`
isiqi
  • 浏览: 16349455 次
  • 性别: Icon_minigender_1
  • 来自: 济南
社区版块
存档分类
最新评论

ASP.NET(C#)经典采集代码

阅读更多

usingSystem;
usingSystem.Data;
usingSystem.Configuration;
usingSystem.Web;
usingSystem.Web.Security;
usingSystem.Web.UI;
usingSystem.Web.UI.WebControls;
usingSystem.Web.UI.WebControls.WebParts;
usingSystem.Web.UI.HtmlControls;
usingSystem.Drawing;
usingMSXML2;
usingSystem.Text.RegularExpressions;
namespacewenweifeng
{
/**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///CaiJi的摘要说明<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top"> /// </summary>
public classCaiJi
{
publicCaiJi()
{
//
//TODO:在此处添加构造函数逻辑
//
}
~CaiJi()
{
Dispose();
}
public voidDispose()
{
GC.SuppressFinalize(this);
}

日期随机函数#region日期随机函数
/**//**********************************
*函数名称:DateRndName
*功能说明:日期随机函数
*参数:ra:随机数
*调用示例:
*GetRemoteObjo=newGetRemoteObj();
*Randomra=newRandom();
*strings=o.DateRndName(ra);
*Response.Write(s);
*o.Dispose();
*********************************/
/**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///日期随机函数<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// </summary>
/// 随机数
/// <returns></returns>
public stringDateRndName(Randomra)
{
DateTimed=DateTime.Now;
strings= null,y,m,dd,h,mm,ss;
y=d.Year.ToString();
m=d.Month.ToString();
if(m.Lengthdd=d.Day.ToString();
if(dd.Lengthh=d.Hour.ToString();
if(h.Lengthmm=d.Minute.ToString();
if(mm.Lengthss=d.Second.ToString();
if(ss.Lengths+=y+ ',' +m+ ',' +dd+ ',' +h+ "-" +mm+ "-" +ss;
s+=ra.Next(1000000,9999999).ToString();
returns;
}
#endregion

取得文件后缀#region取得文件后缀
/**//**********************************
*函数名称:GetFileExtends
*功能说明:取得文件后缀
*参数:filename:文件名称
*调用示例:
*GetRemoteObjo=newGetRemoteObj();
*stringurl=@"http://www.baidu.com/img/logo.gif";
*strings=o.GetFileExtends(url);
*Response.Write(s);
*o.Dispose();
*********************************/
/**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///取得文件后缀<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// </summary>
/// 文件名称
/// <returns></returns>
public stringGetFileExtends(stringfilename)
{
stringext= null;
if(filename.IndexOf('.')> 0)
{
string[]fs=filename.Split('.');
ext=fs[fs.Length- 1];
}
returnext;
}
#endregion

获取远程文件源代码#region获取远程文件源代码
/**//**********************************
*函数名称:GetRemoteHtmlCode
*功能说明:获取远程文件源代码
*参数:Url:远程url
*调用示例:
*GetRemoteObjo=newGetRemoteObj();
*stringurl=@"http://www.baidu.com";
*strings=o.GetRemoteHtmlCode(url);
*Response.Write(s);
*o.Dispose();
*********************************/
/**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///获取远程文件源代码<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// </summary>
/// 远程url
/// <returns></returns>
public stringGetRemoteHtmlCode(stringUrl)
{
strings= "";
MSXML2.XMLHTTP_xmlhttp= newMSXML2.XMLHTTPClass();
_xmlhttp.open("GET",Url,false,null,null);
_xmlhttp.send("");
if(_xmlhttp.readyState== 4)
{
s=System.Text.Encoding.Default.GetString((byte[])_xmlhttp.responseBody);
}
returns;
}

#endregion

保存远程文件#region保存远程文件
/**//**********************************
*函数名称:RemoteSave
*功能说明:保存远程文件
*参数:Url:远程url;Path:保存到的路径
*调用示例:
*GetRemoteObjo=newGetRemoteObj();
*strings="";
*stringurl=@"http://www.baidu.com/img/logo.gif";
*stringpath=Server.MapPath("Html/");
*s=o.RemoteSave(url,path);
*Response.Write(s);
*o.Dispose();
*******************************/
/**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///保存远程文件<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// </summary>
/// 远程url
/// 保存到的路径
/// <returns></returns>
public stringRemoteSave(stringUrl,stringPath)
{

Randomra= newRandom();
stringnewfilename= string.Empty;
stringStringFileName=DateRndName(ra)+ "." +GetFileExtends(Url);
if(GetFileExtends(Url).Trim().ToLower()!= "jpg")
newfilename=StringFileName;
else
newfilename=DateRndName(ra)+ "Addpic." +GetFileExtends(Url);
stringStringFilePath=Path+StringFileName;
stringnewfilepath=Path+newfilename;
stringretname= string.Empty;
try
{
MSXML2.XMLHTTP_xmlhttp= newMSXML2.XMLHTTPClass();
_xmlhttp.open("GET",Url,false,null,null);
_xmlhttp.send("");
if(_xmlhttp.readyState== 4)
{
if(System.IO.File.Exists(StringFilePath))
System.IO.File.Delete(StringFilePath);
System.IO.FileStreamfs= newSystem.IO.FileStream(StringFilePath,System.IO.FileMode.CreateNew);
System.IO.BinaryWriterw= newSystem.IO.BinaryWriter(fs);
w.Write((byte[])_xmlhttp.responseBody);
w.Close();
fs.Close();
if(GetFileExtends(Url).Trim().ToLower()== "jpg")
{
functionmyfunction= newfunction();
//myfunction.AddShuiYinWord(StringFilePath,newfilepath);
servicemyserver=newservice();
myfunction.AddShuiYinPic(StringFilePath,newfilepath,HttpContext.Current.Server.MapPath(myserver.myweblogo));
}

}
else
throw newException(_xmlhttp.statusText);
}
catch(Exceptionex)
{

}
returnnewfilename;
}
#endregion

替换网页中的换行和引号#region替换网页中的换行和引号
/**//**********************************
*函数名称:ReplaceEnter
*功能说明:替换网页中的换行和引号
*参数:HtmlCode:html源代码
*调用示例:
*GetRemoteObjo=newGetRemoteObj();
*stringUrl=@"http://www.baidu.com";
*stringHtmlCode=o.GetRemoteHtmlCode(Url);
*strings=o.ReplaceEnter(HtmlCode);
*Response.Write(s);
*o.Dispose();
*********************************/
/**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///替换网页中的换行和引号<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// </summary>
/// HTML源代码
/// <returns></returns>
public stringReplaceEnter(stringHtmlCode)
{
strings= "";
if(HtmlCode== null ||HtmlCode== "")
s= "";
else
s=HtmlCode.Replace("\"","");
s=s.Replace("\r","");
s=s.Replace("\n","");
returns;
}

#endregion

执行正则提取出值#region执行正则提取出值
/**//**********************************
*函数名称:GetRegValue
*功能说明:执行正则提取出值
*参数:HtmlCode:html源代码
*调用示例:
*GetRemoteObjo=newGetRemoteObj();
*stringUrl=@"http://www.baidu.com";
*stringHtmlCode=o.GetRemoteHtmlCode(Url);
*strings=o.ReplaceEnter(HtmlCode);
*stringReg="

.+?";
*stringGetValue=o.GetRegValue(Reg,HtmlCode)
*Response.Write(GetValue);
*o.Dispose();
*********************************/
/**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///执行正则提取出值<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// </summary>
/// 正则表达式
/// HtmlCode源代码
/// <returns></returns>
public stringGetRegValue(stringRegexString,stringRemoteStr)
{
stringMatchVale= "";
Regexr= newRegex(RegexString);
Matchm=r.Match(RemoteStr);
if(m.Success)
{
MatchVale=m.Value;
}
returnMatchVale;
}
#endregion

替换HTML源代码#region替换HTML源代码
/**//**********************************
*函数名称:RemoveHTML
*功能说明:替换HTML源代码
*参数:HtmlCode:html源代码
*调用示例:
*GetRemoteObjo=newGetRemoteObj();
*stringUrl=@"http://www.baidu.com";
*stringHtmlCode=o.GetRemoteHtmlCode(Url);
*strings=o.ReplaceEnter(HtmlCode);
*stringReg=".+?";
*stringGetValue=o.GetRegValue(Reg,HtmlCode)
*Response.Write(GetValue);
*o.Dispose();
*********************************/
/**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///替换HTML源代码<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// </summary>
/// html源代码
/// <returns></returns>
public stringRemoveHTML(stringHtmlCode)
{
stringMatchVale=HtmlCode;
foreach(MatchsinRegex.Matches(HtmlCode,"<.>"))<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/dot.gif">{<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">MatchVale=MatchVale.Replace(s.Value,"");<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> returnMatchVale;<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top"> #endregion<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"> 匹配页面的链接#region匹配页面的链接<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"> /**//**********************************<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*函数名称:GetHref<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*功能说明:匹配页面的链接<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*参数:HtmlCode:html源代码<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*调用示例:<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*GetRemoteObjo=newGetRemoteObj();<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*stringUrl=@"http://www.baidu.com";<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*stringHtmlCode=o.GetRemoteHtmlCode(Url);<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*strings=o.GetHref(HtmlCode);<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*Response.Write(s);<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*o.Dispose();<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">*********************************/<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"> /**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///获取页面的链接正则<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// </summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// <param> <br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top"> /// <returns></returns><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> public stringGetHref(stringHtmlCode)<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/dot.gif">{<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> stringMatchVale= "";<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> stringReg= @"(h|H)(r|R)(e|E)(f|F)*=*('|"")?((\w|\\|\/|\.|:|-|_)+)[\S]*";<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> foreach(MatchminRegex.Matches(HtmlCode,Reg))<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/dot.gif">{<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">MatchVale+=(m.Value).ToLower().Replace("href=","").Trim()+ "|";<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> returnMatchVale;<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top"> #endregion<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"> 匹配页面的图片地址#region匹配页面的图片地址<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"> /**//**********************************<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*函数名称:GetImgSrc<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*功能说明:匹配页面的图片地址<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*参数:HtmlCode:html源代码;imgHttp:要补充的http.当比如:<img>则要补充http://www.baidu.com/,当包含http信息时,则可以为空<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*调用示例:<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*GetRemoteObjo=newGetRemoteObj();<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*stringUrl=@"http://www.baidu.com";<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*stringHtmlCode=o.GetRemoteHtmlCode(Url);<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*strings=o.GetImgSrc(HtmlCode,"http://www.baidu.com/");<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*Response.Write(s);<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*o.Dispose();<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">*********************************/<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"> /**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///匹配页面的图片地址<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// </summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// <param> <br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// <param>要补充的http://路径信息<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top"> /// <returns></returns><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> public stringGetImgSrc(stringHtmlCode,stringimgHttp)<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/dot.gif">{<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> stringMatchVale= "";<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> stringReg= @"<img.>";<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> foreach(MatchminRegex.Matches(HtmlCode.ToLower(),Reg))<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/dot.gif">{<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">MatchVale+=GetImg((m.Value).ToLower().Trim(),imgHttp)+ "|";<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> returnMatchVale;<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"> /**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///匹配<img>中的图片路径实际链接<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// </summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// <param> <img>字符串<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top"> /// <returns></returns><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> public stringGetImg(stringImgString,stringimgHttp)<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/dot.gif">{<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> stringMatchVale= "";<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> stringReg= @"src=.+\.(bmp|jpg|gif|png|)";<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> foreach(MatchminRegex.Matches(ImgString.ToLower(),Reg))<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/dot.gif">{<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">MatchVale+=(m.Value).ToLower().Trim().Replace("src=","");<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> if(MatchVale.IndexOf(".net")!= -1 ||MatchVale.IndexOf(".com")!= -1 ||MatchVale.IndexOf(".org")!= -1 ||MatchVale.IndexOf(".cn")!= -1 ||MatchVale.IndexOf(".cc")!= -1 ||MatchVale.IndexOf(".info")!= -1 ||MatchVale.IndexOf(".biz")!= -1 ||MatchVale.IndexOf(".tv")!= -1)<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> return(MatchVale);<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> else<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> return(imgHttp+MatchVale);<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top"> #endregion<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"> 替换通过正则获取字符串所带的正则首尾匹配字符串#region替换通过正则获取字符串所带的正则首尾匹配字符串<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"> /**//**********************************<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*函数名称:GetHref<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*功能说明:匹配页面的链接<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*参数:HtmlCode:html源代码<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*调用示例:<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*GetRemoteObjo=newGetRemoteObj();<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*stringUrl=@"http://www.baidu.com";<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*stringHtmlCode=o.GetRemoteHtmlCode(Url);<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*strings=o.RegReplace(HtmlCode,"<title>","</title>");<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*Response.Write(s);<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">*o.Dispose();<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">*********************************/<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"> /**//// <summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> ///替换通过正则获取字符串所带的正则首尾匹配字符串<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// </summary><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// <param>要替换的值<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// <param>正则匹配的首字符串<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> /// <param>正则匹配的尾字符串<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top"> /// <returns></returns><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> public stringRegReplace(stringRegValue,stringregStart,stringregEnd)<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/dot.gif">{<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> strings=RegValue;<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> if(RegValue!= "" &amp;&amp;RegValue!= null)<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/dot.gif">{<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> if(regStart!= "" &amp;&amp;regStart!= null)<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/dot.gif">{<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">s=s.Replace(regStart,"");<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> if(regEnd!= "" &amp;&amp;regEnd!= null)<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockStart.gif" align="top"><img src="http://www.cnblogs.com/Images/OutliningIndicators/ContractedSubBlock.gif" align="top"><img src="http://www.cnblogs.com/Images/dot.gif">{<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top">s=s.Replace(regEnd,"");<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"> returns;<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top"> #endregion<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedSubBlockEnd.gif" align="top">}<br><img src="http://www.cnblogs.com/Images/OutliningIndicators/InBlock.gif" align="top"><br><img src="http://www.cnblogs.com/Images/OutliningIndicators/ExpandedBlockEnd.gif" align="top">}</img.></.>
分享到:
评论

相关推荐

    asp.net网页数据采集源码

    ASP.NET网页数据采集源码是基于微软的ASP.NET框架实现的一种技术,用于自动化地从互联网上抓取大量信息,特别是新闻、数据等。这个技术通常被称为网络爬虫或Web刮取,是数据科学和大数据分析领域的一个重要工具。在...

    Asp.net 新闻采集器

    【Asp.net 新闻采集器】是一款基于Asp.net技术构建的数据采集工具,主要用于从互联网上抓取新闻信息。...对于有兴趣深入学习Asp.net Web开发和数据采集的用户,可以研究该项目的源代码,提升自己的技术水平。

    asp.net荒野新闻采集系统

    【ASP.NET荒野新闻采集系统】是一个基于ASP.NET技术构建的网络应用,主要用于自动化地抓取、处理和展示互联网上的新闻信息。这个系统利用了ASP.NET框架的强大功能,结合Web编程技术,为用户提供了一个高效、易用的...

    asp.net(C#) 数据采集、抓取

    ASP.NET(C#)数据采集与抓取是一个关键的IT技术领域,主要涉及从网络上获取和处理非结构化或半结构化的数据。在本文中,我们将深入探讨这个主题,了解如何利用C#编程语言和ASP.NET框架进行高效的数据采集和抓取。 ...

    asp.net 文章采集系统 免费放送

    ASP.NET 文章采集系统是一种基于微软的ASP.NET技术构建的软件工具,主要用于自动化地从互联网上获取和整理文章内容。这种系统通常包含了网页抓取、数据解析和存储等多个功能模块,能够帮助用户快速有效地收集和处理...

    asp.net人才招聘管理系统完整版C#源码

    资源名:asp.net人才招聘管理系统完整版C#源码 资源类型:程序源代码 源码说明:本系统是使用MS.NET平台中的ASP.NET开发基于B/S体系结构的Web应用程序,在Microsoft Visual Studio .NET 环境下,使用 C# 编程语言并...

    数据采集源码web版asp.net

    根据提供的信息,我们可以总结出以下有关“数据采集源码web版asp.net”的详细知识点: ### 一、项目背景与概述 此项目名为“数据采集源码web版asp.net”,主要功能在于实现网络上的数据采集。根据描述部分可以推测...

