mirror of
https://github.com/webrecorder/pywb.git
synced 2025-03-15 00:03:28 +01:00
add uncompressed warc
This commit is contained in:
parent
312bd71568
commit
531464902f
187
sample_archive/warcs/example.warc
Normal file
187
sample_archive/warcs/example.warc
Normal file
@ -0,0 +1,187 @@
|
||||
WARC/1.0
|
||||
WARC-Type: warcinfo
|
||||
WARC-Record-ID: <urn:uuid:fbd6cf0a-6160-4550-b343-12188dc05234>
|
||||
WARC-Date: 2014-01-03T03:03:22Z
|
||||
Content-Length: 196
|
||||
Content-Type: application/warc-fields
|
||||
WARC-Filename: live-20140103030321-wwwb-app5.us.archive.org.warc.gz
|
||||
|
||||
software: LiveWeb Warc Writer 1.0
|
||||
host: wwwb-app5.us.archive.org
|
||||
isPartOf: liveweb
|
||||
format: WARC file version 1.0
|
||||
conformsTo: http://bibnum.bnf.fr/WARC/WARC_ISO_28500_version1_latestdraft.pdf
|
||||
|
||||
|
||||
WARC/1.0
|
||||
WARC-Type: response
|
||||
WARC-Record-ID: <urn:uuid:6d058047-ede2-4a13-be79-90c17c631dd4>
|
||||
WARC-Date: 2014-01-03T03:03:21Z
|
||||
Content-Length: 1610
|
||||
Content-Type: application/http; msgtype=response
|
||||
WARC-Payload-Digest: sha1:B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A
|
||||
WARC-Target-URI: http://example.com?example=1
|
||||
WARC-Warcinfo-ID: <urn:uuid:fbd6cf0a-6160-4550-b343-12188dc05234>
|
||||
|
||||
HTTP/1.1 200 OK
|
||||
Accept-Ranges: bytes
|
||||
Cache-Control: max-age=604800
|
||||
Content-Type: text/html
|
||||
Date: Fri, 03 Jan 2014 03:03:21 GMT
|
||||
Etag: "359670651"
|
||||
Expires: Fri, 10 Jan 2014 03:03:21 GMT
|
||||
Last-Modified: Fri, 09 Aug 2013 23:54:35 GMT
|
||||
Server: ECS (sjc/4FCE)
|
||||
X-Cache: HIT
|
||||
x-ec-custom-error: 1
|
||||
Content-Length: 1270
|
||||
Connection: close
|
||||
|
||||
<!doctype html>
|
||||
<html>
|
||||
<head>
|
||||
<title>Example Domain</title>
|
||||
|
||||
<meta charset="utf-8" />
|
||||
<meta http-equiv="Content-type" content="text/html; charset=utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
<style type="text/css">
|
||||
body {
|
||||
background-color: #f0f0f2;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
font-family: "Open Sans", "Helvetica Neue", Helvetica, Arial, sans-serif;
|
||||
|
||||
}
|
||||
div {
|
||||
width: 600px;
|
||||
margin: 5em auto;
|
||||
padding: 50px;
|
||||
background-color: #fff;
|
||||
border-radius: 1em;
|
||||
}
|
||||
a:link, a:visited {
|
||||
color: #38488f;
|
||||
text-decoration: none;
|
||||
}
|
||||
@media (max-width: 700px) {
|
||||
body {
|
||||
background-color: #fff;
|
||||
}
|
||||
div {
|
||||
width: auto;
|
||||
margin: 0 auto;
|
||||
border-radius: 0;
|
||||
padding: 1em;
|
||||
}
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
|
||||
<body>
|
||||
<div>
|
||||
<h1>Example Domain</h1>
|
||||
<p>This domain is established to be used for illustrative examples in documents. You may use this
|
||||
domain in examples without prior coordination or asking for permission.</p>
|
||||
<p><a href="http://www.iana.org/domains/example">More information...</a></p>
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
|
||||
|
||||
WARC/1.0
|
||||
WARC-Type: request
|
||||
WARC-Record-ID: <urn:uuid:9a3ffea5-9556-4790-a6bf-c15231fd6b97>
|
||||
WARC-Date: 2014-01-03T03:03:21Z
|
||||
Content-Length: 323
|
||||
Content-Type: application/http; msgtype=request
|
||||
WARC-Concurrent-To: <urn:uuid:6d058047-ede2-4a13-be79-90c17c631dd4>
|
