Jsoup解析HTML文件

仅仅是初步的解析，对于动态网页还没有好的办法。

希望高人可以给出建议。

Jsoup比较方便，只要记住了select的规则就ok了

不明白的多试试就ok了！

代码贴出来分分享下：

//package org.jsoup.examples;
import java.net.UnknownHostException;
import com.mongodb.BasicDBObject;
import com.mongodb.DB;
import com.mongodb.DBCollection;
import com.mongodb.DBCursor;
import com.mongodb.Mongo;
import com.mongodb.MongoException;

import org.jsoup.Jsoup;
import org.jsoup.helper.Validate;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.io.IOException;

/**
 * Example program parse the foursquare!.
 */
public class jsouptest {
	
	/*public void LoginMongodb (Mongo mongo) {   //login the mongodb
		
		Mongo mongo = new Mongo("localhost", 27017);
	}*/

    public static void main(String[] args) throws IOException {
    	
    	
    	Mongo mongo = new Mongo("localhost", 27017);
    	DB db = mongo.getDB("PaChong");
    	DBCollection collection = db.getCollection("PaCHongColl");
        
        BasicDBObject document = new BasicDBObject();
        BasicDBObject document2 = new BasicDBObject();
        String url = "https://foursquare.com/v/singapore-zoo/4b05880ef964a520b8ae22e3";
        print("Fetching %s...", url);

        Document doc = Jsoup.connect(url).get();
        //get the request for the usr and transfer into doc*/
        String title = new String(doc.title()); 
        document.put("Title", title);
        
        // get the title of this URL;
        print("%s", title);
        
        Elements Class = doc.select(".rating>span");
        String score= new String(Class.text());
        document.put("Score", score);
        print("%s ", score);
        /*for (Element score : Class){
        	
        	print("%s", score.text());
        	//print("\r\n");
        }*/
        //print("%s", Class.text());
        //get the score for every place.
        
        String tempstr[];
        
        Elements Similar = doc.select("#similarVenues>a");
        //tempstr = new String[Similar.size()];
        int count = 0;
        for (Element Place : Similar){
        	
        	 String str = new String(Place.text());
        	 count++;
        	 String temp = String.valueOf(count);
        	 document2.put(temp, str);
        	//document.put("similar", temp);
        	//print("%s", Place.text());
        	//print("\r\n");
        }
        String SimilarPlace = new String(Similar.text());
        document.put("Similar", document2);
        print("%s", Similar.text());
        
        Elements Event = doc.select("#exploreNearby>a");
        count = 0;
        BasicDBObject document3 = new BasicDBObject();
        for (Element temp : Event){
        	
        	String str = new String(temp.text());
        	count++;
        	String tempint = String.valueOf(count);
        	document3.put(tempint, str);
        }
        
        document.put("Events", document3);
        collection.insert(document);
    }
    
    private static void print(String msg, Object... args) {
        System.out.println(String.format(msg, args));
    }

   
}
//org/jsoup/examples/ListLinks.java

爬下来的东西存在了mongodb中，以方便今后的查看。

代码主要是查了一个title，div，的信息。