    C#,ASP.NET赶集网信息采集代码.

    很简单的一个程序实现赶集网信息采集!需要的可以下载来看一下.我只提供一部分代码,Webservice自己来吧.

    asp.net + c# 开发网站流量统计系统

    为了深入了解和运行此系统,需要解压文件,查看每个文件夹和文件的详细内容,包括C#代码文件(.cs)、ASP.NET页面(.aspx)、配置文件(.config)、数据库脚本(.sql)等。 总的来说,这个asp.net + C#开发的网站...

    asp.net网站采集与抓取实例

    在本文中,我们将深入探讨如何使用ASP.NET进行网站采集与抓取,以《福布斯中文网-体育娱乐版块》为例。ASP.NET是微软公司推出的一种强大的Web应用程序开发框架,它提供了丰富的功能来构建动态网站和Web服务。在本...

    Asp.net新闻采集器

    【Asp.net新闻采集器】是一种基于微软的Asp.net技术构建的网络应用程序,用于自动抓取、解析和存储特定网站上的新闻数据。新闻采集器的主要功能是对目标网站的新闻内容进行实时或定期的监控,将获取到的信息整理并...

    C#中的Asp.net 数据采集基类

    C#中的Asp.net 数据采集基类(远程抓取,分解,保存,匹配) 分享

    asp.net物联网后台管理系统源码.zip

    2. **MVC(Model-View-Controller)模式**:ASP.NET中的MVC设计模式使得代码结构清晰,有利于团队协作和代码维护。在物联网后台管理中,模型层可能包含设备信息和数据模型,视图层展示数据,控制器层处理用户请求和...

    237ASP.NET电子病历系统

    总结,237ASP.NET电子病历系统是一个综合运用ASP.NET、C#和SQL技术的Web应用,旨在提供便捷的医疗信息管理服务。它涵盖了数据库设计、用户交互、权限控制等多个方面,体现了开发者在Web开发领域的扎实技能。

    .net采集软件(采集插件)

    .NET是由微软公司开发的一种开发平台,它提供了丰富的库和工具,支持多种编程语言如C#、VB.NET等。.NET采集软件则是基于此平台构建的,具备高性能、跨平台等特性,能高效地爬取网页内容并进行数据提取。这类软件通常...

    ASP.NET+H5+Zxing+js+sweetalert2 实现手机端和PC端调用摄像头进行二维码扫一扫

    本程序使用VS2019进行制作,利用ASP.NET+H5+Zxing+js+sweetalert2 实现手机端和PC端调用摄像头进行二维码扫一扫,实现前端采集数据,后端进行分析并向前端传值,pc端可运行,手机端鸿蒙系统,安卓,IOS4.X以上均可...

    C# 数据采集系统 智能采集 数据分析 整套源码

    C# 中的ASP.NET Core框架支持这两种架构,可以创建高性能的服务,并通过服务注册和发现机制实现组件间的解耦。 最后,考虑到系统的部署和监控,可能使用Docker进行容器化部署,以确保环境一致性。同时,日志管理和...

    基于ASP.net的追溯码采集系统源码.zip

    "基于ASP.net的追溯码采集系统源码.zip" 是一个包含源代码的压缩文件,其中的系统是使用ASP.NET技术构建的,主要用于实现追溯码的采集和管理功能。追溯码通常用于追踪产品从生产到销售的全过程,以确保产品质量安全...

    asp.net读取串口数据

    在ASP.NET中实现“读取串口数据”是一个相对复杂但实用的技术点,通常用于实现远程设备监控或者数据采集系统。串口通信(Serial Port Communication)是计算机与外部设备间的一种低速通信方式,常用于连接串行设备如...

    Asp.net房产采集系统Ajax版源码

    【Asp.net房产采集系统Ajax版源码】是一款基于ASP.NET技术开发的高效网页数据抓取和处理系统,主要用于收集和整理房地产领域的相关信息。该系统利用Ajax技术实现了页面的无刷新交互,提升了用户体验,同时也降低了...

Global site tag (gtag.js) - Google Analytics