
标题</td>
<td width="34%"> <input type="radio" name="strSearchType" value="contentSearch">
内容</td>
</tr>
<tr align="center">
<td colspan="3"> <input type="submit" name="Submit" class=mybutton value="确 定">
<input type="reset" name="Subddd" class=mybutton value="清 除"> </td>
</tr>
</table></form>
<table width="100%" cellpadding="0" cellspacing="0" bordercolor="#666666">
<tr>
<td bgcolor="#666666"><font color="#FFFFFF"><strong>JSPCN文章目录分类</strong></font></td>
</tr>
<tr><td>
<table width="100%" height="2" border="0" cellpadding="2" cellspacing="0" bgcolor="#FFFFFF">
<tr><td><a href="B1097670360234.html"><font color=red>缓存区</font></a> [<font color="red">2581</font>]</td><td><a href="B1097670340234.html"><font color=red>JSP基础</font></a> [<font color="red">136</font>]</td></tr><tr><td><a href="B1097670330934.html"><font color=red>JSP其他</font></a> [<font color="red">57</font>]</td><td><a href="B1097670337234.html"><font color=red>JAVABEAN</font></a> [<font color="red">46</font>]</td></tr><tr><td><a href="B1097670334234.html"><font color=red>图片声音</font></a> [<font color="red">17</font>]</td><td><a href="B1097670350234.html"><font color=red>JSP配置</font></a> [<font color="red">219</font>]</td></tr><tr><td><a href="B1097670330237.html"><font color=red>开发工具</font></a> [<font color="red">28</font>]</td><td><a href="B1097670338234.html"><font color=red>上传问题</font></a> [<font color="red">27</font>]</td></tr><tr><td><a href="B1097670330734.html"><font color=red>时间相关</font></a> [<font color="red">16</font>]</td><td><a href="B1097813291140.html"><font color=red>教程系列</font></a> [<font color="red">157</font>]</td></tr><tr><td><a href="B1097670335234.html"><font color=red>文件操作</font></a> [<font color="red">126</font>]</td><td><a href="B1097670330434.html"><font color=red>STRUTS</font></a> [<font color="red">144</font>]</td></tr><tr><td><a href="B1106119723921.html"><font color=red>JSP实例</font></a> [<font color="red">89</font>]</td><td><a href="B1097670339234.html"><font color=red>中文问题</font></a> [<font color="red">69</font>]</td></tr><tr><td><a href="B1097670336234.html"><font color=red>数据库</font></a> [<font color="red">212</font>]</td><td><a href="B1097670330534.html"><font color=red>JAVAMAIL</font></a> [<font color="red">72</font>]</td></tr><tr><td><a href="B1097670333234.html"><font color=red>JAVA基础</font></a> [<font color="red">421</font>]</td><td><a href="B1167791227062.html"><font color=red>Spring</font></a> [<font color="red">34</font>]</td></tr><tr><td><a href="B1106102788031.html"><font color=red>考试相关</font></a> [<font color="red">63</font>]</td><td><a href="B1106121420828.html"><font color=red>JAVA类</font></a> [<font color="red">139</font>]</td></tr><tr><td><a href="B1100167647078.html"><font color=red>Application</font></a> [<font color="red">115</font>]</td><td><a href="B1106103426750.html"><font color=red>Swing</font></a> [<font color="red">26</font>]</td></tr><tr><td><a href="B1106101884500.html"><font color=red>XML</font></a> [<font color="red">163</font>]</td><td><a href="B1106116974203.html"><font color=red>异常处理</font></a> [<font color="red">33</font>]</td></tr><tr><td><a href="B1122279307656.html"><font color=red>JMX</font></a> [<font color="red">8</font>]</td><td><a href="B1106101557078.html"><font color=red>Servlet</font></a> [<font color="red">98</font>]</td></tr><tr><td><a href="B1106102149515.html"><font color=red>J2ME</font></a> [<font color="red">257</font>]</td><td><a href="B1106121052109.html"><font color=red>JAVA实例</font></a> [<font color="red">290</font>]</td></tr><tr><td><a href="B1100049211234.html"><font color=red>JAVA网络</font></a> [<font color="red">179</font>]</td><td><a href="B1106103214468.html"><font color=red>EJB</font></a> [<font color="red">261</font>]</td></tr><tr><td><a