来源: 互联网  发布时间: 2014-02-18

通过JAVA获取优酷、土豆、酷6、6间房等视频
通过JAVA获取优酷、土豆、酷6、6间房、56视频，现在很多社会网站都有这个功能，用户输入优酷、土豆、酷6、6间房、56视频地址后，能找到对应的视频及视频的缩略图，有些社区网站还能获取到视频的时长。
比如：新浪微博就有这个功能，当用户输入优酷、土豆、酷6、6间房、56视频网址后，就能获取到相应的视频地址及视频的缩略图。

其中要用到一个JAR包，链接地址如下：
http://jsoup.org/packages/jsoup-1.5.2.jar


原文地址：http://www.juziku.com/wiki/906.htm


核心代码
view sourceprint?
001 import org.jsoup.Jsoup; 

002 import org.jsoup.nodes.Document; 

003 import org.jsoup.nodes.Element; 

004 import org.jsoup.select.Elements; 

005   

006 /** 

007 * 视频工具类 

008 * @author sunlightcs 

009 * 2011-4-6 

010 * http://hi.juziku.com/sunlightcs/ 

011 */

012 public class VideoUtil { 

013       

014     /** 

015      * 获取视频信息 

016      * @param url 

017      * @return 

018      */

019     public static Video getVideoInfo(String url){ 

020         Video video = new Video(); 

021           

022         if(url.indexOf("v.youku.com")!=-1){ 

023             try { 

024                 video = getYouKuVideo(url); 

025             } catch (Exception e) { 

026                 video = null; 

027             } 

028         }else if(url.indexOf("tudou.com")!=-1){ 

029             try { 

030                 video = getTudouVideo(url); 

031             } catch (Exception e) { 

032                 video = null; 

033             } 

034         }else if(url.indexOf("v.ku6.com")!=-1){ 

035             try { 

036                 video = getKu6Video(url); 

037             } catch (Exception e) { 

038                 video = null; 

039             } 

040         }else if(url.indexOf("6.cn")!=-1){ 

041             try { 

042                 video = get6Video(url); 

043             } catch (Exception e) { 

044                 video = null; 

045             } 

046         }else if(url.indexOf("56.com")!=-1){ 

047             try { 

048                 video = get56Video(url); 

049             } catch (Exception e) { 

050                 video = null; 

051             } 

052         } 

053           

054         return video; 

055     } 

056       

057       

058     /** 

059      * 获取优酷视频 

060      * @param url  视频URL 

061      */

062     public static Video getYouKuVideo(String url) throws Exception{ 

063         Document doc = getURLContent(url); 

064           

065         /** 

066          *获取视频缩略图  

067          */

068         String pic = getElementAttrById(doc, "s_sina", "href"); 

069         int local = pic.indexOf("pic="); 

070         pic = pic.substring(local+4); 

071           

072         /** 

073          * 获取视频地址 

074          */     

075         String flash = getElementAttrById(doc, "link2", "value"); 

076           

077         /** 

078          * 获取视频时间 

079          */ 

080         String time = getElementAttrById(doc, "download", "href"); 

081         String []arrays = time.split("\\|"); 

082         time = arrays[4]; 

083           

084         Video video = new Video(); 

085         video.setPic(pic); 

086         video.setFlash(flash); 

087         video.setTime(time); 

088           

089         return video; 

090     } 

091       

092       

093     /** 

094      * 获取土豆视频 

095      * @param url  视频URL 

096      */

097     public static Video getTudouVideo(String url) throws Exception{ 

098         Document doc = getURLContent(url); 

099         String content = doc.html(); 

100         int beginLocal = content.indexOf("<script>document.domain"); 

101         int endLocal = content.indexOf("</script>"); 

102         content = content.substring(beginLocal, endLocal); 

103           

104         /** 

105          * 获取视频地址 

106          */ 

107         String flash = getScriptVarByName("iid_code", content); 

108         flash = "http://www.tudou.com/v/" + flash + "/v.swf"; 

109           

110         /** 

111          *获取视频缩略图  

112          */

113         String pic = getScriptVarByName("thumbnail", content); 

114           

115         /** 

116          * 获取视频时间 

117          */ 

118         String time = getScriptVarByName("time", content); 

119   

120         Video video = new Video(); 

121         video.setPic(pic); 

122         video.setFlash(flash); 

123         video.setTime(time); 

124           

125         return video; 

126     } 

127       

128       

129     /** 

130      * 获取酷6视频 

131      * @param url  视频URL 

132      */

133     public static Video getKu6Video(String url) throws Exception{ 

134         Document doc = getURLContent(url); 

135           

136         /** 

137          * 获取视频地址 

138          */

139         Element flashEt = doc.getElementById("outSideSwfCode"); 

140         String flash = flashEt.attr("value"); 

141           

142         /** 

143          * 获取视频缩略图 

144          */

145         Element picEt = doc.getElementById("plVideosList"); 

146         String time = null; 

147         String pic = null; 

148         if(picEt!=null){ 

149             Elements pics = picEt.getElementsByTag("img"); 

150             pic = pics.get(0).attr("src"); 

