尝试用 node写爬虫,报错了
代码:
let http = require('http');
let https = require('https');
let fs = require('fs');
let cheerio = require('cheerio');
let request = require('request');
let options = {
hostname: 'http://sz.58.com/chuzu/',
method: 'get'
};
function outToFile($, content){
}
let req = http.request(options, function(res){
let html = '';
let nextPage = '';
res.on('data', function(chunk){
html+=chunk;
});
res.on('end', function(){
let $ = cheerio.load(html);
let item = $('.listUl li').each(function(){
console.log('1');
});
});
}).on('error', function(err){
console.log(err);
});
req.end();
{ Error: getaddrinfo ENOTFOUND http://sz.58.com/chuzu/ http://sz.58.com/chuzu/:80
at errnoException (dns.js:28:10)
at GetAddrInfoReqWrap.onlookup [as oncomplete] (dns.js:76:26)
code: 'ENOTFOUND',
errno: 'ENOTFOUND',
syscall: 'getaddrinfo',
hostname: 'http://sz.58.com/chuzu/',
host: 'http://sz.58.com/chuzu/',
port: 80 }
咋整啊?
请查阅文档;
另外,URL格式为:
protocol://hostname[:port]/path/[;parameters][?query]#fragment
。