Created
December 6, 2016 21:12
-
-
Save brizandrew/850ac0bb860bcac07f406cd6223dddc9 to your computer and use it in GitHub Desktop.
Basic web scraping example with node
This file contains 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
/* | |
Basic web scraping example with node | |
Includes scape and SQL insert | |
Variant of guide found here: https://scotch.io/tutorials/scraping-the-web-with-node-js | |
Scrapes the title of Anchorman 2 and places it into SQL table | |
*/ | |
var express = require('express'); | |
var fs = require('fs'); | |
var request = require('request'); | |
var cheerio = require('cheerio'); | |
var mysql = require('mysql'); | |
var app = express(); | |
var connection = mysql.createConnection({ | |
host : '', | |
user : '', | |
password : '', | |
database : '' | |
}); | |
function scrape(){ | |
var url = 'http://www.imdb.com/title/tt1229340/'; | |
request(url, function(error, response, html){ | |
if(!error){ | |
var $ = cheerio.load(html); | |
var result; | |
$('.title_wrapper').filter(function(){ | |
var data = $(this); | |
title = data.children().first().text(); | |
result = title; | |
}); | |
saveToSQL(result); | |
} | |
}) | |
} | |
function saveToSQL(title){ | |
connection.connect(); | |
connection.query('INSERT INTO test(text) VALUES(?)',[title],function(err,result){ | |
console.log('Inserted ' + title + ' into table.') | |
}); | |
connection.end(); | |
} | |
app.get('/scrape', function(req, res){ | |
scrape(); | |
res.send('See console for results.') | |
}); | |
app.listen('8000') | |
console.log('Listening on localhost:8000/scrape') | |
exports = module.exports = app; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment