test86

harvest是一个下载html网页得机器人

#
# Server-side
<reply>
<data nocheck=1>
HTTP/1.1 200 OK
Date: Thu, 09 Nov 2010 14:49:00 GMT
Server: test-server/fake
Last-Modified: Tue, 13 Jun 2000 12:10:00 GMT
ETag: "21025-dc7-39462498"
Accept-Ranges: bytes
Content-Length: 6
Connection: close
Content-Type: text/html
Funny-head: yesyes

<foo>
</data>
<data1>
HTTP/1.0 200 OK
Content-Type: text/html
Funny-head: swsclose

crap data
</data1>
<data2>
HTTP/1.0 200 OK
Content-Type: text/html
Funny-head: swsclose

crap data
</data2>
<data3>
HTTP/1.0 200 OK
Content-Type: text/html
Funny-head: swsclose

crap data
</data3>
</reply>

#
# Client-side
<client>
<server>
http
</server>
 <name>
HTTP, urlglob []-retrieval and -o #[num] usage
 </name>
 <command option=no-output>
"http://%HOSTIP:%HOSTPORT/[860001-860003]" -o "log/dumpit#1.dump"
</command>
</client>

#
# Verify data after the test has been "shot"
<verify>
<strip>
^User-Agent:.*
</strip>
<protocol>
GET /860001 HTTP/1.1
User-Agent: curl/7.10.7-pre4 (i686-pc-linux-gnu) libcurl/7.10.7-pre4 OpenSSL/0.9.7a ipv6 zlib/1.1.3 GSS
Host: 127.0.0.1:8999
Pragma: no-cache
Accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*

GET /860002 HTTP/1.1
User-Agent: curl/7.10.7-pre4 (i686-pc-linux-gnu) libcurl/7.10.7-pre4 OpenSSL/0.9.7a ipv6 zlib/1.1.3 GSS
Host: 127.0.0.1:8999
Pragma: no-cache
Accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*

GET /860003 HTTP/1.1
User-Agent: curl/7.10.7-pre4 (i686-pc-linux-gnu) libcurl/7.10.7-pre4 OpenSSL/0.9.7a ipv6 zlib/1.1.3 GSS
Host: 127.0.0.1:8999
Pragma: no-cache
Accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*

</protocol>

# we check the second file
<file name="log/dumpit860002.dump">
HTTP/1.0 200 OK
Content-Type: text/html
Funny-head: swsclose

crap data
</file>
</verify>