国产一级a片免费看高清,亚洲熟女中文字幕在线视频,黄三级高清在线播放,免费黄色视频在线看

package net.nutch.fetcher;
                        ...
                        import org.cyberneko.html.parsers.*;
                        import org.xml.sax.*;
                        import org.w3c.dom.*;
                        import org.w3c.dom.html.*;
                        import org.apache.html.dom.*;                        
 
                        
/* A simple fetcher. */
                        public class Fetcher { 
                        ....
                        private DOMFragmentParser parser = new DOMFragmentParser();
                        ....
                        private void handleFetch(URL url, FetchListEntry fle, Http.Response response)
                        throws IOException, SAXException {
                        
                        //判斷HTTP應(yīng)答包的類型，只放過html文件
                        String contentType = response.getHeader("Content-Type");
                        if (contentType != null && !contentType.startsWith("text/html"))
                        throw new IOException("Unknown content-type: " + contentType);
                        //創(chuàng)建文件片段對象
                        DocumentFragment node = new HTMLDocumentImpl().createDocumentFragment();
                        //解析HTML內(nèi)容
                        parser.parse(new InputSource(new ByteArrayInputStream(response.getContent())),node);
                        //取得全部文本內(nèi)容
                        StringBuffer sb = new StringBuffer();
                        getText(sb, node);
                        String text = sb.toString();
                        //取得標(biāo)題信息
                        sb.setLength(0);
                        getTitle(sb, node);
                        String title = sb.toString().trim();
                        //取得該頁所有的出鏈
                        ArrayList l = new ArrayList();
                        getOutlinks(url, l, node);
                        
                        //顯示結(jié)果，存儲信息
                        Outlink[] outlinks = (Outlink[])l.toArray(new Outlink[l.size()]);
                        LOG.fine("found " + outlinks.length + " outlinks in " + url);
                        
      outputPage(new FetcherOutput(fle, MD5Hash.digest(response.getContent()),
                        true, title, outlinks),
                        new FetcherContent(response.getContent()),
                        new FetcherText(text));
                        }
                        private static void getText(StringBuffer sb, Node node) {
                        if (node.getNodeType() == Node.TEXT_NODE) {
                        sb.append(node.getNodeValue());//取得結(jié)點(diǎn)值，即開始與結(jié)束標(biāo)簽之間的信息
                        }
                        NodeList children = node.getChildNodes();
                        if ( children != null ) {
                        int len = children.getLength();
                        for ( int i = 0; i < len; i++ ) {
                        getText(sb, children.item(i));//遞歸遍歷DOM樹
                        }
                        }
                        }
                        
  private static boolean getTitle(StringBuffer sb, Node node) {
                        if (node.getNodeType() == Node.ELEMENT_NODE) {
                        if ("title".equalsIgnoreCase(node.getNodeName())) {
                        getText(sb, node);
                        return true;
                        }
                        }
                        NodeList children = node.getChildNodes();
                        if (children != null) {
                        int len = children.getLength();
                        for (int i = 0; i < len; i++) {
                        if (getTitle(sb, children.item(i))) {
                        return true;
                        }
                        }
                        }
                        return false;
                        }
                        
  private static void getOutlinks(URL base, ArrayList outlinks, Node node) {
                        if (node.getNodeType() == Node.ELEMENT_NODE) {
                        if ("a".equalsIgnoreCase(node.getNodeName())) {
                        StringBuffer linkText = new StringBuffer();
                        getText(linkText, node);
                        
        NamedNodeMap attrs = node.getAttributes();
                        String target= null;
                        for (int i= 0; i < attrs.getLength(); i++ ) {
                        if ("href".equalsIgnoreCase(attrs.item(i).getNodeName())) {
                        target= attrs.item(i).getNodeValue();//在DOM樹中，屬性是一個結(jié)點(diǎn)。
                        break;
                        }
                        }
                        if (target != null)
                        try {
                        URL url = new URL(base, target);
                        outlinks.add(new Outlink(url.toString(),linkText.toString().trim()));
                        } catch (MalformedURLException e) {
                        // don‘t care
                        }
                        }
                        }
                        NodeList children = node.getChildNodes();
                        if ( children != null ) {
                        int len = children.getLength();
                        for ( int i = 0; i < len; i++ ) {
                        getOutlinks(base, outlinks, children.item(i));//遞歸遍歷DOM樹
                        }
                        }
                        }	
                        ....
                        }