HtmlParser抓取百度新歌TOP100

阿拉神灯 — Fri, 05 Feb 2010 01:41:00 GMT

import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.HasAttributeFilter;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.tags.Span;
import org.htmlparser.tags.TableColumn;
import org.htmlparser.tags.TableRow;
import org.htmlparser.tags.TableTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;

public class test3 {
    public static void main(String[] args) throws ParserException {
        String url = "http://list.mp3.baidu.com/top/top100.html";
        Parser parser = new Parser(url);
        NodeFilter filter_table = new NodeClassFilter(TableTag.class);
        NodeFilter filter_span = new NodeClassFilter(Span.class);
        NodeFilter filter_link = new TagNameFilter("A");
        NodeFilter filter_search = new HasAttributeFilter("class","search");
        NodeList nodelist = parser.extractAllNodesThatMatch(filter_table);
        for(int i = 0  ; i < nodelist.size() ; i++){
            TableTag table = (TableTag) nodelist.elementAt(i);
            for(int j = 0 ; j < table.getRowCount() ; j++){
                TableRow row = table.getRow(j);
                TableColumn[] column = row.getColumns();
                for(int m = 0 ; m < row.getColumnCount() ; m++){
                    String tempstr = column[m].getStringText() ;
                    parser = Parser.createParser(tempstr,"utf-8");
                    NodeList list_span = parser.extractAllNodesThatMatch(filter_span);
                    if(list_span.size() > 0){
                        for(int i1 = 0 ; i1 < list_span.size() ; i1++){
                            System.out.print(list_span.elementAt(i1).toPlainTextString() + "  ");
                        }
                    }
                    parser.reset();
                    NodeList list_link = parser.extractAllNodesThatMatch(filter_link);
                    if(list_link.size() > 0){
                        for(int i1 = 0 ; i1 < list_link.size() ; i1++){
                            String content = ((LinkTag)list_link.elementAt(i1)).getLinkText() ;
                            if(!content.equals(null)){
                                System.out.print(content + "  ");
                            }
                        }
                    }
                    parser.reset();
                    NodeList list_search = parser.extractAllNodesThatMatch(filter_search);
                    if(list_search.size() > 0){
                        for(int i1 = 0 ; i1 < list_search.size() ; i1++){
                            String link = ((LinkTag)list_search.elementAt(i1)).getLink() ;
                            if(!link.equals(null)){
                                System.out.print(link + "  ");
                            }
                        }
                    }
                }
                System.out.println();
            }
        }
    }
}

阿拉神灯 2010-02-05 09:41 发表评论

BlogJava-阿拉神灯-随笔分类-JAVA

HtmlParser抓取百度新歌TOP100