[Node.js]웹페이지 크롤링
Updated:
[코드]
const axios = require("axios");
const cheerio = require("cheerio");
const fs = require('fs');
const log = console.log;
var file = 'temp_text.txt';
fs.open(file, 'w', function(err, fd){
if(err) throw err;
console.log('file open complete');
});
const getHtml = async () => {
try {
return await axios.get("https://kimmusic.github.io/");
}
catch (error) { console.error(error); } };
getHtml()
.then(html => {
let ulList = [];
const $ = cheerio.load(html.data);
const $bodyList = $("div.entries-list").children("div.list__item");
$bodyList.each(function(i, elem) {
ulList[i] = {
title: $(this).find('article p.archive__item-excerpt').text()};
});
for(var i = 0; i < ulList.length; ++i)
fs.appendFileSync('temp_text.txt', ulList[i].title + '\n', 'utf-8', function(error){
console.log(k + 'error');
});
const data = ulList.filter(n => n.title);
return data;
}) .then(res => log(res));
참고한 블로그 : https://velog.io/@yesdoing/Node.js-%EC%97%90%EC%84%9C-%EC%9B%B9-%ED%81%AC%EB%A1%A4%EB%A7%81%ED%95%98%EA%B8%B0-wtjugync1m
https://mine7717.tistory.com/11
댓글남기기