#!/bin/sh -
"exec" "python" "-O" "$0" "$@"

__doc__ = """Tiny HTTP Proxy.

This module implements GET, HEAD, POST, PUT and DELETE methods
on BaseHTTPServer, and behaves as an HTTP proxy.  The CONNECT
method is also implemented experimentally, but has not been
tested yet.

Any help will be greatly appreciated.       SUZUKI Hisao
"""

__version__ = "0.2.1"

import BaseHTTPServer, select, socket, SocketServer, urlparse
import re, time

class ProxyHandler (BaseHTTPServer.BaseHTTPRequestHandler):
    __base = BaseHTTPServer.BaseHTTPRequestHandler
    __base_handle = __base.handle

    server_version = "TinyHTTPProxy/" + __version__
    rbufsize = 0                        # self.rfile Be unbuffered

    def handle(self):
        (ip, port) =  self.client_address
        if hasattr(self, 'allowed_clients') and ip not in self.allowed_clients:
            self.raw_requestline = self.rfile.readline()
            if self.parse_request(): self.send_error(403)
        else:
            self.__base_handle()

    def _connect_to(self, netloc, soc):
        #print "_connect_to: %s" % (netloc)

        i = netloc.find(':')
        if i >= 0:
            host_port = netloc[:i], int(netloc[i+1:])
        else:
            host_port = netloc, 80
        #print "\t" "connect to %s:%d" % host_port
        try: soc.connect(host_port)
        except socket.error, arg:
            try: msg = arg[1]
            except: msg = arg
            self.send_error(404, msg)
            return 0
        return 1

    def do_CONNECT(self):
        #print('CONNECT')
        soc = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        try:
            if self._connect_to(self.path, soc):
                self.log_request(200)
                self.wfile.write(self.protocol_version +
                                 " 200 Connection established\r\n")
                self.wfile.write("Proxy-agent: %s\r\n" % self.version_string())
                self.wfile.write("\r\n")
                self._read_write(soc, 300)
        finally:
            #print "\t" "bye"
            soc.close()
            self.connection.close()

    def do_GET(self):
        #print('GET')
        (scm, netloc, path, params, query, fragment) = urlparse.urlparse(
            self.path, 'http')
        if scm != 'http' or fragment or not netloc:
            self.send_error(400, "bad url %s" % self.path)
            return
        soc = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

        pp = path.lower()
        dbg = False
        #dbg = pp.endswith("/") or pp.endswith(".html") or pp.endswith(".htm") or pp.endswith(".xml") or pp.endswith(".php")
        if re.compile("(/|html|htm|bml|xml|php|txt)$", re.IGNORECASE).search(pp):
            dbg = True
            #print "pp:", pp

        dbg_hosts = "(habrahabr|zencd|www.livejournal|7bloggers.ru|lib.ru)"
        if not re.compile(dbg_hosts, re.IGNORECASE).search(netloc):
            dbg = False

        # Myth Busters patch
        #if re.compile("Myth_busters", re.IGNORECASE).search(pp):
        #    dbg = True
        #else:
        #    dbg = False

        if dbg: print "debugging", self.path

        try:
            if self._connect_to(netloc, soc):
                if dbg: self.log_request()
                soc.send("%s %s %s\r\n" % (
                    self.command,
                    urlparse.urlunparse(('', '', path, params, query, '')),
                    self.request_version))

                #for key_val in self.headers.items():
                #    print " header: %s" % (str(key_val))

                self.headers['Connection'] = 'close'
                del self.headers['Proxy-Connection']
                for key_val in self.headers.items():
                    soc.send("%s: %s\r\n" % key_val)
                soc.send("\r\n")
                self._read_write(soc, 20, dbg, self.path)
        finally:
            #print "\t" "bye"
            soc.close()
            self.connection.close()

    def _read_write(self, soc, max_idling, dbg = False, path = ""):
        time1 = time.time()
        #print "_read_write(%d)\n" % (max_idling)
        iw = [self.connection, soc]
        ow = []
        count = 0
        while 1:
            count += 1
            (ins, _, exs) = select.select(iw, ow, iw, 3)
            if exs: break
            if ins:
                for i in ins:
                    if i is soc:
                        out = self.connection
                    else:
                        out = soc
                    try:
                        data = i.recv(8192)
                        if data:
                            #if dbg and data.lower().find("</html") >= 0:
                            #    print "\a</HTML> FOUND"
                            out.send(data)
                            count = 0
                    except:
                        print 'EXCEPTION FOR %s' % (path)
            #else:
            #    print "idle", count
            if count == max_idling: break

        if dbg:
            #print " finished", path
            time2 = time.time()
            s = "%5.2f" % (time2-time1)
            print "%9s %s\a" % (s, path)

    do_HEAD = do_GET
    do_POST = do_GET
    do_PUT  = do_GET
    do_DELETE=do_GET

class ThreadingHTTPServer (SocketServer.ThreadingMixIn,
                           BaseHTTPServer.HTTPServer): pass

if __name__ == '__main__':
    from sys import argv

    #print time.time()
    #exit(1)

    if argv[1:] and argv[1] in ('-h', '--help'):
        print argv[0], "[port [allowed_client_name ...]]"
    else:
        if argv[2:]:
            allowed = []
            for name in argv[2:]:
                client = socket.gethostbyname(name)
                allowed.append(client)
                print "Accept: %s (%s)" % (client, name)
            ProxyHandler.allowed_clients = allowed
            del argv[2:]
        else:
            print "Any clients will be served..."
        BaseHTTPServer.test(ProxyHandler, ThreadingHTTPServer)