网站的轮播图的获取

获取某网站的轮播图

/**
     * 获取轮播图
     * 
     * @author Michael
     * @param newsUrl
     * @return
     */

    public List<Map<String, String>> crawler4Pic(String newsUrl) {
        List<Map<String, String>> picList = new ArrayList<Map<String, String>>();
        try {
            Document newsPageDoc = Jsoup.connect(newsUrl)
                    .header("Content-Type", "text/html; charset=GB2312")
                    .header("Accept-Language", "zh-CN,zh;q=0.8").timeout(3000)
                    .get(); // 获得当前页面的Dom
            String picString = newsPageDoc.select("script").eq(5).toString()
                    .split("var data = ")[1].split(";")[0];
            JSONArray picArray = JSONArray.fromObject(picString);
            for (int i = 0; i < picArray.size(); i++) {
                Map<String, String> picMap = new HashMap<String, String>();
                String picUrl = picArray.getString(i).split("\"")[3];
                String titleUrl = picArray.getString(i).split("\"")[7] + ":"
                        + picArray.getString(i).split("\"")[11];
                picMap.put("picUrl", picUrl);
                picMap.put("title", titleUrl);
                picList.add(picMap);
                System.out.println("picUrl: " + picUrl + "   title:  "
                        + titleUrl);
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        // System.out.println("picList =" + picList);
        return picList;
    }
    /**
     * @param args
     */
    public static void main(String[] args) {
        BBMCCrowler bbmc = new BBMCCrowler();
        bbmc.crawler4Pic("http://www.bbmc.edu.cn/");
    }