C# : 網路爬蟲 (Crawler) 的設計 - 免費電子書：C# 程式設計

原始程式

using System;
using System.Collections;
using System.Collections.Generic;
using System.Text;
using System.IO;
using System.Net;
using System.Text.RegularExpressions;

class WebCrawler
{
//    WebProxy proxy = new WebProxy("http://proxy.internal:3128/", true);
    List<String> urlList = new List<String>();
    // Dictionary<String, String> 

    public static void Main(String[] args)
    {
        WebCrawler crawler = new WebCrawler();
        crawler.urlList.Add("http://tw.msn.com/");
        crawler.craw();
    }

    public void craw()
    {
        int urlIdx = 0;
        while (urlIdx < urlList.Count)
        {
            try
            {
                String url = urlList[urlIdx];
                String fileName = "data/" + toFileName(url);
                Console.WriteLine(urlIdx + ":url=" + url + " file=" + fileName);
                urlToFile(url, fileName);
                String html = fileToText(fileName);
                foreach (String childUrl in matches("\\shref\\s*=\\s*\"(.*?)\"", html, 1))
                {
                    Console.WriteLine(childUrl);
                    urlList.Add(childUrl);
                }
            }
            catch
            {
                Console.WriteLine("Error:" + urlList[urlIdx] + " fail!");
            }
            urlIdx++;
        }
    }

    public static IEnumerable matches(String pPattern, String pText, int pGroupId)
    {
        Regex r = new Regex(pPattern, RegexOptions.IgnoreCase | RegexOptions.Compiled);
        for (Match m = r.Match(pText); m.Success; m = m.NextMatch())
         yield return m.Groups[pGroupId].Value;
    }

    public static String fileToText(String filePath)
    {
        StreamReader file = new StreamReader(filePath);
        String text = file.ReadToEnd();
        file.Close();
        return text;
    }

    public void urlToFile(String url, String file)
    {
        WebClient webclient = new WebClient();
//        webclient.Proxy = proxy;
        webclient.DownloadFile(url, file);
    }

    public static String toFileName(String url)
    {
        String fileName = url.Replace('?', '_');
        fileName = fileName.Replace('/', '_');
        fileName = fileName.Replace('&', '_');
        fileName = fileName.Replace(':', '_');
        fileName = fileName.ToLower();
        if (!fileName.EndsWith(".htm") && !fileName.EndsWith(".html"))
         fileName = fileName + ".htm";
        return fileName;
    }
}

老師你好! 請問這個範例, 假如是需要輸入帳號密碼的網站呢

有無辦法透過cookie 去騙取呢謝謝

Other interesting sites

作者：陳鍾誠

簡介

原始程式

Post preview:

Other interesting sites