sogou proxy

gistfile1.py

# modified based on https://gist.github.com/2770237

from struct import unpack
from BaseHTTPServer import BaseHTTPRequestHandler, HTTPServer
from httplib import HTTPResponse
from SocketServer import ThreadingMixIn
import socket
import time

x_sogou_auth = "9CD285F1E7ADB0BD403C22AD1D545F40/30/853edc6d49ba4e27"


def calc_sogou_hash(t, host):
    s = (t + host + 'SogouExplorerProxy').encode('ascii')
    code = len(s)
    dwords = len(s) / 4
    rest = len(s) % 4

    v = unpack(str(dwords) + 'i' + str(rest) + 's', s)

    for vv in v:
        if type(vv) == type('i'):
            break

        rm = vv & 0xFFFF  # right most
        lm = vv >> 16     # left most

        code += rm
        code ^= code << 16
        code &= 0xffffffff

        code ^= lm << 11
        code += code >> 11
        code &= 0xffffffff

    if rest == 3:
        code += (ord(s[-2]) << 8) + ord(s[-3])
        code ^= code << 16
        code ^= ord(s[-1]) << 18

        code &= 0xffffffff
        code += code >> 11

    elif rest == 2:
        code += (ord(s[-1]) << 8) + ord(s[-2])
        code ^= code << 11

        code &= 0xffffffff
        code += code >> 17

    elif rest == 1:
        code += ord(s[-1])
        code ^= code << 10

        code &= 0xffffffff
        code += code >> 1

    code ^= code << 3
    code &= 0xffffffff
    code += code >> 5

    code ^= code << 4
    code &= 0xffffffff
    code += code >> 17

    code ^= code << 25
    code &= 0xffffffff
    code += code >> 6

    code &= 0xffffffff
    return hex(code)[2:].rstrip('L').zfill(8)


class Handler(BaseHTTPRequestHandler):
    s = 0

    def do_proxy(self):
        try:
            if self.s == 0:
                self.s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
                self.s.connect((proxy_host, 80))

            self.s.send(self.requestline.encode('ascii') + b"\r\n")

            # Add Sogou Verification Tags
            self.headers["X-Sogou-Auth"] = x_sogou_auth

            t = hex(int(time.time()))[2:].rstrip('L').zfill(8)
            self.headers["X-Sogou-Tag"] = \
                    calc_sogou_hash(t, self.headers['Host'])

            self.headers["X-Sogou-Timestamp"] = t
            self.s.send(str(self.headers).encode('ascii') + b"\r\n")

            # Send Post data
            if(self.command == 'POST'):
                self.s.send( \
                        self.rfile.read(int(self.headers['Content-Length'])))
            response = HTTPResponse(\
                    self.s, method=self.command, buffering=True)
            response.begin()

            # Reply to the browser
            status = "HTTP/1.1 " + str(response.status) + " " + response.reason
            self.wfile.write(status.encode('ascii') + b'\r\n')
            h = ''
            for hh, vv in response.getheaders():
                if hh.upper() != 'TRANSFER-ENCODING':
                    h += hh + ': ' + vv + '\r\n'
            self.wfile.write(h.encode('ascii') + b'\r\n')
            while True:
                response_data = response.read(8192)
                if(len(response_data) == 0):
                    break
                self.wfile.write(response_data)
        except socket.error:
            print('socket error for ' + self.requestline)

    def do_POST(self):
        self.do_proxy()

    def do_GET(self):
        self.do_proxy()


class ThreadingHTTPServer(ThreadingMixIn, HTTPServer):
    pass

server = ThreadingHTTPServer(("127.0.0.1", 1998), Handler)

#print(calc_sogou_hash('4d8cdaed', 'www.youku.com'))

#import random

#proxy_host = 'h' + str(random.randint(0, 15)) + '.edu.bj.ie.sogou.com'
#proxy_host = 'h' + str(random.randint(0,3)) + '.ctc.bj.ie.sogou.com'
#proxy_host = 'h' + str(random.randint(0,3)) + '.cnc.bj.ie.sogou.com'
#proxy_host = 'h' + str(random.randint(0,10)) + '.dxt.bj.ie.sogou.com'
proxy_host = 'h15' + '.dxt.bj.ie.sogou.com'

print('Proxy over ' + proxy_host)
server.serve_forever()