scrape from medium
mkdir nodewebscraper
cd nodewebscraper
npm init --yes
npm install
npm run dev
Last active
September 20, 2021 21:37
-
-
Save egohub/4235a0e1423e700b4b234ada2ac570bb to your computer and use it in GitHub Desktop.
medium scrape
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| const cheerio = require('cheerio'); | |
| const express = require('express'); | |
| const exphbs = require('express-handlebars'); | |
| const bodyParser = require('body-parser'); | |
| const request = require('request'); | |
| const app = express(); | |
| app.use(bodyParser.json()); | |
| app.use(bodyParser.urlencoded({extended : false})); | |
| app.engine('handlebars', exphbs({ defaultLayout : 'main'})); | |
| app.set('view engine','handlebars'); | |
| app.get('/', (req, res) => res.render('index', { layout: 'main' })); | |
| app.get('/search',async (req,res) => { | |
| const { tag } = req.query; | |
| let datas = []; | |
| request(`https://medium.com/search?q=${tag}`,(err,response,html) => { | |
| if(response.statusCode === 200){ | |
| const $ = cheerio.load(html); | |
| $('.js-block').each((i,el) => { | |
| const title = $(el).find('h3').text(); | |
| const article = $(el).find('.postArticle-content').find('a').attr('href'); | |
| let data = { | |
| title, | |
| article | |
| } | |
| datas.push(data); | |
| }) | |
| } | |
| console.log(datas); | |
| res.render('list',{ datas }) | |
| }) | |
| }) | |
| app.listen(3000,() => { | |
| console.log("server is running on port 3000"); | |
| }) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment