Created
January 5, 2016 18:48
-
-
Save thejefflarson/e57cefd2eb09ec0c8dee 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
extern crate hyper; | |
extern crate flate2; | |
use hyper::Client; | |
use std::io::{BufRead, BufReader}; | |
use flate2::read::GzDecoder; | |
fn main() { | |
let client = Client::new(); | |
let res = client.get("https://aws-publicdatasets.s3.amazonaws.com/common-crawl/crawl-data/CC-MAIN-2015-40/segments/1443736672328.14/wat/CC-MAIN-20151001215752-00000-ip-10-137-6-227.ec2.internal.warc.wat.gz") | |
.send().unwrap(); | |
let decoder = GzDecoder::new(res).unwrap(); | |
let reader = BufReader::new(decoder); | |
for c in reader.lines() { | |
println!("{}", c.unwrap()); | |
} | |
} | |
/* | |
only outputs a few lines, should spew megabytes: | |
WARC/1.0 | |
WARC-Type: warcinfo | |
WARC-Date: 2015-11-08T20:11:50Z | |
WARC-Filename: CC-MAIN-20151001215752-00000-ip-10-137-6-227.ec2.internal.warc.gz | |
WARC-Record-ID: <urn:uuid:64b2a8b0-ad11-406f-8619-0d615ff46a0b> | |
Content-Type: application/warc-fields | |
Content-Length: 108 | |
Software-Info: ia-web-commons.1.0-SNAPSHOT-20151107044109 | |
Extracted-Date: Sun, 08 Nov 2015 20:11:50 GMT | |
*/ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment