Created
November 4, 2011 21:40
-
-
Save baudehlo/1340555 to your computer and use it in GitHub Desktop.
Cannot figure out why this isn't working.
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 http = require('http'); | |
var Iconv = require('iconv').Iconv; | |
var bt = require('buffertools'); | |
var google = http.createClient(80, 'www.google.it'); | |
var assert = require('assert'); | |
var request = google.request('GET', '/', | |
{ | |
'host': 'www.google.it', | |
'Accept-Charset': 'UTF-8', | |
// Uncomment this to get the data in UTF-8 (and then it works fine) | |
// 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.106 Safari/535', | |
'Accept-Language': 'en-GB', | |
'Accept': 'text/html', | |
} | |
); | |
request.end(); | |
request.on('response', function (response) { | |
var bufflist = []; | |
response.on('data', function (chunk) { | |
bufflist.push(chunk); | |
}); | |
response.on('end', function () { | |
var ct = response.headers['content-type']; | |
var matches = /\bcharset\s*=\s*(?:\"|3D|')?([\w_\-]*)(?:\"|3D|')?/.exec(ct); | |
var enc = 'UTF-8'; | |
if (matches) { | |
enc = matches[1].toUpperCase(); | |
} | |
var iconv = new Iconv(enc, "UTF-8"); | |
console.log("Converting to: " + enc); | |
var outbuf = bt.concat.apply(bt, bufflist); | |
// if I do this, it doesn't work right - the data is incorrect and I get: | |
// "il server non č riuscito" | |
// in the output | |
process.stdout.write(iconv.convert(outbuf)); | |
// If however I comment that out, and uncomment this one, and run: | |
// node scriptname.js | iconv -f ISO-8859-1 -t UTF-8 | |
// then I get the required output, which contains: | |
// "il server non è riuscito" | |
//process.stdout.write(outbuf); | |
}); | |
}); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment