Created
March 18, 2014 06:36
-
-
Save melbourne2991/9614672 to your computer and use it in GitHub Desktop.
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
var request = require('request'); | |
var cheerio = require('cheerio'); | |
var fs = require('fs'); | |
var readline = require('readline'); | |
var stream = require('stream'); | |
if(process.argv[2] === '-links') { | |
var url = 'https://example.com/just-sold?price_min=0'; | |
var count = 1; | |
var is_next; | |
getNext(url); | |
console.log(); | |
function getNext(url) { | |
console.log('called'); | |
request(url, function(err, resp, body) { | |
if (err) | |
throw err; | |
$ = cheerio.load(body); | |
$('#listings > li').each(function() { | |
var data = $('.largetitle a', this).attr('href'); | |
if (data) | |
fs.appendFile('links.txt', data + '\n'); | |
}); | |
if($('.pagination .next').length > 0 && count < 3) { | |
count++; | |
url = 'https://example.com/just-sold?page=' + count +'&price_min=0' | |
getNext(url); | |
} else { | |
console.log('scrape complete'); | |
} | |
}); | |
} | |
} else if(process.argv[2] === '-pages') { | |
var count = 0; | |
var instream = fs.createReadStream('links.txt'); | |
var outstream = new stream; | |
var rl = readline.createInterface(instream, outstream); | |
rl.on('line', function(line) { | |
var url = 'https://example.com' + line; | |
request(url, function(err, resp, body) { | |
if (err) | |
throw err; | |
$ = cheerio.load(body); | |
// CSV format -- revenue,profit,date,niche,site type,monetization,domain registration date,implementation | |
}); | |
console.log(url); | |
}); | |
} else { | |
console.log('Please specify valid option'); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment