爬虫 source <转>

Spidr 是一个Ruby 的网页爬虫库，可以将整个网站、多个网站、某个链接完全抓取到本地。

http://opensource.youkuaiyun.com/p/spidr

网页爬虫汇总，值得收藏

http://apps.hi.baidu.com/share/detail/105705

wiki

http://wiki.blueidea.com/index.php?title=%E7%88%AC%E8%99%AB&diff=6679&oldid=prev

超简单的Web爬虫程序（转贴）&网页爬虫

http://www.lydia-diamond.com/pachong/20100313/vaz8w2z5f1q255972593.html

package test;
/**
 * @author Jack.Wang
 *
 */
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.HashSet;
import java.util.LinkedHashSet;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

// 搜索Web爬行者
public class SearchCrawler implements Runnable {

 /*
  * disallowListCache缓存robot不允许搜索的URL。 Robot协议在Web站点的根目录下设置一个robots.txt文件,
  * 规定站点上的哪些页面是限制搜索的。
  * 搜索程序应该在搜索过程中跳过这些区域,下面是robots.txt的一个例子:
  * # robots.txt for http://somehost.com/ User-agent:
  * Disallow: /cgi-bin/
  * Disallow: /registration # Disallow robots on registration page
  * Disallow: /login
  */

 private HashMap<String, ArrayList<String>> disallowListCache = new HashMap<String, ArrayList<String>>();
 ArrayList<String> errorList = new ArrayList<String>();// 错误信息
 ArrayList<String> result = new ArrayList<String>(); // 搜索到的结果
 String startUrl;// 开始搜索的起点
 int maxUrl;// 最大处理的url数
 String searchString;// 要搜索的字符串(英文)
 boolean caseSensitive = false;// 是否区分大小写
 boolean limitHost = false;// 是否在限制的主机内搜索

 public SearchCrawler(String startUrl, int maxUrl, String searchString) {
  this.startUrl = startUrl;
  this.maxUrl = maxUrl;
  this.searchString = searchString;
 }

 public ArrayList<String> getResult() {
  return result;
 }

 public void run() {// 启动搜索线程
  crawl(startUrl, maxUrl, searchString, limitHost, caseSensitive);
 }

 // 检测URL格式
 private URL verifyUrl(String url) {
  // 只处理HTTP URLs.
  if (!url.toLowerCase().startsWith("http://"))
   return null;
  URL verifiedUrl = null;
  try {
   verifiedUrl = new URL(url);
  } catch (Exception e) {
   return null;
  }
  return verifiedUrl;
 }

 // 检测robot是否允许访问给出的URL.
 private boolean isRobotAllowed(URL urlToCheck) {
  String host = urlToCheck.getHost().toLowerCase();// 获取给出RUL的主机
  // System.out.println("主机="+host);

  // 获取主机不允许搜索的URL缓存
  ArrayList<String> disallowList = disallowListCache.get(host);

  // 如果还没有缓存,下载并缓存。
  if (disallowList == null) {
   disallowList = new ArrayList<String>();
   try {
    URL robotsFileUrl = new URL("http://" + host + "/robots.txt");
    BufferedReader reader = new BufferedReader(
      new InputStreamReader(robotsFileUrl.openStream()));

    // 读robot文件，创建不允许访问的路径列表。
    String line;
    while ((line = reader.readLine()) != null) {
     if (line.indexOf("Disallow:") == 0) {// 是否包含"Disallow:"
      String disallowPath = line.substring("Disallow:"
        .length());// 获取不允许访问路径

      // 检查是否有注释。
      int commentIndex = disallowPath.indexOf("#");
      if (commentIndex != -1) {
       disallowPath = disallowPath.substring(0,
         commentIndex);// 去掉注释
      }

      disallowPath = disallowPath.trim();
      disallowList.add(disallowPath);
     }
    }

    // 缓存此主机不允许访问的路径。
    disallowListCache.put(host, disallowList);
   } catch (Exception e) {
    return true; // web站点根目录下没有robots.txt文件,返回真
   }
  }

  String file = urlToCheck.getFile();
  // System.out.println("文件getFile()="+file);
  for (int i = 0; i < disallowList.size(); i++) {
   String disallow = disallowList.get(i);
   if (file.startsWith(disallow)) {
    return false;
   }
  }

  return true;
 }

 private String downloadPage(URL pageUrl) {
  try {
   // Open connection to URL for reading.
   BufferedReader reader = new BufferedReader(new InputStreamReader(
     pageUrl.openStream()));

