-
-
Save vintagesucks/02caa884904a0c5805ba2b58988a5c8d 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 writing each entry to a text file
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
| var request = require('request'); | |
| var unzip = require('unzip'); | |
| var csv2 = require('csv2'); | |
| var fs = require('fs'); | |
| var wstream = fs.createWriteStream('alexa.txt'); | |
| request.get('http://s3.amazonaws.com/alexa-static/top-1m.csv.zip') | |
| .pipe(unzip.Parse()) | |
| .on('entry', function (entry) { | |
| entry.pipe(csv2()).on('data', function (data) { | |
| wstream.write(data[1] + '\n'); | |
| }) | |
| }) | |
| ; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment