python web 服务器学习笔记（四）
在开始新内容之前，我们先解决socket error 98:Address already in use问题
很容易发现可能是由于端口被占用导致的，端口被占用又有很多可能，比如说的关闭你挂上去的服务器，然后又秒开，你会发现这个错误。
此时似乎是由于tcp本身的特性，端口未来得及释放导致的
我们可以通过以下命令查看端口的使用情况，并试着处理它
kill -9 [进程id] 杀死该进程
lsof -i:[端口号]查看端口属于哪个程序
netstrat tln | grep [端口号]查看端口使用情况
嘛。。网上很多方法改socket让它可以重复使用或者restart很快，总觉得对于一个服务器的源码来说加这些不合适（其实我也不会）
然后是Linux关闭防火墙命令
1） 永久性生效，重启后不会复原 开启：chkconfig iptables on 关闭：chkconfig iptables off
2） 即时生效，重启后复原 开启：service iptables start 关闭：service iptables stop
下面要讨论的问题是公共网关接口（CGI)机制，它为web服务器提供一个标准的方式运行外部程序
比如我要运行一个展示时间的python小程序
from datetime import datetime
print '''\
<html>
<body>
<p>Generated {0}</p>
</body>
</html>'''.format(datetime.now())
下面又是处理方法啦
import sys, os, BaseHTTPServer
#-------------------------------------------------------------------------------
class ServerException(Exception):
'''For internal error reporting.'''
pass
#-------------------------------------------------------------------------------
class case_no_file(object):
'''File or directory does not exist.'''
def test(self, handler):
return not os.path.exists(handler.full_path)
def act(self, handler):
raise ServerException("'{0}' not found".format(handler.path))
#-------------------------------------------------------------------------------
class case_cgi_file(object):
'''Something runnable.'''
def test(self, handler):
return os.path.isfile(handler.full_path) and \
handler.full_path.endswith('.py')
def act(self, handler):
handler.run_cgi(handler.full_path)
#-------------------------------------------------------------------------------
class case_existing_file(object):
'''File exists.'''
def test(self, handler):
return os.path.isfile(handler.full_path)
def act(self, handler):
handler.handle_file(handler.full_path)
#-------------------------------------------------------------------------------
class case_directory_index_file(object):
'''Serve index.html page for a directory.'''
def index_path(self, handler):
return os.path.join(handler.full_path, 'index.html')
def test(self, handler):
return os.path.isdir(handler.full_path) and \
os.path.isfile(self.index_path(handler))
def act(self, handler):
handler.handle_file(self.index_path(handler))
#-------------------------------------------------------------------------------
class case_directory_no_index_file(object):
'''Serve listing for a directory without an index.html page.'''
def index_path(self, handler):
return os.path.join(handler.full_path, 'index.html')
def test(self, handler):
return os.path.isdir(handler.full_path) and \
not os.path.isfile(self.index_path(handler))
def act(self, handler):
handler.list_dir(handler.full_path)
#-------------------------------------------------------------------------------
class case_always_fail(object):
'''Base case if nothing else worked.'''
def test(self, handler):
return True
def act(self, handler):
raise ServerException("Unknown object '{0}'".format(handler.path))
#-------------------------------------------------------------------------------
class RequestHandler(BaseHTTPServer.BaseHTTPRequestHandler):
'''
If the requested path maps to a file, that file is served.
If anything goes wrong, an error page is constructed.