href="B1119514346781.html"><font color=red>Hibernate</font></a> [<font color="red">6</font>]</td><td><a href="B1106116692828.html"><font color=red>声音图片</font></a> [<font color="red">28</font>]</td></tr><tr><td><a href="B1097670332234.html"><font color=red>APPLET</font></a> [<font color="red">78</font>]</td><td><a href="B1106103146187.html"><font color=red>JAVA线程</font></a> [<font color="red">90</font>]</td></tr><tr><td><a href="B1106102159046.html"><font color=red>J2EE</font></a> [<font color="red">374</font>]</td><td><a href="B1106122634375.html"><font color=red>SUN</font></a> [<font color="red">89</font>]</td></tr><tr><td><a href="B1106103575625.html"><font color=red>Java API</font></a> [<font color="red">141</font>]</td><td><a href="B1097670330294.html"><font color=red>JS基础</font></a> [<font color="red">184</font>]</td></tr><tr><td><a href="B1097670330334.html"><font color=red>asp笔记</font></a> [<font color="red">7</font>]</td><td><a href="B1120187785171.html"><font color=red>RSS</font></a> [<font color="red">1</font>]</td></tr><tr><td><a href="B1097670330264.html"><font color=red>B/S开发</font></a> [<font color="red">12</font>]</td><td><a href="B1101172956015.html"><font color=red>B/S其他</font></a> [<font color="red">7</font>]</td></tr><tr><td><a href="B1097670330236.html"><font color=red>原子代码</font></a> [<font color="red">3</font>]</td><td><a href="B1097670330235.html"><font color=red>代码收集</font></a> [<font color="red">8</font>]</td></tr><tr><td><a href="B1098952171312.html"><font color=red>RESIN</font></a> [<font color="red">25</font>]</td><td><a href="B1106100998031.html"><font color=red>JBOSS</font></a> [<font color="red">25</font>]</td></tr><tr><td><a href="B1106117261671.html"><font color=red>weblogic</font></a> [<font color="red">56</font>]</td><td><a href="B1098429275421.html"><font color=red>eclipse</font></a> [<font color="red">42</font>]</td></tr><tr><td><a href="B1106100864250.html"><font color=red>Tomcat</font></a> [<font color="red">93</font>]</td><td><a href="B1106101033171.html"><font color=red>Jbuilder</font></a> [<font color="red">57</font>]</td></tr><tr><td><a href="B1099296186218.html"><font color=red>MYSQL</font></a> [<font color="red">39</font>]</td><td><a href="B1099296177640.html"><font color=red>ORACLE</font></a> [<font color="red">92</font>]</td></tr><tr><td><a href="B1099296161890.html"><font color=red>sql server</font></a> [<font color="red">33</font>]</td><td><a href="B1102321935125.html"><font color=red>WWW服务</font></a> [<font color="red">6</font>]</td></tr><tr><td><a href="B1120482010109.html"><font color=red>常见问题</font></a> [<font color="red">9</font>]</td><td><a href="B1099648785593.html"><font color=red>邮件服务</font></a> [<font color="red">4</font>]</td></tr><tr><td><a href="B1120480629609.html"><font color=red>相关说明</font></a> [<font color="red">1</font>]</td></table>
</td></tr></table>
<table width="100%" cellpadding="0" cellspacing="0" bordercolor="#666666">
<tr>
<td bgcolor="#666666"><font color="#333333"><strong><font color="#FFFFFF">热点文章链接</font></strong></font><font color="#FFFFFF"> </font></td>
</tr>
<tr>
<td>
<table width="100%" height="2" border="0" cellpadding="2" cellspacing="0" bgcolor="#FFFFFF">
<a href="13004003160.html" target=_blank>JSP生成验证码源程序</a> [<font color="red">18695</font>]<br><a href="13004003159.html" target=_blank>JSP彩色验证码</a> [<font color="red">4417</font>]<br><a href="1300400279.html" target=_blank>一个读取xml文件内容的类</a> [<font color="red">3707</font>]<br><a href="1300400285.html" target=_blank>JSP中读文件和写文件的例子</a> [<font color="red">3144</font>]<br><a href="1300400417.html" target=_blank>将一图片同比例缩小绘制</a> [<font color="red">1887</font>]<br><a href="1300400278.html" target=_blank>jsp读取大对象CLOB并生成xml文件示例</a> [<font color="red">1850</font>]<br><a href="1300400377.html" target=_blank>从网上抓取指定URL源码的方案</a> [<font color="red">1701</font>]<br><a href="1300400330.html" target=_blank>多线程学习初步</a> [<font color="red">1163</font>]<br></table></td>
</tr>
</table>
<table width="100%" cellpadding="0" cellspacing="0" bordercolor="#666666">
<tr>
<td bgcolor="#666666"><font color="#333333"><strong><font color="#FFFFFF">相关文章链接</font></strong></font><font color="#FFFFFF"> </font></td>
</tr>
<tr>
<td> <table width="100%" height="2" border="0" cellpadding="2" cellspacing="0" bgcolor="#FFFFFF">
<a href="13004003160.html" target=_blank>JSP生成验证码源程序</a> [2005-04-11]<br><a href="200430341.html" target=_blank>JAVA/JSP学习系列之十一(简单的“抓网页”代码)</a> [2004-10-15]<br></table></td>
</tr>
</table></td>
<td width="1%" align="left" valign="top" bgcolor="#666666"> </td>
<td width="73%" align="left" valign="top" bgcolor="#FFFFFF"> <table width="100%" height="726" border="0" cellpadding="2" cellspacing="0" bgcolor="#CCCCCC">
<tr>
<td height="36" align="center" valign="middle" bgcolor="#FFFFFF" style="word-break:break-all" class="title"><strong>从网上抓取指定URL源码的方案</strong></td>
</tr>
<tr>
<td height="40" align="right" valign="middle" bgcolor="#FFFFFF" style="word-break:break-all">作者:rexsp
文章来源:<a href="http://www.pconline.com.cn" target=_blank>www.pconline.com.cn</a><br>
访问次数:
<iframe name="ad" frameborder=0 width=30 height=10 scrolling=no src=../count.jsp?news_id=377></iframe>
次 加入时间:2004-10-19</td>
</tr>
<tr>
<td height="2" align="left" valign="top" bgcolor="#CCCCCC"></td>
</tr>
<tr>
<td height="649" align="left" valign="top" bgcolor="#FFFFFF" style="word-break:break-all">
<table width="100%" height="92%" border="0" cellpadding="6" cellspacing="0">
<tr>
<td height="623" align="left" valign="top" class="content"><strong>引言</strong><br> 在做无线项目的时候,与通讯公司的数据通讯有一部分是通过XML交互的,所以必须要动态抓取通讯公司提供的固定的Internet上的数据,便研究了一下如何抓取固定url上的数据,现与大家分享一下。<br><br> 类名GetPageCode,有一个方法GetSource,通过属性传递参数,入参控制的是要取得URL的地址,代理服务器的设置及输出方式的控制,这里大家可以再扩展自己的需要,我这里只提供了两种方式,一种是直接写到本地的某个文件中,另外一种就是返回字符串的。类里已经作了比较详细的注释,我想大家很容易就看明白了,如果实在不明白, 那就msn上问吧,MSN:yubo@x263.net。<br><br> 调用方式:<br> #region 测试获取远程网页<br><br><br><table bgcolor="#CCCCCC" bordercolor="#666666" borderColorDark="#CCCCCC" borderColorLight="#666666" width="100%" border="1" cellpadding="0" cellspacing="4"><tr><td align="left" style="WORD-BREAK: break-all"><br>GetPageCode gpc = new GetPageCode();<br> gpc.Url="http://ppcode.com";<br> gpc.ProxyState=1;//使用代理服务器,0为不使用,设置为1后下面的代理设置才起作用<br> gpc.ProxyAddress="http://proxyName.com";//代理服务器地址<br> gpc.ProxyPort="80";//代理服务器的端口<br> gpc.ProxyAccount="proxy";//代理服务器账号<br> gpc.ProxyPassword="password";//代理服务器密码<br> gpc.ProxyDomain="bqc";//代理服务器域<br> gpc.OutFilePath=filePath;//设置输出文件路径的地方,如果不设置,则返回字符串<br> gpc.GetSource();//处理<br> string tempErr=gpc.NoteMessage;//如果出错,这里会提示<br> string tempCode=gpc.OutString;//返回的字符串<br> #endregion<br> 类代码:<br> using System;<br> using System.Collections;<br> using System.ComponentModel;<br> using System.Data;<br> using System.Drawing;<br> using System.IO;<br> using System.Net;<br> using System.Text;<br> using System.Web;<br> namespace Test.Com<br> {<br> /// <summary><br> /// 功能:取得Internet上的URL页的源码<br> /// 创建:2004-03-22<br> /// 作者:Rexsp MSN:yubo@x263.net<br> /// </summary><br> public class GetPageCode<br> {<br> #region 私有变量<br> /// <summary><br> /// 网页URL地址<br> /// </summary><br> private string url=null;<br> /// <summary><br> /// 是否使用代码服务器:0 不使用 1 使用代理服务器<br> /// </summary><br> private int proxyState=0;<br> /// <summary><br> /// 代理服务器地址<br> /// </summary><br> private string proxyAddress=null;<br> /// <summary><br> /// 代理服务器端口<br> /// </summary><br> private string proxyPort=null;<br> /// <summary><br> /// 代理服务器用户名<br> /// </summary><br> private string proxyAccount=null;<br> /// <summary><br> /// 