package com.glht.search.action;

import java.io.BufferedInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Ask {

    /**
     * @param args
     */
    public static void main(String[] args) {
getSuNing("http://www.suning.com/webapp/wcs/stores/servlet/odeSearch?storeId=10052&catalogId=10051&categoryId=20394&langId=-7&suggestionWordList=%5b%5d&isCatalogSearch=1&isList=0&sortType=0&currentPage=0");
        getSuNing("http://www.suning.com/webapp/wcs/stores/servlet/odeSearch?storeId=10052&catalogId=10051&categoryId=20321&langId=-7&suggestionWordList=%5b%5d&isCatalogSearch=1&isList=0&sortType=0&currentPage=0");
    }

    /*
     * 获取苏宁的一个分类页面的产品
     */
    public static void getSuNing(String url) {
        String content = Utils.getURLContent(url, "utf-8");
        System.out.println("内容获取完成");

        StringBuilder regStr = new StringBuilder();
        regStr.append("class=\"pro_img\".*?");
        regStr.append("<a.*?href=\"(.*?)\"");
        regStr.append(".*?src=\"(.*?)\".*?alt=\"(.*?)\"");
        regStr.append(".*?<em>(\\d+.?\\d+)</em>");
        Pattern pattern = Pattern.compile(regStr.toString(), Pattern.DOTALL);
        Matcher matcher = pattern.matcher(content);
        int count = 0;
        while (matcher.find()) {
            System.out.println("第" + (++count) + "个");
        }
        System.out.println("分析完成=========");

    }

    /*
     * 获取页面的内容
     */
    public static String getURLContent(String url, String encoding) {
        if (url == null || "".equals(url.trim()))
            return null;

        StringBuffer content = new StringBuffer();
        try {
            // 新建URL对象
            URL u = new URL(url);
            InputStream in = new BufferedInputStream(u.openStream());
            InputStreamReader theHTML = new InputStreamReader(in,
                    encoding != null ? encoding : "gb2312");
            int c;
            while ((c = theHTML.read()) != -1) {
                content.append((char) c);
            }
        }
        // 处理异常
        catch (MalformedURLException e) {
            System.err.println(e);
        } catch (IOException e) {
            System.err.println(e);
        }
        return content.toString();
    }
}