'''
Cases = [case_no_file(),
case_cgi_file(),
case_existing_file(),
case_directory_index_file(),
case_directory_no_index_file(),
case_always_fail()]
# How to display an error.
Error_Page = """\
<html>
<body>
<h1>Error accessing {path}</h1>
<p>{msg}</p>
</body>
</html>
"""
# How to display a directory listing.
Listing_Page = '''\
<html>
<body>
<ul>
{0}
</ul>
</body>
</html>
'''
# Classify and handle request.
def do_GET(self):
try:
# Figure out what exactly is being requested.
self.full_path = os.getcwd() + self.path
# Figure out how to handle it.
for case in self.Cases:
if case.test(self):
case.act(self)
break
# Handle errors.
except Exception as msg:
self.handle_error(msg)
def handle_file(self, full_path):
try:
with open(full_path, 'rb') as reader:
content = reader.read()
self.send_content(content)
except IOError as msg:
msg = "'{0}' cannot be read: {1}".format(self.path, msg)
self.handle_error(msg)
def list_dir(self, full_path):
try:
entries = os.listdir(full_path)
bullets = ['<li>{0}</li>'.format(e) for e in entries if not e.startswith('.')]
page = self.Listing_Page.format('\n'.join(bullets))
self.send_content(page)
except OSError as msg:
msg = "'{0}' cannot be listed: {1}".format(self.path, msg)
self.handle_error(msg)
def run_cgi(self, full_path):
cmd = "python " + full_path
child_stdin, child_stdout = os.popen2(cmd)
child_stdin.close()
data = child_stdout.read()
child_stdout.close()
self.send_content(data)
# Handle unknown objects.
def handle_error(self, msg):
content = self.Error_Page.format(path=self.path, msg=msg)
self.send_content(content, 404)
# Send actual content.
def send_content(self, content, status=200):
self.send_response(status)
self.send_header("Content-type", "text/html")
self.send_header("Content-Length", str(len(content)))
self.end_headers()
self.wfile.write(content)
#-------------------------------------------------------------------------------
if __name__ == '__main__':
serverAddress = ('', 8080)
server = BaseHTTPServer.HTTPServer(serverAddress, RequestHandler)
server.serve_forever()
从run_cgi上可以看出这个办法是把该.py放在服务器上运行的。显然会带来一些问题。比如服务器上放了一个会产生死循环的程序，当客户端方知道了有这个程序，客户端可以通过这cgi强行运行它，相当于我们的服务器受到攻击了呢
我们的处理方法是：
1.在子进程中运行该程序
2.捕获子进程发送到标准输出的一切
3.返回给发起请求的客户端
完整的cgi协议比这更丰富，它允许URL中存在参数，服务器会将他们传入正在运行的程序（似乎这就是搜索引擎的架构哇，在url中添加参数然后丢到引擎里去然后返回一个html),
但这并不影响系统的整体架构。
于是我们的源码如下：
import sys, os, BaseHTTPServer
#-------------------------------------------------------------------------------
class ServerException(Exception):
'''For internal error reporting.'''
pass
#-------------------------------------------------------------------------------
class base_case(object):
'''Parent for case handlers.'''
def handle_file(self, handler, full_path):
try:
with open(full_path, 'rb') as reader:
content = reader.read()
handler.send_content(content)
except IOError as msg:
msg = "'{0}' cannot be read: {1}".format(full_path, msg)
handler.handle_error(msg)
def index_path(self, handler):
return os.path.join(handler.full_path, 'index.html')
def test(self, handler):
assert False, 'Not implemented.'
def act(self, handler):
assert False, 'Not implemented.'
#-------------------------------------------------------------------------------
class case_no_file(base_case):
'''File or directory does not exist.'''
def test(self, handler):
return not os.path.exists(handler.full_path)
def act(self, handler):
raise ServerException("'{0}' not found".format(handler.path))
#-------------------------------------------------------------------------------
class case_cgi_file(base_case):
'''Something runnable.'''
def run_cgi(self, handler):
cmd = "python " + handler.full_path
child_stdin, child_stdout = os.popen2(cmd)
child_stdin.close()
data = child_stdout.read()
child_stdout.close()
handler.send_content(data)
def test(self, handler):
return os.path.isfile(handler.full_path) and \
handler.full_path.endswith('.py')
def act(self, handler):
self.run_cgi(handler)
#-------------------------------------------------------------------------------
class case_existing_file(base_case):
'''File exists.'''
def test(self, handler):
return os.path.isfile(handler.full_path)
def act(self, handler):
self.handle_file(handler, handler.full_path)
#-------------------------------------------------------------------------------
class case_directory_index_file(base_case):
'''Serve index.html page for a directory.'''
def test(self, handler):
return os.path.isdir(handler.full_path) and \
os.path.isfile(self.index_path(handler))
def act(self, handler):
self.handle_file(handler, self.index_path(handler))
#-------------------------------------------------------------------------------
class case_directory_no_index_file(base_case):
'''Serve listing for a directory without an index.html page.'''
# How to display a directory listing.
Listing_Page = '''\
<html>
<body>
<ul>
{0}
</ul>
</body>
</html>
'''
def list_dir(self, handler, full_path):
try:
entries = os.listdir(full_path)
bullets = ['<li>{0}</li>'.format(e) for e in entries if not e.startswith('.')]
page = self.Listing_Page.format('\n'.join(bullets))
handler.send_content(page)
except OSError as msg:
msg = "'{0}' cannot be listed: {1}".format(self.path, msg)
handler.handle_error(msg)
def test(self, handler):
return os.path.isdir(handler.full_path) and \
not os.path.isfile(self.index_path(handler))
def act(self, handler):
self.list_dir(handler, handler.full_path)
#-------------------------------------------------------------------------------
class case_always_fail(base_case):
'''Base case if nothing else worked.'''
def test(self, handler):
return True
def act(self, handler):
raise ServerException("Unknown object '{0}'".format(handler.path))
#-------------------------------------------------------------------------------
class RequestHandler(BaseHTTPServer.BaseHTTPRequestHandler):
'''
If the requested path maps to a file, that file is served.
If anything goes wrong, an error page is constructed.
'''
Cases = [case_no_file(),
case_cgi_file(),
case_existing_file(),
case_directory_index_file(),
case_directory_no_index_file(),
case_always_fail()]
# How to display an error.
Error_Page = """\
<html>
<body>
<h1>Error accessing {path}</h1>
<p>{msg}</p>
</body>
</html>
"""
# Classify and handle request.
def do_GET(self):
try:
# Figure out what exactly is being requested.
self.full_path = os.getcwd() + self.path
# Figure out how to handle it.
for case in self.Cases:
if case.test(self):
case.act(self)
break
# Handle errors.
except Exception as msg:
self.handle_error(msg)
# Handle unknown objects.
def handle_error(self, msg):
content = self.Error_Page.format(path=self.path, msg=msg)
self.send_content(content, 404)
# Send actual content.
def send_content(self, content, status=200):
self.send_response(status)
self.send_header("Content-type", "text/html")
self.send_header("Content-Length", str(len(content)))
self.end_headers()
self.wfile.write(content)
#-------------------------------------------------------------------------------
if __name__ == '__main__':
serverAddress = ('', 8080)
server = BaseHTTPServer.HTTPServer(serverAddress, RequestHandler)
server.serve_forever()
为我们所有的事件创建一个父类，当且仅当方法在多个处理器间共享时将他们移入父类中，然后分别重载我们的方法就可以啦
然后这个是cgi处理部分
class case_cgi_file(base_case):
'''Something runnable.'''
def run_cgi(self, handler):
cmd = "python " + handler.full_path
child_stdin, child_stdout = os.popen2(cmd)
child_stdin.close()
data = child_stdout.read()
child_stdout.close()
handler.send_content(data)
def test(self, handler):
return os.path.isfile(handler.full_path) and \
handler.full_path.endswith('.py')
def act(self, handler):
self.run_cgi(handler)
os.popen2是实现一个管道，从这个命令中获取的值可以继续被调用。它本来不是阻塞的，但当我测试它的性能时意外发现它阻塞了
我让它运行一个输出1到10000000的数字的脚本，于是这个时候服务器上的其他资源都不能被访问了
原因是subprocess的PIPE是有大小的，在python2.6的版本中，它的大小是65536。当PIPE被填满，就把它给塞死了