代理服务器密码<br> /// </summary><br> private string proxyPassword=null;<br> /// <summary><br> /// 代理服务器域<br> /// </summary><br> private string proxyDomain=null;<br> /// <summary><br> /// 输出文件路径<br> /// </summary><br> private string outFilePath=null;<br> /// <summary><br> /// 输出的字符串<br> /// </summary><br> private string outString=null;<br> /// <summary><br> /// 提示信息<br> /// </summary><br> private string noteMessage;<br><br> #endregion<br><br> #region 公共属性<br> /// <summary><br> /// 欲读取的URL地址<br> /// </summary><br> public string Url<br> {<br> get{return url;}<br> set{url=value;}<br> }<br> /// <summary><br> /// 是否使用代理服务器标志<br> /// </summary><br> public int ProxyState<br> {<br> get{return proxyState;}<br> set{proxyState=value;}<br> }<br> /// <summary><br> /// 代理服务器地址<br> /// </summary><br> public string ProxyAddress<br> {<br> get{return proxyAddress;}<br> set{proxyAddress=value;}<br> }<br> /// <summary><br><br> /// 代理服务器端口<br> /// </summary><br> public string ProxyPort<br> {<br> get{return proxyPort;}<br> set{proxyPort=value;}<br> }<br> /// <summary><br> /// 代理服务器账号<br> /// </summary><br> public string ProxyAccount<br> {<br> get{return proxyAccount;}<br> set{proxyAccount=value;}<br> }<br> /// <summary><br> /// 代理服务器密码<br> /// </summary><br> public string ProxyPassword<br> {<br> get{return proxyPassword;}<br> set{proxyPassword=value;}<br> }<br> /// <summary><br> /// 代理服务器域<br> /// </summary><br> public string ProxyDomain<br> {<br> get{return proxyDomain;}<br> set{proxyDomain=value;}<br> }<br> /// <summary><br> /// 输出文件路径<br> /// </summary><br> public string OutFilePath<br> {<br> get{return outFilePath;}<br><br> set{outFilePath=value;}<br> }<br> /// <summary><br> /// 返回的字符串<br> /// </summary><br> public string OutString<br> {<br> get{return outString;}<br> <br> }<br> /// <summary><br> /// 返回提示信息<br> /// </summary><br> public string NoteMessage<br> {<br> get{return noteMessage;}<br> <br> }<br> <br> #endregion<br> <br> #region 构造函数<br> public GetPageCode()<br> {<br> }<br> #endregion<br><br> #region 公共方法<br> /// <summary><br> /// 读取指定URL地址,存到指定文件中<br> /// </summary><br> public void GetSource() <br> { <br> WebRequest request = WebRequest.Create(this.url);<br> //使用代理服务器的处理<br> if(this.proxyState==1)<br> {<br> //默认读取80端口的数据<br><br> if(this.proxyPort==null)<br> this.ProxyPort="80";<br><br> WebProxy myProxy=new WebProxy(); <br> myProxy = (WebProxy)request.Proxy; <br> myProxy.Address = new Uri(this.ProxyAddress+":"+this.ProxyPort); <br> myProxy.Credentials = new NetworkCredential(this.proxyAccount, this.proxyPassword, this.ProxyDomain);<br> request.Proxy = myProxy; <br> }<br> try<br> <br> {<br> //请求服务<br> WebResponse response = request.GetResponse();<br> //返回信息<br> Stream resStream = response.GetResponseStream(); <br> StreamReader sr = new StreamReader(resStream, System.Text.Encoding.Default);<br> string tempCode= sr.ReadToEnd();<br> resStream.Close(); <br> sr.Close();<br><br> //如果输出文件路径为空,便将得到的内容赋给OutString属性<br> if(this.outFilePath==null)<br> {<br> this.outString=tempCode;<br> }<br> else<br> {<br><br> FileInfo fi = new FileInfo(this.outFilePath);<br> //如果存在文件则先干掉<br> if(fi.Exists)<br> fi.Delete();<br> StreamWriter sw = new StreamWriter(this.outFilePath,true,Encoding.Default);<br> sw.Write(tempCode);<br> sw.Flush();<br> sw.Close();<br> }<br> }<br> catch<br> {<br> this.noteMessage="出错了,请检查网络是否连通;";<br> }<br><br> }<br> #endregion<br><br> }<br> }<br><br><br></td></tr></table><br></td>
</tr>
</table></td>
</tr>
</table>
<table width="100%" height="61" border="0" cellpadding="0" cellspacing="0" bgcolor="#FFFFFF">
<tr>
<td height="29" align="right" valign="middle"><a href="../read_review.jsp?news_id=377">查看该新闻的相关评论</a></td>
</tr>
<tr>
<td height="16" align="right" valign="middle"> </td>
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -