Android 使用Jsoup解析HTML实现快速爬虫抓包

jsoup Cookbook(中文版)
注意：div的class名称有空格的话，是解析不到的，比如：

<div class="container clearfix pt0" id="mainBox"></div>

还有一种情况，就是页面需要点击按钮添加数据，简单的说，通过点击调用JS来加载数据，那么这部分数据也不好抓取。

mMeiList = new ArrayList<>();
        new Thread(new Runnable() {
            @Override
            public void run() {
                try {//http://m.mmjpg.com/tag/mengmei
//                    Document doc = Jsoup.connect("http://www.mmjpg.com/tag/mengmei").get();
//                    Elements els = doc.select("div.pic");
//                    //Log.e("萌妹", els.toString());
//                    Elements elements = els.select("li");
//                    //Log.e("萌妹-li", elements.toString());
//                    for (int i = 0; i < elements.size(); i++) {

//                        Element el = elements.get(i);
//                        //扩展名为.jpg的图片
//                        Elements jpgs = el.select("img[src$=.jpg]");
//                        String src = jpgs.attr("src");
//                        String alt = jpgs.attr("alt");
//
//                    }
                    Document doc = Jsoup.connect("http://www.mmonly.cc/ktmh/").get();
                    Elements els = doc.select("div.imgwkc");
                    //Log.e("萌妹", els.toString());
                    Elements elements = els.select("a");
                    //Log.e("萌妹-li", elements.toString());

                    for (int i = 0; i < elements.size(); i++) {
                        mMengMei = new MengMei();
                        Element el = elements.get(i);
                        //扩展名为.jpg的图片
                        Elements jpgs = el.select("img[src$=.jpg]");
                        String src = jpgs.attr("src");
                        String alt = jpgs.attr("alt");

                        Log.e("萌妹-jpgs", jpgs.toString());
                        Log.e("萌妹-src", src.toString());
                        Log.e("萌妹-alt", alt.toString());

                        mMengMei.setImg(src);
                        mMengMei.setAlt(alt);
                        mMeiList.add(mMengMei);

                    }

                } catch (IOException pE) {
                    pE.printStackTrace();
                }
                //通过mHandler对象的obtainMessage()
                //方法得到一个消息msg对象实例
                Message msg = mHandler.obtainMessage();
                //封装消息ID
                msg.what = MESSAGE_ID;
                //通过mHandler对象将消息发送出去
                mHandler.sendMessage(msg);
            }
        }).start();

    }

    //创建一个Handler局部类对象
    Handler mHandler = new Handler(){
        @Override
        public void handleMessage(Message msg) {

            //得到封装的消息ID进行匹配
            if (MESSAGE_ID == msg.what){
                //更换ImageView的背景
                initData();
            }
        }

    };

    private void initData() {
        // 加载网络图片
        // 创建布局管理
        LinearLayoutManager layoutManager = new LinearLayoutManager(getActivity());
        layoutManager.setOrientation(LinearLayoutManager.VERTICAL);
        mRecyclerView.setLayoutManager(layoutManager);
        // 创建适配器
        mMengMeiAdapter = new MengMeiAdapter(R.layout.item_img_list, mMeiList);
        // 给RecyclerView设置适配器
        mRecyclerView.setAdapter(mMengMeiAdapter);

        mMengMeiAdapter.setOnItemClickListener(new BaseQuickAdapter.OnItemClickListener() {
            @Override
            public void onItemClick(BaseQuickAdapter adapter, View view, int position) {
                Intent intent = new Intent(getActivity(), ImgDetailsActivity.class);
                Bundle bundle = new Bundle();
                bundle.putInt("position", position);
                intent.putExtra("bundle", bundle);
                startActivity(intent);
            }
        });

    }