public class Demo2 {

 public static void main(String[] args) {

  // 需要爬的網(wǎng)頁(yè)的文章列表
  String url = "http://www.toutiao.com/news_finance/";
  //文章詳情頁(yè)的前綴(由于今日頭條的文章都是在group這個(gè)目錄下,所以定義了前綴,而且通過(guò)請(qǐng)求獲取到的html頁(yè)面)
  String url2="http://www.toutiao.com/group/";
  //鏈接到該網(wǎng)站
  Connection connection = Jsoup.connect(url);
  Document content = null;
  try {
    //獲取內(nèi)容
    content = connection.get();
  } catch (IOException e) {
    e.printStackTrace();
  }
  //轉(zhuǎn)換成字符串
  String htmlStr = content.html();
  //因?yàn)榻袢疹^條的文章展示比較奇葩,都是通過(guò)js定義成變量,所以無(wú)法使用獲取dom元素的方式獲取值
  String jsonStr = StringUtils.substringBetween(htmlStr,"var _data = ", ";");
  System.out.println(jsonStr);
  Map parse = (Map) JSONObject.parse(jsonStr);
  JSONArray parseArray = (JSONArray) parse.get("real_time_news");
  Map map=null;
  List<Map> maps=new ArrayList<>();
  //遍歷這個(gè)jsonArray,獲取到每一個(gè)json對(duì)象,然后將其轉(zhuǎn)換成Map對(duì)象(在這里其實(shí)只需要一個(gè)group_id,那么沒(méi)必要使用map)
  for(int i=0;i<parseArray.size();i++){
    map = (Map)parseArray.get(i);
    maps.add((Map)parseArray.get(i));
    System.out.println(map.get("group_id"));

  }
  //遍歷之前獲取到的map集合,然后分別訪問(wèn)這些文章詳情頁(yè)
  for (Map map2 : maps) {
    connection = Jsoup.connect(url2+map2.get("group_id"));
    try {
      Document document = connection.get();
      //獲取文章標(biāo)題
      Elements title = document.select("[class=article-title]");
      System.out.println(title.html());
      //獲取文章來(lái)源和文章發(fā)布時(shí)間
      Elements articleInfo = document.select("[class=articleInfo]");
      Elements src = articleInfo.select("[class=src]");
      System.out.println(src.html());
      Elements time = articleInfo.select("[class=time]");
      System.out.println(time.html());
      //獲取文章內(nèi)容
      Elements contentEle = document.select("[class=article-content]");
      System.out.println(contentEle.html());
    } catch (IOException e) {
      e.printStackTrace();
    }
  }
 }
}