这是一个专题 记录学习python标准库的笔记及心得
简单http服务 SimpleHTTPServer
使用 python -m SimpleHTTPServer 默认启动8000端口
源码:
"""Simple HTTP Server.
This module builds on BaseHTTPServer by implementing the standard GET
and HEAD requests in a fairly straightforward manner.
"""
__version__ = "0.6"
__all__ = ["SimpleHTTPRequestHandler"]
import os
import posixpath
import BaseHTTPServer
import urllib
import urlparse
import cgi
import sys
import shutil
import mimetypes
try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO
class SimpleHTTPRequestHandler(BaseHTTPServer.BaseHTTPRequestHandler):
"""Simple HTTP request handler with GET and HEAD commands.
This serves files from the current directory and any of its
subdirectories. The MIME type for files is determined by
calling the .guess_type() method.
The GET and HEAD requests are identical except that the HEAD
request omits the actual contents of the file.
"""
server_version = "SimpleHTTP/" + __version__
def do_GET(self):
"""Serve a GET request."""
f = self.send_head()
if f:
try:
self.copyfile(f, self.wfile)
finally:
f.close()
def do_HEAD(self):
"""Serve a HEAD request."""
f = self.send_head()
if f:
f.close()
def send_head(self):
"""Common code for GET and HEAD commands.
This sends the response code and MIME headers.
Return value is either a file object (which has to be copied
to the outputfile by the caller unless the command was HEAD,
and must be closed by the caller under all circumstances), or
None, in which case the caller has nothing further to do.
"""
path = self.translate_path(self.path)
f = None
if os.path.isdir(path):
parts = urlparse.urlsplit(self.path)
if not parts.path.endswith('/'):
# redirect browser - doing basically what apache does
self.send_response(301)
new_parts = (parts[0], parts[1], parts[2] + '/',
parts[3], parts[4])
new_url = urlparse.urlunsplit(new_parts)
self.send_header("Location", new_url)
self.end_headers()
return None
for index in "index.html", "index.htm":
index = os.path.join(path, index)
if os.path.exists(index):
path = index
break
else:
return self.list_directory(path)
ctype = self.guess_type(path)
try:
# Always read in binary mode. Opening files in text mode may cause
# newline translations, making the actual size of the content
# transmitted *less* than the content-length!
f = open(path, 'rb')
except IOError:
self.send_error(404, "File not found")
return None
try:
self.send_response(200)
self.send_header("Content-type", ctype)
fs = os.fstat(f.fileno())
self.send_header("Content-Length", str(fs[6]))
self.send_header("Last-Modified", self.date_time_string(fs.st_mtime))
self.end_headers()
return f
except:
f.close()
raise
def list_directory(self, path):
"""Helper to produce a directory listing (absent index.html).
Return value is either a file object, or None (indicating an
error). In either case, the headers are sent, making the
interface the same as for send_head().
"""
try:
list = os.listdir(path)
except os.error:
self.send_error(404, "No permission to list directory")
return None
list.sort(key=lambda a: a.lower())
f = StringIO()
displaypath = cgi.escape(urllib.unquote(self.path))
f.write('<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">')
f.write("<html>
<title>Directory listing for %s</title>
" % displaypath)
f.write("<body>
<h2>Directory listing for %s</h2>
" % displaypath)
f.write("<hr>
<ul>
")
for name in list:
fullname = os.path.join(path, name)
displayname = linkname = name
# Append / for directories or @ for symbolic links
if os.path.isdir(fullname):
displayname = name + "/"
linkname = name + "/"
if os.path.islink(fullname):
displayname = name + "@"
# Note: a link to a directory displays with @ and links with /
f.write('<li><a href="%s">%s</a>
'
% (urllib.quote(linkname), cgi.escape(displayname)))
f.write("</ul>
<hr>
</body>
</html>
")
length = f.tell()
f.seek(0)
self.send_response(200)
encoding = sys.getfilesystemencoding()
self.send_header("Content-type", "text/html; charset=%s" % encoding)
self.send_header("Content-Length", str(length))
self.end_headers()
return f
def translate_path(self, path):
"""Translate a /-separated PATH to the local filename syntax.
Components that mean special things to the local file system
(e.g. drive or directory names) are ignored. (XXX They should
probably be diagnosed.)
"""
# abandon query parameters
path = path.split('?',1)[0]
path = path.split('#',1)[0]
# Don't forget explicit trailing slash when normalizing. Issue17324
trailing_slash = path.rstrip().endswith('/')
path = posixpath.normpath(urllib.unquote(path))
words = path.split('/')
words = filter(None, words)
path = os.getcwd()
for word in words:
if os.path.dirname(word) or word in (os.curdir, os.pardir):
# Ignore components that are not a simple file/directory name
continue
path = os.path.join(path, word)
if trailing_slash:
path += '/'
return path
def copyfile(self, source, outputfile):
"""Copy all data between two file objects.
The SOURCE argument is a file object open for reading
(or anything with a read() method) and the DESTINATION
argument is a file object open for writing (or
anything with a write() method).
The only reason for overriding this would be to change
the block size or perhaps to replace newlines by CRLF
-- note however that this the default server uses this
to copy binary data as well.
"""
shutil.copyfileobj(source, outputfile)
def guess_type(self, path):
"""Guess the type of a file.
Argument is a PATH (a filename).
Return value is a string of the form type/subtype,
usable for a MIME Content-type header.
The default implementation looks the file's extension
up in the table self.extensions_map, using application/octet-stream
as a default; however it would be permissible (if
slow) to look inside the data to make a better guess.
"""
base, ext = posixpath.splitext(path)
if ext in self.extensions_map:
return self.extensions_map[ext]
ext = ext.lower()
if ext in self.extensions_map:
return self.extensions_map[ext]
else:
return self.extensions_map['']
if not mimetypes.inited:
mimetypes.init() # try to read system mime.types
extensions_map = mimetypes.types_map.copy()
extensions_map.update({
'': 'application/octet-stream', # Default
'.py': 'text/plain',
'.c': 'text/plain',
'.h': 'text/plain',
})
def test(HandlerClass = SimpleHTTPRequestHandler,
ServerClass = BaseHTTPServer.HTTPServer):
BaseHTTPServer.test(HandlerClass, ServerClass)
if __name__ == '__main__':
test()
接收GET，HEAD请求
先判断是否是目录，目录不加/会重定向，默认显示目录下的index.html/index.htm文件，如果没有上述文件将目录下文件列表显示
copyfile函数调用shutil基本库，以后再介绍
利用MIME进行文件类型判断