home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
The Datafile PD-CD 5
/
DATAFILE_PDCD5.iso
/
utilities
/
p
/
python
/
!Python
/
Lib
/
NetLib
/
py
/
BaseHTTPSe
next >
Wrap
Text File
|
1996-02-12
|
15KB
|
483 lines
"""HTTP server base class.
Note: the class in this module doesn't implement any HTTP request; see
SimpleHTTPServer for simple implementations of GET, HEAD and POST
(including CGI scripts).
Contents:
- BaseHTTPRequestHandler: HTTP request handler base class
- test: test function
XXX To do:
- send server version
- log requests even later (to capture byte count)
- log user-agent header and other interesting goodies
- send error log to separate file
- are request names really case sensitive?
"""
# See also:
#
# HTTP Working Group T. Berners-Lee
# INTERNET-DRAFT R. T. Fielding
# <draft-ietf-http-v10-spec-00.txt> H. Frystyk Nielsen
# Expires September 8, 1995 March 8, 1995
#
# URL: http://www.ics.uci.edu/pub/ietf/http/draft-ietf-http-v10-spec-00.txt
# Log files
# ---------
#
# Here's a quote from the NCSA httpd docs about log file format.
#
# | The logfile format is as follows. Each line consists of:
# |
# | host rfc931 authuser [DD/Mon/YYYY:hh:mm:ss] "request" ddd bbbb
# |
# | host: Either the DNS name or the IP number of the remote client
# | rfc931: Any information returned by identd for this person,
# | - otherwise.
# | authuser: If user sent a userid for authentication, the user name,
# | - otherwise.
# | DD: Day
# | Mon: Month (calendar name)
# | YYYY: Year
# | hh: hour (24-hour format, the machine's timezone)
# | mm: minutes
# | ss: seconds
# | request: The first line of the HTTP request as sent by the client.
# | ddd: the status code returned by the server, - if not available.
# | bbbb: the total number of bytes sent,
# | *not including the HTTP/1.0 header*, - if not available
# |
# | You can determine the name of the file accessed through request.
#
# (Actually, the latter is only true if you know the server configuration
# at the time the request was made!)
__version__ = "0.2"
import sys
import time
import socket # For gethostbyaddr()
import string
import rfc822
import mimetools
import SocketServer
# Default error message
DEFAULT_ERROR_MESSAGE = """\
<head>
<title>Error response</title>
</head>
<body>
<h1>Error response</h1>
<p>Error code %(code)d.
<p>Message: %(message)s.
<p>Error code explanation: %(code)s = %(explain)s.
</body>
"""
class HTTPServer(SocketServer.TCPServer):
def server_bind(self):
"""Override server_bind to store the server name."""
SocketServer.TCPServer.server_bind(self)
host, port = self.socket.getsockname()
if not host or host == '0.0.0.0':
host = socket.gethostname()
hostname, hostnames, hostaddrs = socket.gethostbyaddr(host)
if '.' not in hostname:
for host in hostnames:
if '.' in host:
hostname = host
break
self.server_name = hostname
self.server_port = port
class BaseHTTPRequestHandler(SocketServer.StreamRequestHandler):
"""HTTP request handler base class.
The following explanation of HTTP serves to guide you through the
code as well as to expose any misunderstandings I may have about
HTTP (so you don't need to read the code to figure out I'm wrong
:-).
HTTP (HyperText Transfer Protocol) is an extensible protocol on
top of a reliable stream transport (e.g. TCP/IP). The protocol
recognizes three parts to a request:
1. One line identifying the request type and path
2. An optional set of RFC-822-style headers
3. An optional data part
The headers and data are separated by a blank line.
The first line of the request has the form
<command> <path> <version>
where <command> is a (case-sensitive) keyword such as GET or POST,
<path> is a string containing path information for the request,
and <version> should be the string "HTTP/1.0". <path> is encoded
using the URL encoding scheme (using %xx to signify the ASCII
character with hex code xx).
The protocol is vague about whether lines are separated by LF
characters or by CRLF pairs -- for compatibility with the widest
range of clients, both should be accepted. Similarly, whitespace
in the request line should be treated sensibly (allowing multiple
spaces between components and allowing trailing whitespace).
Similarly, for output, lines ought to be separated by CRLF pairs
but most clients grok LF characters just fine.
If the first line of the request has the form
<command> <path>
(i.e. <version> is left out) then this is assumed to be an HTTP
0.9 request; this form has no optional headers and data part and
the reply consists of just the data.
The reply form of the HTTP 1.0 protocol again has three parts:
1. One line giving the response code
2. An optional set of RFC-822-style headers
3. The data
Again, the headers and data are separated by a blank line.
The response code line has the form
<version> <responsecode> <responsestring>
where <version> is the protocol version (always "HTTP/1.0"),
<responsecode> is a 3-digit response code indicating success or
failure of the request, and <responsestring> is an optional
human-readable string explaining what the response code means.
This server parses the request and the headers, and then calls a
function specific to the request type (<command>). Specifically,
a request SPAM will be handled by a method handle_SPAM(). If no
such method exists the server sends an error response to the
client. If it exists, it is called with no arguments:
do_SPAM()
Note that the request name is case sensitive (i.e. SPAM and spam
are different requests).
The various request details are stored in instance variables:
- client_address is the client IP address in the form (host,
port);
- command, path and version are the broken-down request line;
- headers is an instance of mimetools.Message (or a derived
class) containing the header information;
- rfile is a file object open for reading positioned at the
start of the optional input data part;
- wfile is a file object open for writing.
IT IS IMPORTANT TO ADHERE TO THE PROTOCOL FOR WRITING!
The first thing to be written must be the response line. Then
follow 0 or more header lines, then a blank line, and then the
actual data (if any). The meaning of the header lines depends on
the command executed by the server; in most cases, when data is
returned, there should be at least one header line of the form
Content-type: <type>/<subtype>
where <type> and <subtype> should be registered MIME types,
e.g. "text/html" or "text/plain".
"""
# The Python system version, truncated to its first component.
sys_version = "Python/" + string.split(sys.version)[0]
# The server software version. You may want to override this.
# The format is multiple whitespace-separated strings,
# where each string is of the form name[/version].
server_version = "BaseHTTP/" + __version__
def handle(self):
"""Handle a single HTTP request.
You normally don't need to override this method; see the class
__doc__ string for information on how to handle specific HTTP
commands such as GET and POST.
"""
self.raw_requestline = self.rfile.readline()
self.request_version = version = "HTTP/0.9" # Default
requestline = self.raw_requestline
if requestline[-2:] == '\r\n':
requestline = requestline[:-2]
elif requestline[-1:] == '\n':
requestline = requestline[:-1]
self.requestline = requestline
words = string.split(requestline)
if len(words) == 3:
[command, path, version] = words
if version != self.protocol_version:
self.send_error(400, "Bad request version (%s)" % `version`)
return
elif len(words) == 2:
[command, path] = words
if command != 'GET':
self.send_error(400,
"Bad HTTP/0.9 request type (%s)" % `command`)
return
else:
self.send_error(400, "Bad request syntax (%s)" % `requestline`)
return
self.command, self