test42

harvest是一个下载html网页得机器人

#
# Server-side
<reply>
<data>
HTTP/1.1 302 OK swsclose
Location: ../m o o.html/420002    
Date: Thu, 09 Nov 2010 14:49:00 GMT
Connection: close

</data>
<data2>
HTTP/1.1 200 OK swsclose
Location: this should be ignored
Date: Thu, 09 Nov 2010 14:49:00 GMT
Connection: close

body
</data2>
<datacheck>
HTTP/1.1 302 OK swsclose
Location: ../m o o.html/420002    
Date: Thu, 09 Nov 2010 14:49:00 GMT
Connection: close

HTTP/1.1 200 OK swsclose
Location: this should be ignored
Date: Thu, 09 Nov 2010 14:49:00 GMT
Connection: close

body
</datacheck>
</reply>

#
# Client-side
<client>
<server>
http
</server>
 <name>
HTTP redirect with whitespace in path (and conversion)
 </name>
 <command>
http://%HOSTIP:%HOSTPORT/we/are/all/twits/42 -L
</command>
</client>

#
# Verify data after the test has been "shot"
<verify>
<strip>
^User-Agent:.*
</strip>
<protocol>
GET /we/are/all/twits/42 HTTP/1.1
Host: 127.0.0.1:8999
Pragma: no-cache
Accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*

GET /we/are/all/m%20o%20o.html/420002 HTTP/1.1
User-Agent: curl/7.10 (i686-pc-linux-gnu) libcurl/7.10 OpenSSL/0.9.6c ipv6 zlib/1.1.3
Host: 127.0.0.1:8999
Pragma: no-cache
Accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*

</protocol>
</verify>