   // Read page into buffer.
   String line;
   StringBuffer pageBuffer = new StringBuffer();
   while ((line = reader.readLine()) != null) {
    pageBuffer.append(line);
   }

   return pageBuffer.toString();
  } catch (Exception e) {
  }

  return null;
 }

 // 从URL中去掉"www"
 private String removeWwwFromUrl(String url) {
  int index = url.indexOf("://www.");
  if (index != -1) {
   return url.substring(0, index + 3) + url.substring(index + 7);
  }

  return (url);
 }

 // 解析页面并找出链接
 private ArrayList<String> retrieveLinks(URL pageUrl, String pageContents,
   HashSet crawledList, boolean limitHost) {
  // 用正则表达式编译链接的匹配模式。
  Pattern p = Pattern.compile("<a\\s+href\\s*=\\s*\"?(.*?)[\"|>]",
    Pattern.CASE_INSENSITIVE);
  Matcher m = p.matcher(pageContents);

  ArrayList<String> linkList = new ArrayList<String>();
  while (m.find()) {
   String link = m.group(1).trim();

   if (link.length() < 1) {
    continue;
   }

   // 跳过链到本页面内链接。
   if (link.charAt(0) == '#') {
    continue;
   }

   if (link.indexOf("mailto:") != -1) {
    continue;
   }

   if (link.toLowerCase().indexOf("javascript") != -1) {
    continue;
   }

   if (link.indexOf("://") == -1) {
    if (link.charAt(0) == '/') {// 处理绝对地
     link = "http://" + pageUrl.getHost() + ":"
       + pageUrl.getPort() + link;
    } else {
     String file = pageUrl.getFile();
     if (file.indexOf('/') == -1) {// 处理相对地址
      link = "http://" + pageUrl.getHost() + ":"
        + pageUrl.getPort() + "/" + link;
     } else {
      String path = file.substring(0,
        file.lastIndexOf('/') + 1);
      link = "http://" + pageUrl.getHost() + ":"
        + pageUrl.getPort() + path + link;
     }
    }
   }

   int index = link.indexOf('#');
   if (index != -1) {
    link = link.substring(0, index);
   }

   link = removeWwwFromUrl(link);

   URL verifiedLink = verifyUrl(link);
   if (verifiedLink == null) {
    continue;
   }

   /* 如果限定主机，排除那些不合条件的URL */
   if (limitHost
     && !pageUrl.getHost().toLowerCase().equals(
       verifiedLink.getHost().toLowerCase())) {
    continue;
   }

   // 跳过那些已经处理的链接.
   if (crawledList.contains(link)) {
    continue;
   }

   linkList.add(link);
  }

  return (linkList);
 }

 // 搜索下载Web页面的内容，判断在该页面内有没有指定的搜索字符串

 private boolean searchStringMatches(String pageContents,
   String searchString, boolean caseSensitive) {
  String searchContents = pageContents;
  if (!caseSensitive) {// 如果不区分大小写
   searchContents = pageContents.toLowerCase();
  }

  Pattern p = Pattern.compile("[\\s]+");
  String[] terms = p.split(searchString);
  for (int i = 0; i < terms.length; i++) {
   if (caseSensitive) {
    if (searchContents.indexOf(terms[i]) == -1) {
     return false;
    }
   } else {
    if (searchContents.indexOf(terms[i].toLowerCase()) == -1) {
     return false;
    }
   }
  }

  return true;
 }

 // 执行实际的搜索操作
 public ArrayList<String> crawl(String startUrl, int maxUrls,
   String searchString, boolean limithost, boolean caseSensitive) {

  HashSet<String> crawledList = new HashSet<String>();
  LinkedHashSet<String> toCrawlList = new LinkedHashSet<String>();

  if (maxUrls < 1) {
   errorList.add("Invalid Max URLs value.");
   System.out.println("Invalid Max URLs value.");
  }

  if (searchString.length() < 1) {
   errorList.add("Missing Search String.");
   System.out.println("Missing search String");
  }

  if (errorList.size() > 0) {
   System.out.println("err!!!");
   return errorList;
  }

  // 从开始URL中移出www
  startUrl = removeWwwFromUrl(startUrl);

  toCrawlList.add(startUrl);
  while (toCrawlList.size() > 0) {

   if (maxUrls != -1) {
    if (crawledList.size() == maxUrls) {
     break;
    }
   }

   // Get URL at bottom of the list.
   String url = toCrawlList.iterator().next();

   // Remove URL from the to crawl list.
   toCrawlList.remove(url);

   // Convert string url to URL object.
   URL verifiedUrl = verifyUrl(url);

   // Skip URL if robots are not allowed to access it.
   if (!isRobotAllowed(verifiedUrl)) {
    continue;
   }

   // 增加已处理的URL到crawledList
   crawledList.add(url);
   String pageContents = downloadPage(verifiedUrl);

   if (pageContents != null && pageContents.length() > 0) {
    // 从页面中获取有效的链接
    ArrayList<String> links = retrieveLinks(verifiedUrl,
      pageContents, crawledList, limitHost);

    toCrawlList.addAll(links);

    if (searchStringMatches(pageContents, searchString,
      caseSensitive)) {
     result.add(url);
     System.out.println(url);
    }
   }

  }
  return result;
 }

 // 主函数
 public static void main(String[] args) {
  SearchCrawler crawler = new SearchCrawler("http://www.blogjava.net/Jack2007/", 20,"jack");
  Thread search = new Thread(crawler);
  System.out.println("Start searching...");
  System.out.println("result:");
  search.start();
  try {
   search.join();
  } catch (InterruptedException e) {
   // TODO Auto-generated catch block
   e.printStackTrace();
  }
 }
}

网页爬虫

http://blog.youkuaiyun.com/sfz_roger/archive/2008/04/10/2277125.aspx

关于HTTP协议的内容，记述如下：

        RFC2616中主要描述了HTTP 1.1协议。下面的描述没有实现其各个方面的内容，只提出了一种能够完成所有HTTP网页抓取的最小实现（不能够抓取HTTPS）。

        1、首先提交一个URL地址，分为普通的GET网页获取，POST的数据提交两种基本模式。

建立HttpWebReques实例，其中uri是网页的URL的地址：
   HttpWebRequest webrequest = (HttpWebRequest) WebRequest.Create(uri);

KeepAlive表示HTTP的连接是长连接：
   webrequest.KeepAlive = true;

如果需要，添加引用地址，主要用于防止其他网站的连接引用，比如登陆时，经常需要验证：
   if(referer!=null)
   {
    webrequest.Referer=referer;
   }

选择数据的提交方式，有GET、POST两种方式，HEAD不常用：
   switch(RequestMethod)
   {
    case 1:
     webrequest.Method="GET";
     break;
    case 2:
     webrequest.Method="POST";
     break;
    case 3:
     webrequest.Method="HEAD";
     break;
    default:
     webrequest.Method="GET";
     break;
   }

设置User－Agent，经常遇到，在某些网站中，做了限制，User－Agent为空，则不能访问：
   webrequest.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; .NET CLR 1.1.4322; .NET CLR 2.0.50215; fqSpider)";

添加其他的HTTP的Header信息，collHeader是一个NameValue的Collection：
   if(collHeader!=null&&collHeader.Count>0)
   {
    int iCount = collHeader.Count;
    string key;
    string keyvalue;

    for (int i=0; i < iCount; i++)
    {
     key = collHeader.Keys[i];
     keyvalue = collHeader[i];
     webrequest.Headers.Add(key, keyvalue);
    }
   }

设置Content－Type的内容，如果为POST，设置成application/x-www-form-urlencoded，如果是Get设置成text/html：
   if(webrequest.Method=="POST")
   {
    webrequest.ContentType="application/x-www-form-urlencoded";
   }
   else
   {
    webrequest.ContentType = "text/html"; 
   }


设置代理服务器地址和端口：
   if ((ProxyServer!=null) &&(ProxyServer.Length > 0))
   {
    webrequest.Proxy = new 
     WebProxy(ProxyServer,ProxyPort);
   }

设置是否允许自动转移：
   webrequest.AllowAutoRedirect = true;

设置基本的登陆认证 ：
   if (NwCred)
   {
    CredentialCache wrCache = 
     new CredentialCache();
    wrCache.Add(new Uri(uri),"Basic",
     new NetworkCredential(UserName,UserPwd));
    webrequest.Credentials = wrCache;
   }  

设置Request的Cookie容器：
   webrequest.CookieContainer=Cookies;

设置POST数据：
   byte[] bytes = Encoding.ASCII.GetBytes(RequestData);
   webrequest.ContentLength=bytes.Length;

   Stream oStreamOut = webrequest.GetRequestStream();
   oStreamOut.Write(bytes,0,bytes.Length);
   oStreamOut.Close();

具体代码如下：

1.

using System.IO;
using System.Net;
using System.Text.RegularExpressions;
namespace datagrid_study
{

 public class WebForm3 : System.Web.UI.Page
 {
  public WebClient web=new WebClient(); 
  private void Page_Load(object sender, System.EventArgs e)
  {
   // 在此处放置用户代码以初始化页面

    Stream str;
    str=web.OpenRead(http://news.XXXXXX.com);
    StreamReader read=new StreamReader(str,System.Text.Encoding.GetEncoding("GB2312"));
    string html=read.ReadToEnd();
    string aaa=html.ToString();
    string bbb=Regex.Split(aaa,"<td colspan=\"2\">",RegexOptions.IgnoreCase)[1];
       string ccc=Regex.Split(bbb,"</td>",RegexOptions.IgnoreCase)[0];
    Response.Write(ccc);
  }

2.