151               

152             /** 

153              * 获取视频时长 

154              */

155             Element timeEt = picEt.select("span.review>cite").first();  

156             time = timeEt.text(); 

157         }else{ 

158             pic = doc.getElementsByClass("s_pic").first().text(); 

159         } 

160           

161         Video video = new Video(); 

162         video.setPic(pic); 

163         video.setFlash(flash); 

164         video.setTime(time); 

165           

166         return video; 

167           

168     } 

169       

170       

171     /** 

172      * 获取6间房视频 

173      * @param url  视频URL 

174      */

175     public static Video get6Video(String url) throws Exception{ 

176         Document doc = getURLContent(url); 

177           

178         /** 

179          * 获取视频缩略图 

180          */

181         Element picEt = doc.getElementsByClass("summary").first(); 

182         String pic = picEt.getElementsByTag("img").first().attr("src"); 

183           

184         /** 

185          * 获取视频时长 

186          */

187         String time = getVideoTime(doc, url, "watchUserVideo"); 

188         if(time==null){ 

189             time = getVideoTime(doc, url, "watchRelVideo"); 

190         } 

191           

192         /** 

193          * 获取视频地址 

194          */

195         Element flashEt = doc.getElementById("video-share-code"); 

196         doc = Jsoup.parse(flashEt.attr("value"));   

197         String flash = doc.select("embed").attr("src"); 

198           

199         Video video = new Video(); 

200         video.setPic(pic); 

201         video.setFlash(flash); 

202         video.setTime(time); 

203           

204         return video; 

205     } 

206       

207       

208     /** 

209      * 获取56视频 

210      * @param url  视频URL 

211      */

212     public static Video get56Video(String url) throws Exception{ 

213         Document doc = getURLContent(url); 

214         String content = doc.html(); 

215           

216         /** 

217          * 获取视频缩略图 

218          */

219         int begin = content.indexOf("\"img\":\""); 

220         content = content.substring(begin+7, begin+200); 

221         int end = content.indexOf("\"};"); 

222         String pic = content.substring(0, end).trim(); 

223         pic = pic.replaceAll("\\\\", "");        

224           

225         /** 

226          * 获取视频地址 

227          */

228         String flash = "http://player.56.com" + url.substring(url.lastIndexOf("/"), url.lastIndexOf(".html")) + ".swf"; 

229           

230         Video video = new Video(); 

231         video.setPic(pic); 

232         video.setFlash(flash); 

233           

234         return video; 

235     } 

236   

237     /** 

238      * 获取6间房视频时长     

239      */

240     private static String getVideoTime(Document doc, String url, String id) { 

241         String time = null; 

242           

243         Element timeEt = doc.getElementById(id);  

244         Elements links = timeEt.select("dt > a"); 

245           

246           

247         for (Element link : links) { 

248           String linkHref = link.attr("href"); 

249           if(linkHref.equalsIgnoreCase(url)){ 

250               time = link.parent().getElementsByTag("em").first().text(); 

251               break; 

252           } 

253         } 

254         return time; 

255     } 

256       

257               

258     /** 

259      * 获取script某个变量的值 

260      * @param name  变量名称 

261      * @return   返回获取的值  

262      */

263     private static String getScriptVarByName(String name, String content){ 

264         String script = content; 

265           

266         int begin = script.indexOf(name); 

267           

268         script = script.substring(begin+name.length()+2); 

269           

270         int end = script.indexOf(","); 

271           

272         script = script.substring(0,end); 

273           

274         String result=script.replaceAll("'", ""); 

275         result = result.trim(); 

276           

277         return result; 

278     } 

279       

280       

281     /** 

282      * 根据HTML的ID键及属于名，获取属于值 

283      * @param id  HTML的ID键 

284      * @param attrName  属于名 

285      * @return  返回属性值 

286      */

287     private static String getElementAttrById(Document doc, String id, String attrName)throws Exception{ 

288         Element et = doc.getElementById(id); 

289         String attrValue = et.attr(attrName); 

290           

291         return attrValue; 

292     } 

293       

294       

295       

296     /** 

297      * 获取网页的内容 

298      */

299     private static Document getURLContent(String url) throws Exception{ 

300         Document doc = Jsoup.connect(url) 

301           .data("query", "Java") 

302           .userAgent("Mozilla") 

303           .cookie("auth", "token") 

304           .timeout(6000) 

305           .post(); 

306         return doc; 

307     } 

308       

309       

310     public static void main(String[] args) { 

311         //String url = "http://v.youku.com/v_show/id_XMjU0MjI2NzY0.html"; 

312         //String url = "http://www.tudou.com/programs/view/pVploWOtCQM/"; 

313         //String url = "http://v.ku6.com/special/show_4024167/9t7p64bisV2A31Hz.html"; 

314         //String url = "http://v.ku6.com/show/BpP5LeyVwvikbT1F.html"; 

315         //String url = "http://6.cn/watch/14757577.html"; 

316         String url = "http://www.56.com/u64/v_NTkzMDEzMTc.html"; 

317         Video video = getVideoInfo(url); 

318         System.out.println("视频缩略图："+video.getPic()); 

319         System.out.println("视频地址："+video.getFlash()); 

320         System.out.println("视频时长："+video.getTime()); 

321     } 

322 }
[代码] 视频封装类
view sourceprint?01 /** 

02 * 视频封装 

03 * @author sunlightcs 

04 * 2011-4-6 

05 * http://hi.juziku.com/sunlightcs/ 

06 */

07 public class Video { 

08     private String flash; 

09     private String pic; 

10     private String time; 

11     public String getFlash() { 

12         return flash; 

13     } 

14     public void setFlash(String flash) { 

15         this.flash = flash; 

16     } 

17     public String getPic() { 

18         return pic; 

19     } 

20     public void setPic(String pic) { 

21         this.pic = pic; 

22     } 

23     public String getTime() { 

24         return time; 

25     } 

26     public void setTime(String time) { 

27         this.time = time; 

28     } 

29 }

    

    来源: 互联网  发布时间: 2014-02-18

视频地址挖掘抓取
//得到视频标题  
   public String getVideoTitle(String beginTitleStr,int beginTextNum,String endTitleStr){  
    int beginTitleNum =  videoStr.indexOf(beginTitleStr,beginTextNum)+beginTitleStr.length();  
    int endTitleNum = videoStr.indexOf(endTitleStr,beginTitleNum);  
    String videoTitle = new ToolsSubString().mySubString(videoStr,beginTitleNum,endTitleNum);         
    return videoTitle;  
   }  
 
//得到视频地址ID  
   public String getVideoId(String beginIdStr,int beginTextNum,String endIdStr){  
    int beginIdNum = videoStr.indexOf(beginIdStr,beginTextNum)+beginIdStr.length();  
    int endIdNum = videoStr.indexOf(endIdStr,beginIdNum);  
    String videoId = new ToolsSubString().mySubString(videoStr,beginIdNum,endIdNum);  
    return videoId;  
   }  
     
   //抓取土豆网视频信息的方法  
   public void catchTudouVideo(int neadCatchNum,String beginSearchVideoNumStr){  
    //抓取内容定位  
    String endSearchVideoNumStr = "</em>";  
    String beginTextStr = "<a inner\" target=\"new";  
    String beginIdStr = "href=/index.html"http://www.tudou.com/programs/view/";  
    String endIdStr = "/\"";  
    String beginTitleStr = "title=\"";        
    String endTitleStr = "\"";  
    int beginTextNum = 0;  
      
    //得到搜索到视频个数，循环得到视频信息          
    int searchVideoNum = getVideoNum(neadCatchNum,beginSearchVideoNumStr, endSearchVideoNumStr);  
    for(int i=0;i<searchVideoNum;i++){  
        //内容定位  
        beginTextNum = videoStr.indexOf(beginTextStr,beginTextNum)+beginTextStr.length();  
          
        //得到视频信息  
        String videoTitle = getVideoTitle(beginTitleStr, beginTextNum, endTitleStr);  
        String videoId = getVideoId(beginIdStr, beginTextNum, endIdStr);                      
        String videoUrl = "http://www.tudou.com/v/"+videoId+"/v.swf";  
 
        //创建video对象保存视频信息，并添加到video集合，为存入数据库做准备  
        VideoEntity video = new VideoEntity(videoTitle,"土豆网",videoUrl);  
        videoList.add(video);  
    }  
   }

    

    来源: 互联网  发布时间: 2014-02-18

简单好用的网络爬虫spider/crawler
package spider;  
 
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;  
 
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(/blog_article/String url/index.html) {  
        // 只处理HTTP URLs.  
        if (!url.toLowerCase().startsWith("http://"))  
            return null;  
        URL verifiedUrl = null;  
        try {  
            verifiedUrl = new URL(/blog_article/url/index.html);  
        } 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(/blog_article/String url/index.html) {  
        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  
    @SuppressWarnings("unchecked")  
    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) == '/') {// 处理绝对地址  
                    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(/blog_article/link/index.html);  
 
            URL verifiedLink = verifyUrl(/blog_article/link/index.html);  
            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(/blog_article/startUrl/index.html);  
 
        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();  
        }  
    }  
}