python 基础网络编程2
前一篇讲了socketserver.py中BaseServer类, 下面介绍下TCPServer和UDPServer
class TCPServer(BaseServer):
"""Base class for various socket-based server classes.
Defaults to synchronous IP stream (i.e., TCP).
Methods for the caller:
- __init__(server_address, RequestHandlerClass, bind_and_activate=True)
- serve_forever(poll_interval=0.5)
- shutdown()
- handle_request() # if you don't use serve_forever()
- fileno() -> int # for selector
Methods that may be overridden:
- server_bind()
- server_activate()
- get_request() -> request, client_address
- handle_timeout()
- verify_request(request, client_address)
- process_request(request, client_address)
- shutdown_request(request)
- close_request(request)
- handle_error()
Methods for derived classes:
- finish_request(request, client_address)
Class variables that may be overridden by derived classes or
instances:
- timeout
- address_family
- socket_type
- request_queue_size (only for stream sockets)
- allow_reuse_address
Instance variables:
- server_address
- RequestHandlerClass
- socket
"""
address_family = socket.AF_INET
socket_type = socket.SOCK_STREAM
request_queue_size = 5
allow_reuse_address = False
def __init__(self, server_address, RequestHandlerClass, bind_and_activate=True):
"""Constructor. May be extended, do not override."""
BaseServer.__init__(self, server_address, RequestHandlerClass)
self.socket = socket.socket(self.address_family,
self.socket_type)
if bind_and_activate:
try:
self.server_bind()
self.server_activate()
except:
self.server_close()
raise
def server_bind(self):
"""Called by constructor to bind the socket.
May be overridden.
"""
if self.allow_reuse_address:
self.socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
self.socket.bind(self.server_address)
self.server_address = self.socket.getsockname()
def server_activate(self):
"""Called by constructor to activate the server.
May be overridden.
"""
self.socket.listen(self.request_queue_size)
def server_close(self):
"""Called to clean-up the server.
May be overridden.
"""
self.socket.close()
def fileno(self):
"""Return socket file number.
Interface required by selector.
"""
return self.socket.fileno()
def get_request(self):
"""Get the request and client address from the socket.
May be overridden.
"""
return self.socket.accept()
def shutdown_request(self, request):
"""Called to shutdown and close an individual request."""
try:
#explicitly shutdown. socket.close() merely releases
#the socket and waits for GC to perform the actual close.
request.shutdown(socket.SHUT_WR)
except OSError:
pass #some platforms may raise ENOTCONN here
self.close_request(request)
def close_request(self, request):
"""Called to clean up an individual request."""
request.close()
可见基本上没有动, 只是针对tcp协议做了相应的变化, 基本的模式还是在BaseServer上, 重要函数都没有重载. UDP也一样.
HTTP Server
源码在Lib/http/server.py
主要定义了根据socketserver.TCPServer构建的HTTPServer. 其中有两个类比较重要, 一个是HTTPServer, 一个是RequestHandlerClass.(这里有三个实现BaseHTTPRequestHandler, SimpleHTTPRequestHandler, CGIHTTPRequestHandler) 下面具体分析.
def run(server_class=HTTPServer, handler_class=BaseHTTPRequestHandler):
server_address = ('', 8000)
httpd = server_class(server_address, handler_class)
httpd.serve_forever()
类似以上代码就可以实现一个简单的HTTPServer, 其中server_address会下沉到socket中, handler_class需要一个RequestHandlerClass, 但是BaseHTTPRequestHandler并没有具体实现HTTP的GET, POST等请求, 具体是在SimpleHTTPRequestHandler中, 而有关CGI脚本的相关实现都在CGIHTTPRequestHandler上.
class HTTPServer(socketserver.TCPServer):
allow_reuse_address = 1 # Seems to make sense in testing environment
def server_bind(self):
"""Override server_bind to store the server name."""
socketserver.TCPServer.server_bind(self)
host, port = self.socket.getsockname()[:2]
self.server_name = socket.getfqdn(host)
self.server_port = port
HTTPServer类本身就是把处理的部分都放在RequestHandlerClass, 而连接等相关的部分也有TCPServer处理了.
所以重点在于RequestHandlerClass, 先看下BaseHTTPRequestHandler:
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" or "HTTP/1.1".
<path> is encoded using the URL encoding scheme (using %xx to signify
the ASCII character with hex code xx).
The specification specifies that lines are separated by CRLF but
for compatibility with the widest range of clients recommends
servers also handle LF. Similarly, whitespace in the request line
is 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.x 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 ("HTTP/1.0" or "HTTP/1.1"),
<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 do_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 email.message.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/" + sys.version.split()[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__
error_message_format = DEFAULT_ERROR_MESSAGE
error_content_type = DEFAULT_ERROR_CONTENT_TYPE
# The default request version. This only affects responses up until
# the point where the request line is parsed, so it mainly decides what
# the client gets back when sending a malformed request line.
# Most web servers default to HTTP 0.9, i.e. don't send a status line.
default_request_version = "HTTP/0.9"
def parse_request(self):
"""Parse a request (internal).
The request should be stored in self.raw_requestline; the results
are in self.command, self.path, self.request_version and
self.headers.
Return True for success, False for failure; on failure, an
error is sent back.
"""
self.command = None # set in case of error on the first line
self.request_version = version = self.default_request_version
self.close_connection = True
requestline = str(self.raw_requestline, 'iso-8859-1')
requestline = requestline.rstrip('
')
self.requestline = requestline
words = requestline.split()
if len(words) == 3:
command, path, version = words
if version[:5] != 'HTTP/':
self.send_error(
HTTPStatus.BAD_REQUEST,
"Bad request version (%r)" % version)
return False
try:
base_version_number = version.split('/', 1)[1]
version_number = base_version_number.split(".")
# RFC 2145 section 3.1 says there can be only one "." and
# - major and minor numbers MUST be treated as
# separate integers;
# - HTTP/2.4 is a lower version than HTTP/2.13, which in
# turn is lower than HTTP/12.3;
# - Leading zeros MUST be ignored by recipients.
if len(version_number) != 2:
raise ValueError
version_number = int(version_number[0]), int(version_number[1])
except (ValueError, IndexError):
self.send_error(
HTTPStatus.BAD_REQUEST,
"Bad request version (%r)" % version)
return False
if version_number >= (1, 1) and self.protocol_version >= "HTTP/1.1":
self.close_connection = False
if version_number >= (2, 0):
self.send_error(
HTTPStatus.HTTP_VERSION_NOT_SUPPORTED,
"Invalid HTTP Version (%s)" % base_version_number)
return False
elif len(words) == 2:
command, path = words
self.close_connection = True
if command != 'GET':
self.send_error(
HTTPStatus.BAD_REQUEST,
"Bad HTTP/0.9 request type (%r)" % command)
return False
elif not words:
return False
else:
self.send_error(
HTTPStatus.BAD_REQUEST,
"Bad request syntax (%r)" % requestline)
return False
self.command, self.path, self.request_version = command, path, version
# Examine the headers and look for a Connection directive.
try:
self.headers = http.client.parse_headers(self.rfile,
_class=self.MessageClass)
except http.client.LineTooLong:
self.send_error(
HTTPStatus.BAD_REQUEST,
"Line too long")
return False
except http.client.HTTPException as err:
self.send_error(
HTTPStatus.REQUEST_HEADER_FIELDS_TOO_LARGE,
"Too many headers",
str(err)
)
return False
conntype = self.headers.get('Connection', "")
if conntype.lower() == 'close':
self.close_connection = True
elif (conntype.lower() == 'keep-alive' and
self.protocol_version >= "HTTP/1.1"):
self.close_connection = False
# Examine the headers and look for an Expect directive
expect = self.headers.get('Expect', "")
if (expect.lower() == "100-continue" and
self.protocol_version >= "HTTP/1.1" and
self.request_version >= "HTTP/1.1"):
if not self.handle_expect_100():
return False
return True
def handle_expect_100(self):
"""Decide what to do with an "Expect: 100-continue" header.
If the client is expecting a 100 Continue response, we must
respond with either a 100 Continue or a final response before
waiting for the request body. The default is to always respond
with a 100 Continue. You can behave differently (for example,
reject unauthorized requests) by overriding this method.
This method should either return True (possibly after sending
a 100 Continue response) or send an error response and return
False.
"""
self.send_response_only(HTTPStatus.CONTINUE)
self.end_headers()
return True
def handle_one_request(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.
"""
try:
self.raw_requestline = self.rfile.readline(65537)
if len(self.raw_requestline) > 65536:
self.requestline = ''
self.request_version = ''
self.command = ''
self.send_error(HTTPStatus.REQUEST_URI_TOO_LONG)
return
if not self.raw_requestline:
self.close_connection = True
return
if not self.parse_request():
# An error code has been sent, just exit
return
mname = 'do_' + self.command
if not hasattr(self, mname):
self.send_error(
HTTPStatus.NOT_IMPLEMENTED,
"Unsupported method (%r)" % self.command)
return
method = getattr(self, mname)
method()
self.wfile.flush() #actually send the response if not already done.
except socket.timeout as e:
#a read or a write timed out. Discard this connection
self.log_error("Request timed out: %r", e)
self.close_connection = True
return
def handle(self):
"""Handle multiple requests if necessary."""
self.close_connection = True
self.handle_one_request()
while not self.close_connection:
self.handle_one_request()
def send_error(self, code, message=None, explain=None):
"""Send and log an error reply.
Arguments are
* code: an HTTP error code
3 digits
* message: a simple optional 1 line reason phrase.
*( HTAB / SP / VCHAR / %x80-FF )
defaults to short entry matching the response code
* explain: a detailed message defaults to the long entry
matching the response code.
This sends an error response (so it must be called before any
output has been generated), logs the error, and finally sends
a piece of HTML explaining the error to the user.
"""
try:
shortmsg, longmsg = self.responses[code]
except KeyError:
shortmsg, longmsg = '???', '???'
if message is None:
message = shortmsg
if explain is None:
explain = longmsg
self.log_error("code %d, message %s", code, message)
self.send_response(code, message)
self.send_header('Connection', 'close')
# Message body is omitted for cases described in:
# - RFC7230: 3.3. 1xx, 204(No Content), 304(Not Modified)
# - RFC7231: 6.3.6. 205(Reset Content)
body = None
if (code >= 200 and
code not in (HTTPStatus.NO_CONTENT,
HTTPStatus.RESET_CONTENT,
HTTPStatus.NOT_MODIFIED)):
# HTML encode to prevent Cross Site Scripting attacks
# (see bug #1100201)
content = (self.error_message_format % {
'code': code,
'message': _quote_html(message),
'explain': _quote_html(explain)
})
body = content.encode('UTF-8', 'replace')
self.send_header("Content-Type", self.error_content_type)
self.send_header('Content-Length', int(len(body)))
self.end_headers()
if self.command != 'HEAD' and body:
self.wfile.write(body)
def send_response(self, code, message=None):
"""Add the response header to the headers buffer and log the
response code.
Also send two standard headers with the server software
version and the current date.
"""
self.log_request(code)
self.send_response_only(code, message)
self.send_header('Server', self.version_string())
self.send_header('Date', self.date_time_string())
def send_response_only(self, code, message=None):
"""Send the response header only."""
if message is None:
if code in self.responses:
message = self.responses[code][0]
else:
message = ''
if self.request_version != 'HTTP/0.9':
if not hasattr(self, '_headers_buffer'):
self._headers_buffer = []
self._headers_buffer.append(("%s %d %s
" %
(self.protocol_version, code, message)).encode(
'latin-1', 'strict'))
def send_header(self, keyword, value):
"""Send a MIME header to the headers buffer."""
if self.request_version != 'HTTP/0.9':
if not hasattr(self, '_headers_buffer'):
self._headers_buffer = []
self._headers_buffer.append(
("%s: %s
" % (keyword, value)).encode('latin-1', 'strict'))
if keyword.lower() == 'connection':
if value.lower() == 'close':
self.close_connection = True
elif value.lower() == 'keep-alive':
self.close_connection = False
def end_headers(self):
"""Send the blank line ending the MIME headers."""
if self.request_version != 'HTTP/0.9':
self._headers_buffer.append(b"
")
self.flush_headers()
def flush_headers(self):
if hasattr(self, '_headers_buffer'):
self.wfile.write(b"".join(self._headers_buffer))
self._headers_buffer = []
def log_request(self, code='-', size='-'):
"""Log an accepted request.
This is called by send_response().
"""
if isinstance(code, HTTPStatus):
code = code.value
self.log_message('"%s" %s %s',
self.requestline, str(code), str(size))
def log_error(self, format, *args):
"""Log an error.
This is called when a request cannot be fulfilled. By
default it passes the message on to log_message().
Arguments are the same as for log_message().
XXX This should go to the separate error log.
"""
self.log_message(format, *args)
def log_message(self, format, *args):
"""Log an arbitrary message.
This is used by all other logging functions. Override
it if you have specific logging wishes.
The first argument, FORMAT, is a format string for the
message to be logged. If the format string contains
any % escapes requiring parameters, they should be
specified as subsequent arguments (it's just like
printf!).
The client ip and current date/time are prefixed to
every message.
"""
sys.stderr.write("%s - - [%s] %s
" %
(self.address_string(),
self.log_date_time_string(),
format%args))
def version_string(self):
"""Return the server software version string."""
return self.server_version + ' ' + self.sys_version
def date_time_string(self, timestamp=None):
"""Return the current date and time formatted for a message header."""
if timestamp is None:
timestamp = time.time()
year, month, day, hh, mm, ss, wd, y, z = time.gmtime(timestamp)
s = "%s, %02d %3s %4d %02d:%02d:%02d GMT" % (
self.weekdayname[wd],
day, self.monthname[month], year,
hh, mm, ss)
return s
def log_date_time_string(self):
"""Return the current time formatted for logging."""
now = time.time()
year, month, day, hh, mm, ss, x, y, z = time.localtime(now)
s = "%02d/%3s/%04d %02d:%02d:%02d" % (
day, self.monthname[month], year, hh, mm, ss)
return s
weekdayname = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']
monthname = [None,
'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
def address_string(self):
"""Return the client address."""
return self.client_address[0]
# Essentially static class variables
# The version of the HTTP protocol we support.
# Set this to HTTP/1.1 to enable automatic keepalive
protocol_version = "HTTP/1.0"
# MessageClass used to parse headers
MessageClass = http.client.HTTPMessage
# hack to maintain backwards compatibility
responses = {
v: (v.phrase, v.description)
for v in HTTPStatus.__members__.values()
}
这里比较重要的几个方法在handle()相关:
def handle(self):
"""Handle multiple requests if necessary."""
self.close_connection = True
self.handle_one_request()
while not self.close_connection:
self.handle_one_request()
可见这里handle的具体实现在handle_one_request()上. 而self.close_connection只在keep-alive的情况下才会变成False, 以前是每次请求重新建立链接, 发送一次就关闭. 这里主要就是防止多次链接浪费资源, 一次链接多次传递数据.
def handle_one_request(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.
"""
try:
self.raw_requestline = self.rfile.readline(65537)
if len(self.raw_requestline) > 65536:
self.requestline = ''
self.request_version = ''
self.command = ''
self.send_error(HTTPStatus.REQUEST_URI_TOO_LONG)
return
if not self.raw_requestline:
self.close_connection = True
return
if not self.parse_request():
# An error code has been sent, just exit
return
mname = 'do_' + self.command
if not hasattr(self, mname):
self.send_error(
HTTPStatus.NOT_IMPLEMENTED,
"Unsupported method (%r)" % self.command)
return
method = getattr(self, mname)
method()
self.wfile.flush() #actually send the response if not already done.
except socket.timeout as e:
#a read or a write timed out. Discard this connection
self.log_error("Request timed out: %r", e)
self.close_connection = True
return
原始的HTTP信息存储在self.raw_requestline中, 就是HTTP请求的头一行, 后面是Headers,再然后才是真正请求的内容, 这中间都是用一个空行分割的.
这里面主要用parse_request()来解析http协议, 真正的处理GET和POST是调用do_GET(),do_POST()等方法, 这里的GET和POST是HTTP Command, 区分大小写. 然后直接从self里调用mname()方法,其实就是do_Commond()
在self.parse_request()中:
def parse_request(self):
"""Parse a request (internal).
The request should be stored in self.raw_requestline; the results
are in self.command, self.path, self.request_version and
self.headers.
Return True for success, False for failure; on failure, an
error is sent back.
"""
self.command = None # set in case of error on the first line
self.request_version = version = self.default_request_version
self.close_connection = True
requestline = str(self.raw_requestline, 'iso-8859-1')
requestline = requestline.rstrip('
')
self.requestline = requestline
words = requestline.split()
if len(words) == 3:
command, path, version = words
if version[:5] != 'HTTP/':
self.send_error(
HTTPStatus.BAD_REQUEST,
"Bad request version (%r)" % version)
return False
try:
base_version_number = version.split('/', 1)[1]
version_number = base_version_number.split(".")
# RFC 2145 section 3.1 says there can be only one "." and
# - major and minor numbers MUST be treated as
# separate integers;
# - HTTP/2.4 is a lower version than HTTP/2.13, which in
# turn is lower than HTTP/12.3;
# - Leading zeros MUST be ignored by recipients.
if len(version_number) != 2:
raise ValueError
version_number = int(version_number[0]), int(version_number[1])
except (ValueError, IndexError):
self.send_error(
HTTPStatus.BAD_REQUEST,
"Bad request version (%r)" % version)
return False
if version_number >= (1, 1) and self.protocol_version >= "HTTP/1.1":
self.close_connection = False
if version_number >= (2, 0):
self.send_error(
HTTPStatus.HTTP_VERSION_NOT_SUPPORTED,
"Invalid HTTP Version (%s)" % base_version_number)
return False
elif len(words) == 2:
command, path = words
self.close_connection = True
if command != 'GET':
self.send_error(
HTTPStatus.BAD_REQUEST,
"Bad HTTP/0.9 request type (%r)" % command)
return False
elif not words:
return False
else:
self.send_error(
HTTPStatus.BAD_REQUEST,
"Bad request syntax (%r)" % requestline)
return False
self.command, self.path, self.request_version = command, path, version
# Examine the headers and look for a Connection directive.
try:
self.headers = http.client.parse_headers(self.rfile,
_class=self.MessageClass)
except http.client.LineTooLong:
self.send_error(
HTTPStatus.BAD_REQUEST,
"Line too long")
return False
except http.client.HTTPException as err:
self.send_error(
HTTPStatus.REQUEST_HEADER_FIELDS_TOO_LARGE,
"Too many headers",
str(err)
)
return False
conntype = self.headers.get('Connection', "")
if conntype.lower() == 'close':
self.close_connection = True
elif (conntype.lower() == 'keep-alive' and
self.protocol_version >= "HTTP/1.1"):
self.close_connection = False
# Examine the headers and look for an Expect directive
expect = self.headers.get('Expect', "")
if (expect.lower() == "100-continue" and
self.protocol_version >= "HTTP/1.1" and
self.request_version >= "HTTP/1.1"):
if not self.handle_expect_100():
return False
return True
这里先解析了HTTP的头一行, 最大65537字节. 然后解析headers.在http.client中解析
self.headers = http.client.parse_headers(self.rfile,_class=self.MessageClass)
这里的SimpleHTTPRequestHandler实现了do_GET()和do_HEAD()方法, CGIHTTPRequestHandler实现了do_POST()方法.