每日博客

java爬虫

来自：Java爬虫之爬取数据_y……的博客-CSDN博客_java爬数据

pom.xml

<dependencies>
    <dependency>
        <groupId>com.googlecode.juniversalchardet</groupId>
        <artifactId>juniversalchardet</artifactId>
        <version>1.0.3</version>
    </dependency>
    <dependency>
        <groupId>org.kie.modules</groupId>
        <artifactId>org-apache-commons-httpclient</artifactId>
        <version>6.2.0.CR2</version>
        <type>pom</type>
    </dependency>
    <dependency>
        <groupId>org.jsoup</groupId>
        <artifactId>jsoup</artifactId>
        <version>1.10.3</version>
    </dependency>

</dependencies>

public interface LinkFilter {
    public boolean accept(String url);
}

public class Links {

    //已访问的 url 集合  已经访问过的 主要考虑 不能再重复了 使用set来保证不重复;
    private static Set visitedUrlSet = new HashSet();

    //待访问的 url 集合  待访问的主要考虑 1:规定访问顺序;2:保证不提供重复的带访问地址;
    private static LinkedList unVisitedUrlQueue = new LinkedList();

    //获得已经访问的 URL 数目
    public static int getVisitedUrlNum() {
        return visitedUrlSet.size();
    }

    //添加到访问过的 URL
    public static void addVisitedUrlSet(String url) {
        visitedUrlSet.add(url);
    }

    //移除访问过的 URL
    public static void removeVisitedUrlSet(String url) {
        visitedUrlSet.remove(url);
    }



    //获得 待访问的 url 集合
    public static LinkedList getUnVisitedUrlQueue() {
        return unVisitedUrlQueue;
    }

    // 添加到待访问的集合中  保证每个 URL 只被访问一次
    public static void addUnvisitedUrlQueue(String url) {
        if (url != null && !url.trim().equals("")  && !visitedUrlSet.contains(url)  && !unVisitedUrlQueue.contains(url)){
            unVisitedUrlQueue.add(url);
        }
    }

    //删除 待访问的url
    public static Object removeHeadOfUnVisitedUrlQueue() {
        return unVisitedUrlQueue.removeFirst();
    }

    //判断未访问的 URL 队列中是否为空
    public static boolean unVisitedUrlQueueIsEmpty() {
        return unVisitedUrlQueue.isEmpty();
    }

}

public class Page {

    private byte[] content;
    private String html;  //网页源码字符串
    private Document doc;//网页Dom文档
    private String charset;//字符编码
    private String url;//url路径
    private String contentType;// 内容类型


    public Page(byte[] content, String url, String contentType) {
        this.content = content;
        this.url = url;
        this.contentType = contentType;
    }

    public String getCharset() {
        return charset;
    }

    public String getUrl() {
        return url;
    }

    public String getContentType() {
        return contentType;
    }

    public byte[] getContent() {
        return content;
    }

    /**
     * 返回网页的源码字符串
     *
     * @return 网页的源码字符串
     */
    public String getHtml() {
        if (html != null) {
            return html;
        }
        if (content == null) {
            return null;
        }
        if (charset == null) {
            charset = CharsetDetector.guessEncoding(content); // 根据内容来猜测 字符编码
        }
        try {
            this.html = new String(content, charset);
            return html;
        } catch (UnsupportedEncodingException ex) {
            ex.printStackTrace();
            return null;
        }
    }

    /*
     *  得到文档
     * */
    public Document getDoc() {
        if (doc != null) {
            return doc;
        }
        try {
            this.doc = Jsoup.parse(getHtml(), url);
            return doc;
        } catch (Exception ex) {
            ex.printStackTrace();
            return null;
        }
    }

}

public class PageParserTool {


    /* 通过选择器来选取页面的 */
    public static Elements select(Page page , String cssSelector) {
        return page.getDoc().select(cssSelector);
    }

    /*
     *  通过css选择器来得到指定元素;
     *
     *  */
    public static Element select(Page page , String cssSelector, int index) {
        Elements eles = select(page , cssSelector);
        int realIndex = index;
        if (index < 0) {
            realIndex = eles.size() + index;
        }
        return eles.get(realIndex);
    }


    /**
     * 获取满足选择器的元素中的链接 选择器cssSelector必须定位到具体的超链接
     * 例如我们想抽取id为content的div中的所有超链接，这里
     * 就要将cssSelector定义为div[id=content] a
     *  放入set 中 防止重复；
     * @param cssSelector
     * @return
     */
    public static  Set<String> getLinks(Page page ,String cssSelector) {
        Set<String> links  = new HashSet<String>() ;
        Elements es = select(page , cssSelector);
        Iterator iterator  = es.iterator();
        while(iterator.hasNext()) {
            Element element = (Element) iterator.next();
            if ( element.hasAttr("href") ) {
                links.add(element.attr("abs:href"));
            }else if( element.hasAttr("src") ){
                links.add(element.attr("abs:src"));
            }
        }
        return links;
    }



    /**
     * 获取网页中满足指定css选择器的所有元素的指定属性的集合
     * 例如通过getAttrs("img[src]","abs:src")可获取网页中所有图片的链接
     * @param cssSelector
     * @param attrName
     * @return
     */
    public static ArrayList<String> getAttrs(Page page , String cssSelector, String attrName) {
        ArrayList<String> result = new ArrayList<String>();
        Elements eles = select(page ,cssSelector);
        for (Element ele : eles) {
            if (ele.hasAttr(attrName)) {
                result.add(ele.attr(attrName));
            }
        }
        return result;
    }
}

public static Page  sendRequstAndGetResponse(String url) {
        Page page = null;
        // 1.生成 HttpClinet 对象并设置参数
        HttpClient httpClient = new HttpClient();
        // 设置 HTTP 连接超时 5s
        // 2.生成 GetMethod 对象并设置参数
        GetMethod getMethod = new GetMethod(url);
        // 设置 get 请求超时 5s
        // 设置请求重试处理
        getMethod.getParams().setParameter(HttpMethodParams.RETRY_HANDLER, new DefaultHttpMethodRetryHandler());
        // 3.执行 HTTP GET 请求
        try {
            int statusCode = httpClient.executeMethod(getMethod);
            // 判断访问的状态码
            if (statusCode != HttpStatus.SC_OK) {
                System.err.println("Method failed: " + getMethod.getStatusLine());
            }
            // 4.处理 HTTP 响应内容
            byte[] responseBody = getMethod.getResponseBody();// 读取为字节 数组
            String contentType = getMethod.getResponseHeader("Content-Type").getValue(); // 得到当前返回类型
            page = new Page(responseBody,url,contentType); //封装成为页面
        } catch (HttpException e) {
            // 发生致命的异常，可能是协议不对或者返回的内容有问题
            System.out.println("Please check your provided http address!");
            e.printStackTrace();
        } catch (IOException e) {
            // 发生网络异常
            e.printStackTrace();
        } finally {
            // 释放连接
            getMethod.releaseConnection();
        }
        return page;
    }

public class CharsetDetector {

    //从Nutch借鉴的网页编码检测代码
    private static final int CHUNK_SIZE = 2000;

    private static Pattern metaPattern = Pattern.compile(
            "<meta\\s+([^>]*http-equiv=(\"|')?content-type(\"|')?[^>]*)>",
            Pattern.CASE_INSENSITIVE);
    private static Pattern charsetPattern = Pattern.compile(
            "charset=\\s*([a-z][_\\-0-9a-z]*)", Pattern.CASE_INSENSITIVE);
    private static Pattern charsetPatternHTML5 = Pattern.compile(
            "<meta\\s+charset\\s*=\\s*[\"']?([a-z][_\\-0-9a-z]*)[^>]*>",
            Pattern.CASE_INSENSITIVE);

    //从Nutch借鉴的网页编码检测代码
    private static String guessEncodingByNutch(byte[] content) {
        int length = Math.min(content.length, CHUNK_SIZE);

        String str = "";
        try {
            str = new String(content, "ascii");
        } catch (UnsupportedEncodingException e) {
            return null;
        }

        Matcher metaMatcher = metaPattern.matcher(str);
        String encoding = null;
        if (metaMatcher.find()) {
            Matcher charsetMatcher = charsetPattern.matcher(metaMatcher.group(1));
            if (charsetMatcher.find()) {
                encoding = new String(charsetMatcher.group(1));
            }
        }
        if (encoding == null) {
            metaMatcher = charsetPatternHTML5.matcher(str);
            if (metaMatcher.find()) {
                encoding = new String(metaMatcher.group(1));
            }
        }
        if (encoding == null) {
            if (length >= 3 && content[0] == (byte) 0xEF
                    && content[1] == (byte) 0xBB && content[2] == (byte) 0xBF) {
                encoding = "UTF-8";
            } else if (length >= 2) {
                if (content[0] == (byte) 0xFF && content[1] == (byte) 0xFE) {
                    encoding = "UTF-16LE";
                } else if (content[0] == (byte) 0xFE
                        && content[1] == (byte) 0xFF) {
                    encoding = "UTF-16BE";
                }
            }
        }

        return encoding;
    }

    /**
     * 根据字节数组，猜测可能的字符集，如果检测失败，返回utf-8
     *
     * @param bytes 待检测的字节数组
     * @return 可能的字符集，如果检测失败，返回utf-8
     */
    public static String guessEncodingByMozilla(byte[] bytes) {
        String DEFAULT_ENCODING = "UTF-8";
        UniversalDetector detector = new UniversalDetector(null);
        detector.handleData(bytes, 0, bytes.length);
        detector.dataEnd();
        String encoding = detector.getDetectedCharset();
        detector.reset();
        if (encoding == null) {
            encoding = DEFAULT_ENCODING;
        }
        return encoding;
    }

