数据采集Interop.MSXML2.dll引用
using System;
using System.Data;
using System.Configuration;
using System.Web;
using System.Web.Security;
using System.Web.UI;
using System.Web.UI.WebControls;
using System.Web.UI.WebControls.WebParts;
using System.Web.UI.HtmlControls;
using MSXML2;
using System.Text.RegularExpressions;
/// <summary>
/// ASP.NET数据采集封装注意：记得添加引用 Interop.MSXML2.dll 否则msxml2命名空间用不了 COM组件Interop.MSXML2.dll则COM的引用列表中的Microsoft.xml v3.0
/// </summary>
public class Search
{
public Search()
{
//
// TODO: 在此处添加构造函数逻辑
//
}
public void Dispose()
{
GC.SuppressFinalize(this);
}
#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:
* GetRemoteObj o = new GetRemoteObj();
* Random ra = new Random();
* string s = o.DateRndName(ra);
* Response.Write(s);
* o.Dispose();
* ********************************/
/// <summary>
/// 日期随机函数
/// </summary>
/// <param name="ra">随机数</param>
/// <returns></returns>
public string DateRndName(Random ra)
{
DateTime d = DateTime.Now;
string s = null, y, m, dd, h, mm, ss;
y = d.Year.ToString();
m = d.Month.ToString();
if (m.Length < 2) m = "0" + m;
dd = d.Day.ToString();
if (dd.Length < 2) dd = "0" + dd;
h = d.Hour.ToString();
if (h.Length < 2) h = "0" + h;
mm = d.Minute.ToString();
if (mm.Length < 2) mm = "0" + mm;
ss = d.Second.ToString();
if (ss.Length < 2) ss = "0" + ss;
s += y + m + dd + h + mm + ss;
s += ra.Next(100, 999).ToString();
return s;
}
#endregion
#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:
* GetRemoteObj o = new GetRemoteObj();
* string url = @"http://www.baidu.com/img/logo.gif";
* string s = o.GetFileExtends(url);
* Response.Write(s);
* o.Dispose();
* ********************************/
/// <summary>
/// 取得文件后缀
/// </summary>
/// <param name="filename">文件名称</param>
/// <returns></returns>
public string GetFileExtends(string filename)
{
string ext = null;
if (filename.IndexOf('.') > 0)
{
string[] fs = filename.Split('.');
ext = fs[fs.Length - 1];
}
return ext;
}
#endregion
#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:
* GetRemoteObj o = new GetRemoteObj();
* string url = @"http://www.baidu.com/";
* string s = o.GetRemoteHtmlCode(url);
* Response.Write(s);
* o.Dispose();
* ********************************/
/// <summary>
/// 获取远程文件源代码
/// </summary>
/// <param name="url">远程url</param>
/// <returns></returns>
public string GetRemoteHtmlCode(string Url)
{
string s = "";
try
{
MSXML2.XMLHTTP _xmlhttp = new MSXML2.XMLHTTPClass();
_xmlhttp.open("GET", Url, false, null, null);
_xmlhttp.send("");
if (_xmlhttp.readyState == 4)
{
s = System.Text.Encoding.Default.GetString((byte[])_xmlhttp.responseBody);
}
}
catch (Exception ex)
{
s = ex.Message+"指定的地址不存在或地址错误";
}
return s;
}
#endregion
#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:
* GetRemoteObj o = new GetRemoteObj();
* string s = "";
* string url = @"http://www.baidu.com/img/logo.gif";
* string path =Server.MapPath("Html/");
* s = o.RemoteSave(url,path);
* Response.Write(s);
* o.Dispose();
* ******************************/
/// <summary>
/// 保存远程文件
/// </summary>
/// <param name="Url">远程url</param>
/// <param name="Path">保存到的路径</param>
/// <returns></returns>
public string RemoteSave(string Url, string Path)
{
Random ra = new Random();
string StringFileName = DateRndName(ra) + "." + GetFileExtends(Url);
string StringFilePath = Path + StringFileName;
MSXML2.XMLHTTP _xmlhttp = new MSXML2.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.FileStream fs = new System.IO.FileStream(StringFilePath, System.IO.FileMode.CreateNew);
System.IO.BinaryWriter w = new System.IO.BinaryWriter(fs);
w.Write((byte[])_xmlhttp.responseBody);
w.Close();
fs.Close();
}
else
throw new Exception(_xmlhttp.statusText);
return StringFileName;
}
#endregion
