批量抓取网页代码中的HTTP和邮件地址,IO,正则表达式,抓网页源码
2006-08-23 17:28
706 查看
上个星期开会说现在中国的垃圾邮件很赚钱啊。我也很想多赚点钱。不过做技术的都很死板。脑壳不灵活。只能多研究研究一些方法来实现这样子那样的程序代码,搜集整理的两天。终于找到自己想要的代码。不很完善多多改进就好了。
using System.IO;
using System.Text.RegularExpressions;
public string GetPageContent(string url)
{
//抓取网页源代码
string ContentHtml=String.Empty;
HttpWebRequest rt=null;
HttpWebResponse rs=null;
Stream stream=null;
StreamReader sr=null;
rt=(HttpWebRequest)WebRequest.Create(url);
rs=(HttpWebResponse)rt.GetResponse();
stream=rs.GetResponseStream();
sr=new StreamReader(stream,System.Text.Encoding.Default);
ContentHtml=sr.ReadToEnd();
sr.Close();
stream.Close();
rs.Close();
return ContentHtml;
}
public string SetHttpUrl(string StrText)
{
//用正则表达式识别URL超链接
Regex UrlRegex = new Regex(@"(http:////([/w.]+//?)/S*)", RegexOptions.IgnoreCase | RegexOptions.Compiled);
//进规则查询Url
MatchCollection matches = UrlRegex.Matches(StrText);
foreach (Match match in matches)
{
StrText = StrText.Replace(match.Value, string.Format("<a href=/"{0}/" target=/"_blank/">{1}</a>", match.Value, match.Value));
}
return StrText;
}
public string SetEmailUrl(string StrText)
{
//用正则表达式识别Email地址
Regex EmailRegex = new Regex(@"([a-zA-Z_0-9.-]+/@[a-zA-Z_0-9.-]+/./w+)", RegexOptions.IgnoreCase | RegexOptions.Compiled);
MatchCollection matches = EmailRegex.Matches(StrText);
foreach (Match match in matches)
{
StrText = StrText.Replace(match.Value, string.Format("<a href=mailto:{0}>{1}</a>", match.Value, match.Value));
}
return StrText;
}
public string GetHttpUrl(string StrText)
{
//将读取出来的全部URL写如文本文件
string strPageUrlFileName=Application.StartupPath+"//HttpPageUrl.txt";
StreamWriter strwriterobj=File.CreateText(strPageUrlFileName);
//用正则表达式识别URL超链接进规则查询Url
Regex UrlRegex = new Regex(@"(http:////([/w.]+//?)/S*)", RegexOptions.IgnoreCase | RegexOptions.Compiled);
MatchCollection matches = UrlRegex.Matches(StrText);
foreach (Match match in matches)
{
lstHttp.Items.Add(match.Value.ToString());
strwriterobj.WriteLine(match.Value.ToString());
}
strwriterobj.Close();
return StrText;
}
public string GetEmailUrl(string StrText)
{
//将读取出来的全部URL写如文本文件
string strPageEmailFileName=Application.StartupPath+"//HttpPageEmail.txt";
StreamWriter strwriterobj=File.CreateText(strPageEmailFileName);
//用正则表达式识别Email地址
Regex EmailRegex = new Regex(@"([a-zA-Z_0-9.-]+/@[a-zA-Z_0-9.-]+/./w+)", RegexOptions.IgnoreCase | RegexOptions.Compiled);
MatchCollection matches = EmailRegex.Matches(StrText);
foreach (Match match in matches)
{
lstEmail.Items.Add(match.Value.ToString());
strwriterobj.WriteLine(match.Value.ToString());
}
strwriterobj.Close();
return StrText;
}
批量抓取网页代码中的HTTP和邮件地址,IO,正则表达式,抓网页源码
using System.IO;
using System.Text.RegularExpressions;
public string GetPageContent(string url)
{
//抓取网页源代码
string ContentHtml=String.Empty;
HttpWebRequest rt=null;
HttpWebResponse rs=null;
Stream stream=null;
StreamReader sr=null;
rt=(HttpWebRequest)WebRequest.Create(url);
rs=(HttpWebResponse)rt.GetResponse();
stream=rs.GetResponseStream();
sr=new StreamReader(stream,System.Text.Encoding.Default);
ContentHtml=sr.ReadToEnd();
sr.Close();
stream.Close();
rs.Close();
return ContentHtml;
}
public string SetHttpUrl(string StrText)
{
//用正则表达式识别URL超链接
Regex UrlRegex = new Regex(@"(http:////([/w.]+//?)/S*)", RegexOptions.IgnoreCase | RegexOptions.Compiled);
//进规则查询Url
MatchCollection matches = UrlRegex.Matches(StrText);
foreach (Match match in matches)
{
StrText = StrText.Replace(match.Value, string.Format("<a href=/"{0}/" target=/"_blank/">{1}</a>", match.Value, match.Value));
}
return StrText;
}
public string SetEmailUrl(string StrText)
{
//用正则表达式识别Email地址
Regex EmailRegex = new Regex(@"([a-zA-Z_0-9.-]+/@[a-zA-Z_0-9.-]+/./w+)", RegexOptions.IgnoreCase | RegexOptions.Compiled);
MatchCollection matches = EmailRegex.Matches(StrText);
foreach (Match match in matches)
{
StrText = StrText.Replace(match.Value, string.Format("<a href=mailto:{0}>{1}</a>", match.Value, match.Value));
}
return StrText;
}
public string GetHttpUrl(string StrText)
{
//将读取出来的全部URL写如文本文件
string strPageUrlFileName=Application.StartupPath+"//HttpPageUrl.txt";
StreamWriter strwriterobj=File.CreateText(strPageUrlFileName);
//用正则表达式识别URL超链接进规则查询Url
Regex UrlRegex = new Regex(@"(http:////([/w.]+//?)/S*)", RegexOptions.IgnoreCase | RegexOptions.Compiled);
MatchCollection matches = UrlRegex.Matches(StrText);
foreach (Match match in matches)
{
lstHttp.Items.Add(match.Value.ToString());
strwriterobj.WriteLine(match.Value.ToString());
}
strwriterobj.Close();
return StrText;
}
public string GetEmailUrl(string StrText)
{
//将读取出来的全部URL写如文本文件
string strPageEmailFileName=Application.StartupPath+"//HttpPageEmail.txt";
StreamWriter strwriterobj=File.CreateText(strPageEmailFileName);
//用正则表达式识别Email地址
Regex EmailRegex = new Regex(@"([a-zA-Z_0-9.-]+/@[a-zA-Z_0-9.-]+/./w+)", RegexOptions.IgnoreCase | RegexOptions.Compiled);
MatchCollection matches = EmailRegex.Matches(StrText);
foreach (Match match in matches)
{
lstEmail.Items.Add(match.Value.ToString());
strwriterobj.WriteLine(match.Value.ToString());
}
strwriterobj.Close();
return StrText;
}
批量抓取网页代码中的HTTP和邮件地址,IO,正则表达式,抓网页源码
相关文章推荐
- 批量抓取网页代码中的HTTP和邮件地址,IO,正则表达式,抓网页源码
- Java正则表达式,抓取网页email地址实例
- 正则表达式抓取网页中的邮箱地址
- Python抓取网页&批量下载文件方法初探(正则表达式+BeautifulSoup) (转)
- php结合正则批量抓取网页中邮箱地址
- Java正则表达式,抓取网页email地址实例
- 正则表达式-网页爬虫-从服务器或本地文件获取邮件地址
- 使用正则表达式写一个网页爬虫案例获取指定文档中的邮件地址保存到自己指定的文件夹中
- 正则表达式的威力5_网页爬虫,爬邮件地址
- 利用正则表达式统计代码中的(代码行数,注释行数,空白行数)利用正则表达式获取一个网页中所有的邮箱地址
- 正则表达式——抓取网页中的http及网络图片
- Python抓取网页&批量下载文件方法初探(正则表达式+BeautifulSoup)
- 笨笨图片批量抓取下载 V0.2 beta[C# | WinForm | 正则表达式 | HttpWebRequest | Async异步编程]
- C# 正则表达式抓取网页上某个标签的内容,并替换链接地址和图片地址
- 正则表达式抓取文件内容中的http链接地址
- php结合正则批量抓取网页中邮箱地址
- Java正则表达式(一)、抓取网页email地址实例
- Java正则表达式学习笔记,分离网页邮件地址的蜘蛛程序
- Java正则表达式(一)、抓取网页email地址实例
- Python抓取网页&批量下载文件方法初探(正则表达式+BeautifulSoup)