    /**
     * 根据字节数组，猜测可能的字符集，如果检测失败，返回utf-8
     * @param content 待检测的字节数组
     * @return 可能的字符集，如果检测失败，返回utf-8
     */
    public static String guessEncoding(byte[] content) {
        String encoding;
        try {
            encoding = guessEncodingByNutch(content);
        } catch (Exception ex) {
            return guessEncodingByMozilla(content);
        }

        if (encoding == null) {
            encoding = guessEncodingByMozilla(content);
            return encoding;
        } else {
            return encoding;
        }
    }
}

public class FileTool {

    private static String dirPath;


    /**
     * getMethod.getResponseHeader("Content-Type").getValue()
     * 根据 URL 和网页类型生成需要保存的网页的文件名，去除 URL 中的非文件名字符
     */
    private static String getFileNameByUrl(String url, String contentType) {
        //去除 http://
        url = url.substring(7);
        //text/html 类型
        if (contentType.indexOf("html") != -1) {
            url = url.replaceAll("[\\?/:*|<>\"]", "_") + ".html";
            return url;
        }
        //如 application/pdf 类型
        else {
            return url.replaceAll("[\\?/:*|<>\"]", "_") + "." +
                    contentType.substring(contentType.lastIndexOf("/") + 1);
        }
    }

    /*
     *  生成目录
     * */
    private static void mkdir() {
        if (dirPath == null) {
            dirPath = Class.class.getClass().getResource("/").getPath() + "temp\\";
        }
        File fileDir = new File(dirPath);
        if (!fileDir.exists()) {
            fileDir.mkdir();
        }
    }

    /**
     * 保存网页字节数组到本地文件，filePath 为要保存的文件的相对地址
     */

    public static void saveToLocal(Page page) {
        mkdir();
        String fileName =  getFileNameByUrl(page.getUrl(), page.getContentType()) ;
        String filePath = dirPath + fileName ;
        byte[] data = page.getContent();
        try {
            DataOutputStream out = new DataOutputStream(new FileOutputStream(new File(filePath)));
            // for (int i = 0; i < data.length; i++) {
            //     out.write(data[i]);
            // }
            out.write(data);
            out.flush();
            out.close();
            System.out.println("文件："+ fileName + "已经被存储在"+ filePath  );
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

}

public RegexRule addRule(String rule) {
        if (rule.length() == 0) {
            return this;
        }
        char pn = rule.charAt(0);
        String realrule = rule.substring(1);
        if (pn == '+') {
            addPositive(realrule);
        } else if (pn == '-') {
            addNegative(realrule);
        } else {
            addPositive(rule);
        }
        return this;
    }

public void crawling(String[] seeds) {

        //初始化 URL 队列
        initCrawlerWithSeeds(seeds);

        //定义过滤器，提取以 http://www.baidu.com 开头的链接
        LinkFilter filter = new LinkFilter() {
            public boolean accept(String url) {
                if (url.startsWith("你想爬取的网站"))
                    return true;
                else
                    return false;
            }
        };

        //循环条件：待抓取的链接不空且抓取的网页不多于 1000
        while (!Links.unVisitedUrlQueueIsEmpty()  && Links.getVisitedUrlNum() <= 1000) {

            //先从待访问的序列中取出第一个；
            String visitUrl = (String) Links.removeHeadOfUnVisitedUrlQueue();
            if (visitUrl == null){
                continue;
            }

            //根据URL得到page;
            Page page = RequestAndResponseTool.sendRequstAndGetResponse(visitUrl);

            //对page进行处理： 访问DOM的某个标签
            Elements es = PageParserTool.select(page,"a");
            if(!es.isEmpty()){
                System.out.println("下面将打印所有a标签： ");
                System.out.println(es);
            }

            //将保存文件
            FileTool.saveToLocal(page);

            //将已经访问过的链接放入已访问的链接中；
            Links.addVisitedUrlSet(visitUrl);

            //得到超链接
            Set<String> links = PageParserTool.getLinks(page,"img");
            for (String link : links) {
                Links.addUnvisitedUrlQueue(link);
                System.out.println("新增爬取路径: " + link);
            }
        }
    }