#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:
* GetRemoteObj o = new GetRemoteObj();
* string Url = @"http://www.baidu.com/";
* strion HtmlCode = o.GetRemoteHtmlCode(Url);
* string s = o.ReplaceEnter(HtmlCode);
* Response.Write(s);
* o.Dispose();
* ********************************/
/// <summary>
/// 替换网页中的换行和引号
/// </summary>
/// <param name="HtmlCode">HTML源代码</param>
/// <returns></returns>
public string ReplaceEnter(string HtmlCode)
{
string s = "";
if (HtmlCode == null || HtmlCode == "")
s = "";
else
s = HtmlCode.Replace("\"", "");
s = s.Replace("\r\n", "");
return s;
}
#endregion
#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:
* GetRemoteObj o = new GetRemoteObj();
* string Url = @"http://www.baidu.com/";
* strion HtmlCode = o.GetRemoteHtmlCode(Url);
* string s = o.ReplaceEnter(HtmlCode);
* string Reg="<title>.+?</title>";
* string GetValue=o.GetRegValue(Reg,HtmlCode)
* Response.Write(GetValue);
* o.Dispose();
* ********************************/
/// <summary>
/// 执行正则提取出值
/// </summary>
/// <param name="RegexString">正则表达式</param>
/// <param name="RemoteStr">HtmlCode源代码</param>
/// <returns></returns>
public string GetRegValue(string RegexString, string RemoteStr)
{
string MatchVale = "";
Regex r = new Regex(RegexString);
Match m = r.Match(RemoteStr);
if (m.Success)
{
MatchVale = m.Value;
}
return MatchVale;
}
#endregion
#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:
* GetRemoteObj o = new GetRemoteObj();
* string Url = @"http://www.baidu.com/";
* strion HtmlCode = o.GetRemoteHtmlCode(Url);
* string s = o.ReplaceEnter(HtmlCode);
* string Reg="<title>.+?</title>";
* string GetValue=o.GetRegValue(Reg,HtmlCode)
* Response.Write(GetValue);
* o.Dispose();
* ********************************/
/// <summary>
/// 替换HTML源代码
/// </summary>
/// <param name="HtmlCode">html源代码</param>
/// <returns></returns>
public string RemoveHTML(string HtmlCode)
{
string MatchVale = HtmlCode;
foreach (Match s in Regex.Matches(HtmlCode, "<.+?>"))
{
MatchVale = MatchVale.Replace(s.Value, "");
}
return MatchVale;
}
#endregion
#region 匹配页面的链接
/**********************************
* 函数名称:GetHref
* 功能说明:匹配页面的链接
* 参 数:HtmlCode:html源代码
* 调用示例:
* GetRemoteObj o = new GetRemoteObj();
* string Url = @"http://www.baidu.com/";
* strion HtmlCode = o.GetRemoteHtmlCode(Url);
* string s = o.GetHref(HtmlCode);
* Response.Write(s);
* o.Dispose();
* ********************************/
/// <summary>
/// 获取页面的链接正则
/// </summary>
/// <param name="HtmlCode"></param>
/// <returns></returns>
public string GetHref(string HtmlCode)
{
string MatchVale = "";
string Reg = @"(h|H)(r|R)(e|E)(f|F) *= *('|"")?((\w|\\|\/|\.|:|-|_)+)('|""| *|>)?";
foreach (Match m in Regex.Matches(HtmlCode, Reg))
{
MatchVale += (m.Value).ToLower().Replace("href=", "").Trim() + "||";
}
return MatchVale;
}
#endregion
#region 匹配页面的图片地址
/**********************************
* 函数名称:GetImgSrc
* 功能说明:匹配页面的图片地址
* 参 数:HtmlCode:html源代码;imgHttp:要补充的http.当比如:<img src="bb/x.gif">则要补充http://www.baidu.com/,当包含http信息时,则可以为空
* 调用示例:
* GetRemoteObj o = new GetRemoteObj();
* string Url = @"http://www.baidu.com/";
* strion HtmlCode = o.GetRemoteHtmlCode(Url);
* string s = o.GetImgSrc(HtmlCode,"http://www.baidu.com/");
* Response.Write(s);
* o.Dispose();
* ********************************/
/// <summary>
/// 匹配页面的图片地址
/// </summary>
/// <param name="HtmlCode"></param>
/// <param name="imgHttp">要补充的http://路径信息</param>
/// <returns></returns>
public string GetImgSrc(string HtmlCode, string imgHttp)
{
string MatchVale = "";
string Reg = @"<img.+?>";
foreach (Match m in Regex.Matches(HtmlCode, Reg))
{
MatchVale += GetImg((m.Value).ToLower().Trim(), imgHttp) + "||";
}
return MatchVale;
}
/// <summary>
/// 匹配<img src="" />中的图片路径实际链接
/// </summary>
/// <param name="ImgString"><img src="" />字符串</param>
/// <returns></returns>
public string GetImg(string ImgString, string imgHttp)
{
string MatchVale = "";
string Reg = @"src=.+\.(bmp|jpg|gif|png|)";
foreach (Match m in Regex.Matches(ImgString.ToLower(), Reg))
{
MatchVale += (m.Value).ToLower().Trim().Replace("src=", "");
}
return (imgHttp + MatchVale);
}
#endregion
#region 替换通过正则获取字符串所带的正则首尾匹配字符串
/**********************************
* 函数名称:GetHref
* 功能说明:匹配页面的链接
* 参 数:HtmlCode:html源代码
* 调用示例:
* GetRemoteObj o = new GetRemoteObj();
* string Url = @"http://www.baidu.com/";
* strion HtmlCode = o.GetRemoteHtmlCode(Url);
* string s = o.RegReplace(HtmlCode,"<title>","</title>");
* Response.Write(s);
* o.Dispose();
* ********************************/
/// <summary>
/// 替换通过正则获取字符串所带的正则首尾匹配字符串
/// </summary>
/// <param name="RegValue">要替换的值</param>
/// <param name="regStart">正则匹配的首字符串</param>
/// <param name="regEnd">正则匹配的尾字符串</param>
/// <returns></returns>
public string RegReplace(string RegValue, string regStart, string regEnd)
{
string s = RegValue;
if (RegValue != "" && RegValue != null)
{
if (regStart != "" && regStart != null)
{
s = s.Replace(regStart, "");
}
if (regEnd != "" && regEnd != null)
{
s = s.Replace(regEnd, "");
}
}
return s;
}
/********************************** 以下为测试过的,在魏言项目里使用的采集方法.按方法顺序调用既可采集
* 函数名称:SniffwebCode
* 功能说明:获得页面HTML代码中开始标记和结束标记中间的数据:测试可用
* 参 数:HTML源代码 ,开始标记,结束标记
* 调用示例:
*string url = @"http://sohe.inhe.net/Search/SearchingGuild.aspx";
*string s = o.GetRemoteHtmlCode(url);//获得网站源码
*s=this.SniffwebCode(s,this.TextBox2.Text,this.TextBox3.Text);//获得指定HTML开始标记和结束标记中间的数据
* ********************************/
/// <summary>
/// 获得HTML代码开始标记和结束标记中间的数据
/// </summary>
/// <param name="code">HTML代码</param>
/// <param name="wordsBegin">开始标记</param>
/// <param name="wordsEnd">结束标记</param>
/// <returns></returns>
public string SniffwebCode(string code, string wordsBegin, string wordsEnd)
{
string NewsTitle = "";
Regex regex1 = new Regex("" + wordsBegin + @"(?<title>[\s\S]+?)" +
wordsEnd + "", RegexOptions.Compiled | RegexOptions.IgnoreCase);
for (Match match1 = regex1.Match(code); match1.Success; match1 = match1.NextMatch())
{
NewsTitle = match1.Groups["title"].ToString();
}
return NewsTitle;
}
/*** 调用例子 获得指定Html代码中所有超级连接的标题和连接地址:测试有效 反回DataTable列说明:title 文字 url 地址
* string url = @"http://sohe.inhe.net/Search/SearchingGuild.aspx";
* string HtmlAllCode = o.GetRemoteHtmlCode(url);//获得网站所有源码
* HtmlAllCode = o.SniffwebCode(HtmlAllCode, this.TextBox2.Text, this.TextBox3.Text);//根据开始标记和结束标记获得中间的数据
* DataTable table = o.GetCodeHref(HtmlAllCode);//获得指定Html所有超级连接的标题和连接地址返回一个DataTable表
* foreach(DataRow row in table.Rows)//循环表输出标题和连接
* {
* Response.Write(row["title"]+"<br>");
* Response.Write(row["url"] + "<br>");
* }
*/
/// <summary>
/// 获得指定Html代码中所有超级连接的标题和连接地址:测试有效 反回DataTable列说明:title 文字 url 地址
/// </summary>
/// <param name="HtmlCode">需要匹配出超级连接的HTML代码</param>
/// <returns></returns>
public DataTable GetCodeHref(string HtmlCode)
{
//匹配指定HTML代码中所有的超级连接中的href 和超连接文字内容的正则 有时候需要根据实际情况做小调整如果标题中间有<B>文字</B>的话
string regex =
@"\<a.*href\s*=\s*(?:""(?<url>[^""]*)""|'(?<url>[^']*)'|(?<url>[^\>^\s]+)).*\>(?<title>[^\<^\>]*)\<[^\</a\>]*/a\>";
Regex reg1 = new Regex(regex, RegexOptions.IgnoreCase);//创建正则表达式对象
MatchCollection ms1 = reg1.Matches(HtmlCode);//根据正则表达式匹配出所有匹配项返匹配集合
DataTable table = new DataTable();//创建存储标题和连接的内存表
table.Columns.Add("title");//标题文字列
table.Columns.Add("url");//连接字符串
foreach (Match m1 in ms1)//迭代集合获得每个匹配项
{
DataRow row = table.NewRow();//创建一行
row["title"] = m1.Groups["title"].Value.ToString();
row["url"] = m1.Groups["url"].Value.ToString();
table.Rows.Add(row);//添加入行集合
}
return table;
}
#endregion
}