//根据Url地址得到网页的html源码
  private string GetWebContent1(string Url)
  {
   string strResult="";
   try
   {
    HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);
　　　　//声明一个HttpWebRequest请求
    request.Timeout = 30000;
    //设置连接超时时间
    request.Headers.Set("Pragma", "no-cache");
    HttpWebResponse response = (HttpWebResponse)request.GetResponse();
    Stream streamReceive = response.GetResponseStream();
    System.Text.Encoding encoding = System.Text.Encoding.GetEncoding("GB2312");
    StreamReader streamReader = new StreamReader(streamReceive, encoding);
    strResult = streamReader.ReadToEnd();
   }
   catch
   {
    return "";
   }
   return strResult;
  }

例3.

 public class WebForm1 : System.Web.UI.Page
 {
  protected System.Web.UI.WebControls.DataGrid dgData;

  private void Page_Load(object sender, System.EventArgs e)
  {
   // 在此处放置用户代码以初始化页面
   dgData.DataSource=getInfo();
   dgData.DataBind();

  }

  //根据Url地址得到网页的html源码
  private string GetWebContent1(string Url)
  {
   string strResult="";
   try
   {
    HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);
　　　　//声明一个HttpWebRequest请求
    request.Timeout = 30000;
    //设置连接超时时间
    request.Headers.Set("Pragma", "no-cache");
    HttpWebResponse response = (HttpWebResponse)request.GetResponse();
    Stream streamReceive = response.GetResponseStream();
    System.Text.Encoding encoding = System.Text.Encoding.GetEncoding("GB2312");
    StreamReader streamReader = new StreamReader(streamReceive, encoding);
    strResult = streamReader.ReadToEnd();
   }
   catch
   {
    return "";
   }
   return strResult;
  }


  //获取超级链接和文章标题、内容
  private DataTable getInfo()
  {
   //创建datatable
   DataTable dt = new DataTable(); 
   dt.Columns.Add("title",typeof(string));
   dt.Columns.Add("URL",typeof(string));
   dt.Columns.Add("content",typeof(string));
   dt.Columns.Add("newsdate",typeof(string));
   dt.TableName="newsthief";


   string html=GetWebContent1("http://www.xxxxxxxxx");

   string strPattern0=@"<td width=84% >";

   //计算匹配的个数
   int Count=0;
   MatchCollection Matches=Regex.Matches(html,strPattern0,RegexOptions.IgnoreCase|RegexOptions.Compiled);
   foreach(Match NextMatch in Matches)
   {
    Count++;

   }


   string sHtml=html;
   string strPattern=@"a[\s]+href=(?<Link>[^\s>]+)[^>]*>(?<Text>[^<]*)</a>";

   for(int j=0;j<Count-1;j++)//Count-1
   {

    string sTemp=Regex.Split(sHtml,"<td width=84% >",RegexOptions.IgnoreCase)[j+1];
    string sHref=Regex.Split(sTemp,"</td>",RegexOptions.IgnoreCase)[0];
    string sDateTemp=Regex.Split(sTemp,"</td>",RegexOptions.IgnoreCase)[1];
    string sDate=Regex.Split(sDateTemp,"<td Width=12% >",RegexOptions.IgnoreCase)[1];
    Matches=Regex.Matches(sHref,strPattern,RegexOptions.IgnoreCase|RegexOptions.Compiled);
    foreach(Match NextMatch in Matches)
    {
     string URL="http://www.china-insurance.com/news-center/"+NextMatch.Groups["Link"].Value.ToString().Trim();
     string title=NextMatch.Groups["Text"].Value.ToString().Trim();
     string htmlContent=GetWebContent1(URL);
     string sContentTemp=Regex.Split(htmlContent,"<table width=\"99%\"   height=\"100%\" border=\"0\" cellspacing=\"0\" cellpadding=\"0\" align=\"center\">",RegexOptions.IgnoreCase)[1];
     string sContent=Regex.Split(sContentTemp,"</table>",RegexOptions.IgnoreCase)[0];
     sContentTemp=Regex.Split(sContent,"<font id=zoom>",RegexOptions.IgnoreCase)[2];
     sContent=Regex.Split(sContentTemp,"</font>",RegexOptions.IgnoreCase)[0];
     //去掉<img ...>   @"\<IMG(.[^\<]*)?()\>)"
     string sContent1=Regex.Replace(sContent,@"<img[\s\S]*?>","&nbsp",RegexOptions.IgnoreCase|RegexOptions.Compiled);
     DataRow dr = dt.NewRow();
     dr["title"]=title;
     dr["URL"]=URL;
     dr["content"]=sContent1;
     dr["newsdate"]=sDate;
     dt.Rows.Add(dr);
    }
   }
   return dt;


  }