爬虫spider

转：

爬虫spider

const originRequest = require('request');
const cheerio = require('cheerio');
const iconv = require('iconv-lite');

const request = (url, cb ) => {
    const options = {
        url: url,
        encoding: null
    };
    originRequest(url, options, cb);
}

for (let i=1; i< 10; i++) {
    const url = `https://www.gdnync.com/news/snzx/list_1_${i}.html`;
    request(url, (err, res, body) => {
        
        const html = iconv.decode(body, 'gb2312');
        const $ = cheerio.load(html);
        const list = $('.list-group-item');
        for (let i=0,len=list.length; i<len; i++)="" {="" let="" title="list.eq(i).find('.nc-subcolumn-list-item-title').text();" console.log(title);="" }="" })="" <="" code="">

标签：iconv,const,url,cheerio,list,spider,爬虫,html
来源： https://www.cnblogs.com/wangtcc/p/14743439.html