-
-
Save wanghaisheng/bc2483b3fc02ec0fe0f884443d18deb5 to your computer and use it in GitHub Desktop.
Getting the Alexa top 1 million sites directly from the server, unzipping it, parsing the csv and getting each line as an array. Now with majestic
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 unzip = require('unzip'); | |
var csv2 = require('csv2'); | |
const alexa = 'http://s3.amazonaws.com/alexa-static/top-1m.csv.zip' | |
const majestic = 'http://downloads.majesticseo.com/majestic_million.csv' | |
const sources = [majestic]; | |
const zSources = [alexa]; | |
source.forEach(getFile); | |
zSources.forEach(getZFile); | |
const getFile = (url) => { | |
request.get(url) | |
.on('entry', function (entry) { | |
entry.pipe(csv2()).on('data', console.log); | |
}); | |
} | |
const getZFile = (url) => { | |
request.get(url) | |
.pipe(unzip.Parse()) | |
.on('entry', function (entry) { | |
entry.pipe(csv2()).on('data', console.log); | |
}); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment