18行代码实现【node.js爬取网站详情页】

最新推荐文章于 2024-09-21 09:29:16 发布

老板来杯冰阔乐

最新推荐文章于 2024-09-21 09:29:16 发布

阅读量145

点赞数

文章标签： javascript node.js

本文链接：https://blog.csdn.net/weixin_43936341/article/details/115387391

版权

const axios = require('axios');
const cheerio = require('cheerio');

async function getDetail(url){
  const web_1 = await axios.get(url);
  const $_1 = cheerio.load(web_1.data);
  var items = $_1('div.volume-wrap ul.cf li');
  for(let i = 0; i < items.length; i++) {
    var item = items[i];
    var href = $_1(item).find('a').attr('href');
    const web_2 = await axios.get('https:' + href);
    const $_2 = cheerio.load(web_2.data);
    var detailName = $_2('div.text-head span.content-wrap').text();
    var detailContent = $_2('div.read-content p').text();
    console.log(detailName + '：' + detailContent);
  }
}
getDetail('https://book.qidian.com/info/1023781557#Catalog');