提取网页中的javascript脚本和下载链接

　　网上有个不错的视频教程，是swf格式的，想下载下来，但是网页太多了，每次打开网页查看源码再定位到那么JavaScript块，复制粘贴，好不繁琐。于是就想通过程序来减少工作量。

程序功能：批量提取网页中的Javascript脚本，提取脚本中的视频下载链接信息。

首先通过网络请求网页，得到响应的流文件，通过正则表达式匹配提取其中的JavaScript脚本块。再匹配提出Url下载链接。

using System;
using System.Collections.Generic;
using System.ComponentModel;
using System.Data;
using System.Drawing;
using System.Linq;
using System.Text;
using System.Windows.Forms;
using System.Net;
using System.IO;
using System.Text.RegularExpressions;
namespace CsWebBrower
{
public partial class GetUri : Form
{
public GetUri()
{
InitializeComponent();
}

private void button1_Click(object sender, EventArgs e)
{
string[] strs = textBox1.Lines;
foreach (string str in strs)
{
Uri uri = new Uri(str);

WebRequest req = WebRequest.Create(uri);

WebResponse result = req.GetResponse();
Stream ReceiveStream = result.GetResponseStream();
StreamReader readerOfStream = new StreamReader(ReceiveStream,
System.Text.Encoding.GetEncoding("UTF-8"));
string temp = readerOfStream.ReadToEnd();
//Regex ex = new Regex("<script.+?type ?= ?(/\"|')text/javascript(/\"|')>.*?</script>",
//RegexOptions.Singleline);
MatchCollection mc = Regex.Matches(temp, @"<script[^>]*>[\s\S]*?</script>", RegexOptions.IgnoreCase);
foreach (Match m in mc)
{

//MatchCollection mc2 = Regex.Matches(m.Value, @"http://([\w-]+\.)+[\w-]+(/[\w- ./?%&=]*)?", RegexOptions.IgnoreCase);[a-zA-z]+://[^\s]*
MatchCollection mc2 = Regex.Matches(m.Value, @"http://[\s\S]*?.swf", RegexOptions.IgnoreCase);
foreach (Match m2 in mc2)
{
richTextBox1.Text += m2.Value + "\n\n";
}

}
readerOfStream.Close();
ReceiveStream.Close();

}
}
}
}