异步的node怎么打印出最后的结果,保证不是空的
发布于 4 年前 作者 ZhangMingZhao1 2100 次浏览 来自 问答

node新手爬虫,主要是异步流程的控制不是很熟练。 getTitleHref()函数是获取标题的链接,然后getLink()模拟进入了改标题的链接去获取到电影的bt链接种子。

现在我想打印出最后的ans结果,由于打印操作是同步的,直接打印会是空的,该怎么解决😂

const cheerio = require('cheerio');
const http = require('http');
const iconv = require('iconv-lite');

let baseUrl = "http://www.ygdy8.net/html/gndy/dyzz/list_23_";
let Host = "http://www.ygdy8.net/";

const totalPage = 2; //指定爬多少页数据
let ans = [];
//获取页面电影数据
function getTitleHref(url,page) {
  let startUrl = url+page+".html";
  http.get(startUrl,function(res) {
    const { statusCode } = res;
    let chunks = [];
    res.on('data',function(chunk){
      chunks.push(chunk);
    });
    res.on('end',function(){
      let title = [];
      
      let html = iconv.decode(Buffer.concat(chunks),'gb2312');
      let $ = cheerio.load(html, {decodeEntities: false});
      // console.log($);
      $('.co_content8 .ulink').each(function(i,d) {
        let $d = $(d);
        let titleHref = [];
        titleHref.push({
          href: $d.attr('href')
        });
        getLink(titleHref)
      });
      // console.log(ans);
    });  
  });
}


// /*
//获取种子链接
function getLink(titleHref) {
  console.log('进入getLink');
  console.log(titleHref);
  if(titleHref) {
    titleHref.forEach(function(v,k) {
      console.log('~~~~~~~~~~~~~~~~~~~~');
      let infoUrl = Host + v.href;
      // console.log(infoUrl);
    
        http.get(infoUrl,function(res) {
          const { statusCode } = res;
          const contentType = res.headers['content-type'];
        
          let error;
          if (statusCode !== 200) {
            error = new Error('请求失败。\n' +
                             `状态码: ${statusCode}`);
          } 
          if (error) {
            console.error(error.message);
            // 消耗响应数据以释放内存
            res.resume();
            return;
          }
          console.log('进入getlink http');
          let chunks = [];
          res.on('data',function(chunk) {  
            chunks.push(chunk);
          });
          res.on('end', function(){
            try {
              let html = iconv.decode(Buffer.concat(chunks),'gb2312');
              let $ = cheerio.load(html, {decodeEntities: false});
              let bt = '';
              bt = $('#Zoom td').children('a').attr('href');
              // console.log(bt);
              // console.log(typeof bt)
              ans.push(bt);
            }catch (e) {
              console.error('bt',e.message);
            }
          })
        }).on('error', (e) => {
          console.error(`错误: ${e.message}`);
        });
    });
  }
};
// */
for(let i = 1; i <= totalPage; i++) {
  getTitleHref(baseUrl,i);
};

3 回复

解决了,自问自答吧,看来cnnode的都是高手,不屑于回答这么低级的问题😂

const cheerio = require('cheerio')
const http = require('http')
const iconv = require('iconv-lite')

const baseUrl = 'http://www.ygdy8.net/html/gndy/dyzz/list_23_'
const Host = 'http://www.ygdy8.net/'

const totalPage = 2 //指定爬多少页数据
let ans = []
//获取页面电影数据
function getTitleHref(url, page) {
  return new Promise((resolve, reject) => {
    let startUrl = url + page + '.html'

    http.get(startUrl, function(res) {
      const { statusCode } = res
      let chunks = []
      res.on('data', function(chunk) {
        chunks.push(chunk)
      })
      res.on('end', function() {
        let title = []

        let html = iconv.decode(Buffer.concat(chunks), 'gb2312')
        let $ = cheerio.load(html, { decodeEntities: false })

        let titleHref = []
        $('.co_content8 .ulink').each(function(i, d) {
          let $d = $(d)
          titleHref.push({
            href: $d.attr('href')
          })
        })

        resolve(getLink(titleHref))
      })
    })
  })
}

// /*
//获取种子链接
function getLink(titleHref, cb) {
  console.log('进入getLink')
  console.log(titleHref)
  if (titleHref) {
    return Promise.all(
      titleHref.map(function(v, k) {
        return new Promise((resolve, reject) => {
          console.log('~~~~~~~~~~~~~~~~~~~~')
          let infoUrl = Host + v.href

          http
            .get(infoUrl, function(res) {
              const { statusCode } = res
              const contentType = res.headers['content-type']

              let error
              if (statusCode !== 200) {
                error = new Error('请求失败。\n' + `状态码: ${statusCode}`)
              }
              if (error) {
                console.error(error.message)
                // 消耗响应数据以释放内存
                res.resume()
                return
              }
              let chunks = []
              res.on('data', function(chunk) {
                chunks.push(chunk)
              })
              res.on('end', function() {
                try {
                  let html = iconv.decode(Buffer.concat(chunks), 'gb2312')
                  let $ = cheerio.load(html, { decodeEntities: false })
                  let bt = ''
                  bt = $('#Zoom td')
                    .children('a')
                    .attr('href')
                  resolve(bt)
                } catch (e) {
                  reject(e)
                }
              })
            })
            .on('error', e => {
              reject(e)
            })
        })
      })
    )
  } else {
    return Promise.resolve()
  }
}

async function main() {
  // */
  let results = await Promise.all(
    new Array(totalPage).fill().map((_, i) => getTitleHref(baseUrl, i + 1))
  )

  ans = ans.concat(...results)
  console.log('get data:', ans)
}

main()

这个阶段学习node 异步强烈建议直接上 async/await, 理解也比较容易,代码也好读

慢慢来,坑总是要踩的

回到顶部