||||
WARC-Target-URI: http://example.com?example=1
|
||||
WARC-Warcinfo-ID: <urn:uuid:fbd6cf0a-6160-4550-b343-12188dc05234>
|
||||
|
||||
GET /?example=1 HTTP/1.1
|
||||
Connection: close
|
||||
Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8
|
||||
Accept-Language: en-US,en;q=0.8
|
||||
User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.57 Safari/537.36 (via Wayback Save Page)
|
||||
Host: example.com
|
||||
|
||||
|
||||
WARC/1.0
|
||||
WARC-Type: revisit
|
||||
WARC-Record-ID: <urn:uuid:3619f5b0-d967-44be-8f24-762098d427c4>
|
||||
WARC-Date: 2014-01-03T03:03:41Z
|
||||
Content-Length: 340
|
||||
Content-Type: application/http; msgtype=response
|
||||
WARC-Payload-Digest: sha1:B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A
|
||||
WARC-Target-URI: http://example.com?example=1
|
||||
WARC-Warcinfo-ID: <urn:uuid:fbd6cf0a-6160-4550-b343-12188dc05234>
|
||||
WARC-Profile: http://netpreserve.org/warc/0.18/revisit/identical-payload-digest
|
||||
WARC-Refers-To-Target-URI: http://example.com?example=1
|
||||
WARC-Refers-To-Date: 2014-01-03T03:03:21Z
|
||||
|
||||
HTTP/1.1 200 OK
|
||||
Accept-Ranges: bytes
|
||||
Cache-Control: max-age=604800
|
||||
Content-Type: text/html
|
||||
Date: Fri, 03 Jan 2014 03:03:41 GMT
|
||||
Etag: "359670651"
|
||||
Expires: Fri, 10 Jan 2014 03:03:41 GMT
|
||||
Last-Modified: Fri, 09 Aug 2013 23:54:35 GMT
|
||||
Server: ECS (sjc/4FCE)
|
||||
X-Cache: HIT
|
||||
x-ec-custom-error: 1
|
||||
Content-Length: 1270
|
||||
Connection: close
|
||||
|
||||
|
||||
|
||||
WARC/1.0
|
||||
WARC-Type: request
|
||||
WARC-Record-ID: <urn:uuid:c59f3330-b241-4fca-8513-d687cd85bcfb>
|
||||
WARC-Date: 2014-01-03T03:03:41Z
|
||||
Content-Length: 323
|
||||
Content-Type: application/http; msgtype=request
|
||||
WARC-Concurrent-To: <urn:uuid:3619f5b0-d967-44be-8f24-762098d427c4>
|
||||
WARC-Target-URI: http://example.com?example=1
|
||||
WARC-Warcinfo-ID: <urn:uuid:fbd6cf0a-6160-4550-b343-12188dc05234>
|
||||
|
||||
GET /?example=1 HTTP/1.1
|
||||
Connection: close
|
||||
Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8
|
||||
Accept-Language: en-US,en;q=0.8
|
||||
User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.57 Safari/537.36 (via Wayback Save Page)
|
||||
Host: example.com
|
||||
|
||||
|
||||
WARC/1.0
|
||||
WARC-Type: response
|
||||
WARC-Record-ID: <urn:uuid:1d673b2a-c593-402e-8973-3950d0bc6163>
|
||||
WARC-Date: 2014-01-28T05:15:39Z
|
||||
Content-Length: 471
|
||||
Content-Type: application/http; msgtype=response
|
||||
WARC-Payload-Digest: sha1:JZ622UA23G5ZU6Y3XAKH4LINONUEICEG
|
||||
WARC-Target-URI: http://www.iana.org/domains/example
|
||||
WARC-Warcinfo-ID: <urn:uuid:e9f7f74b-0280-47fd-99bc-f00f1a570a46>
|
||||
|
||||
HTTP/1.1 302 Found
|
||||
Server: Apache
|
||||
Location: /domains/reserved
|
||||
Content-Type: text/html; charset=iso-8859-1
|
||||
Content-Length: 201
|
||||
Accept-Ranges: bytes
|
||||
Date: Tue, 28 Jan 2014 05:15:39 GMT
|
||||
X-Varnish: 774901408 774900872
|
||||
Age: 80
|
||||
Via: 1.1 varnish
|
||||
Connection: close
|
||||
|
||||
<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML 2.0//EN">
|
||||
<html><head>
|
||||
<title>302 Found</title>
|
||||
</head><body>
|
||||
<h1>Found</h1>
|
||||
<p>The document has moved <a href="/domains/reserved">here</a>.</p>
|
||||
</body></html>
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user