I'm using libmproxy to capture http traffic. I would like to use web driver to load a web page while the proxy is running. The proxy code is working great but I am unable to launch the page. I assume the script is becoming stuck in a loop at m.run(). How can I move to the web driver code while the proxy is running?
import unittest
import sys
from libmproxy import proxy, dump, cmdline
from libmproxy.version import VERSION
from optparse import OptionParser
from selenium import webdriver
class Test(unittest.TestCase):
def setUp(self):
parser = OptionParser(
usage = "%prog [options] [filter]",
version="%%prog %s"%VERSION,
)
cmdline.common_options(parser)
parser.add_option(
"--keepserving",
action="store_true", dest="keepserving", default=False,
help="Continue serving after client playback or file read. We exit by default."
)
options, args = parser.parse_args()
if options.quiet:
options.verbose = 0
proxyconfig = proxy.process_proxy_options(parser, options)
if options.no_server:
server = proxy.DummyServer(proxyconfig)
else:
try:
server = proxy.ProxyServer(proxyconfig, options.port, options.addr)
except proxy.ProxyServerError, v:
print >> sys.stderr, "mitmdump:", v.args[0]
sys.exit(1)
try:
dumpopts = dump.Options(**cmdline.get_common_options(options))
except cmdline.OptionException, v:
parser.error(v.message)
dumpopts.keepserving = options.keepserving
if args:
filt = " ".join(args)
else:
filt = None
try:
PROXY_HOST = "localhost"
PROXY_PORT = 8080
#driver.get("http://msn.com")
#f = open('/Users/cnave/Documents/capture/dump.txt', 'w')
#sys.stdout('/Users/cnave/Documents/capture/dump.txt', 'w')
#open('/Users/cnave/Documents/capture/dump.txt', 'w')
m = dump.DumpMaster(server, dumpopts, filt)
m.run()
#sys.stdout('/Users/cnave/Documents/capture/dump')
fp = webdriver.FirefoxProfile()
# Direct = 0, Manual = 1, PAC = 2, AUTODETECT = 4, SYSTEM = 5
fp.set_preference("network.proxy.type", 1)
fp.set_preference("network.proxy.http", PROXY_HOST)
fp.set_preference("network.proxy.http_port", PROXY_PORT)
fp.set_preference("network.proxy.no_proxies_on", "") # set this value as desired
driver = webdriver.Firefox(firefox_profile=fp)
driver.get('http://google.com')
except dump.DumpError, e:
print >> sys.stderr, "mitmdump:", e
sys.exit(1)
except KeyboardInterrupt:
pass
self.dm = dump.DumpMaster(server, dumpopts, filt)
// run the MITM proxy in a background thread
thread.start_new_thread(self.dm.run,())
// and you maybe need to shutdown the proxy in tearDown()
self.dm.shutdown()
Related
I decided to create a checker for Instagram accounts.
Please tell me how you can change the ip when you restart the browser. I have a Tor profile. That is, the ip automatically changes every 10 minutes. How can I make the ip change 1 time per minute. Is this even possible?
Maybe there is some kind of set_preference setting or how in general you can change the ip when restarting the Firefox browser with the Tor settings.
import time
from selenium import webdriver
from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
file = open('Good2.txt', encoding='utf-8-sig').read().split('\n')
goods = open('good_acc.txt', 'a+')
def settings_browser():
""" Настройки браузера FireFox. """
profile = FirefoxProfile(r'C:\Users\ASUS\Desktop\Scrape\Tor Browser\Browser\TorBrowser\Data\Browser\profile.default')
profile.set_preference('network.proxy.type', 1)
profile.set_preference('network.proxy.socks', '127.0.0.1')
profile.set_preference('network.proxy.socks_port', 9050)
profile.set_preference("network.proxy.socks_remote_dns", False)
# get a huge speed increase by not downloading images
profile.set_preference("permissions.default.image", 2)
profile.update_preferences()
return profile
def check_email():
""" Принимает всплывающее окно куки. Чекает валидность почт, если почта валидна, то сохраняет в файл 'good_acc.txt'. """
driver = webdriver.Firefox(firefox_profile=settings_browser(), executable_path=r'C:\Users\ASUS\Desktop\Scrape\geckodriver.exe')
for login in file:
driver.get("https://www.instagram.com/accounts/password/reset/")
body = driver.find_elements_by_class_name('pbNvD.FrS-d.gD9tr')
for bd in body:
if bd.find_element_by_class_name('aOOlW.bIiDR').text == 'Принять все':
bd.find_element_by_class_name('aOOlW.bIiDR').click()
time.sleep(7)
authorization = driver.find_elements_by_class_name("AHCwU")
pops = driver.find_elements_by_class_name("_-rjm")
username = login.split(":")[0]
password = login.split(":")[1]
for data in authorization:
# почта логин
data_login = data.find_element_by_name('cppEmailOrUsername')
data_login.click()
data_login.send_keys(username)
time.sleep(1)
# кнопка входа
clock_button = data.find_element_by_class_name('sqdOP.L3NKy.y3zKF')
clock_button.click()
time.sleep(2)
for pop in pops:
if 'Мы отправили ссылку для восстановления' in pop.find_element_by_class_name('tA2fc').text:
# Почта зарегана
goods.write(username + ' : ' + password + '\n')
print('Валидный аккаунт ' + username + ' : ' + password)
elif 'Подождите несколько минут, прежде чем пытаться снова.' in pop.find_element_by_class_name('tA2fc').text:
driver.quit()
driver = webdriver.Firefox(firefox_profile=settings_browser(), executable_path=r'C:\Users\ASUS\Desktop\Scrape\geckodriver.exe')
print('Успешная перезагрузка драйвера из-за "Подождите несколько минут, прежде чем пытаться снова."')
elif 'feedback_required' in pop.find_element_by_class_name('tA2fc').text:
driver.quit()
driver = webdriver.Firefox(firefox_profile=settings_browser(), executable_path=r'C:\Users\ASUS\Desktop\Scrape\geckodriver.exe')
print('Успешная перезагрузка драйвера из-за "feedback_required"')
else:
# Почта не зарегана
print(f"Не валидный аккаунт " + username)
goods.close()
def main():
check_email()
if __name__ == '__main__':
main()
If you set ControlPort: 9051 (and Passord: ...) in config file (on Linux /etc/tor/torrc) then you can use even standard socket to send signal to tor to change IP.
import socket
s = socket.socket()
s.connect(('127.0.0.1', 9051))
s.send('AUTHENTICATE "your_passord"\r\nSIGNAL NEWNYM\r\n'.encode())
It needs few seconds to get new IP from tor network.
And after few seconds proxy should use new IP.
You may also use module stem for this (it also needs settings in torrc)
from stem import Signal
from stem.control import Controller
with Controller.from_port(port=9051) as controller:
controller.authenticate(password='your_password')
controller.signal(Signal.NEWNYM)
More: Python: How to use Tor Network with requests to change IP?
EDIT:
import socket
def main():
# send signal to `tor` to change IP
s = socket.socket()
s.connect(('127.0.0.1', 9051))
s.send('AUTHENTICATE "your_passord"\r\nSIGNAL NEWNYM\r\n'.encode())
# wait few seconds for new IP
time.sleep(3)
check_email()
I'm writing a script to access a website using proxies with multiple threads but now I'm stuck in multiple threads, when I run the script below, it opens 5 browsers but all 5 use 1 proxy, I want 5 browsers to use different proxies, can someone help me complete it? thank you
Here is my script :
from selenium import webdriver
from selenium import webdriver
import time , random
import threading
def e():
a = open("sock2.txt", "r")
for line in a.readlines():
b = line
prox = b.split(":")
IP = prox[0]
PORT = int(prox[1].strip("\n"))
print(IP)
print(PORT)
profile = webdriver.FirefoxProfile()
profile.set_preference("network.proxy.type", 1)
profile.set_preference("network.proxy.socks", IP)
profile.set_preference("network.proxy.socks_port", PORT)
try:
driver = webdriver.Firefox(firefox_profile=profile)
driver.get("http://www.whatsmyip.org/")
except:
print("Proxy Connection Error")
driver.quit()
else:
time.sleep(random.randint(40, 70))
driver.quit()
for i in range(5):
t = threading.Thread(target=e)
t.start()
(Wish everyone has a happy and lucky new year)
Dominik Lašo captured it correctly - each threads processes the file from the beginning. Here's probably how it should look like:
from selenium import webdriver
from selenium import webdriver
import time , random
import threading
def e(ip, port):
profile = webdriver.FirefoxProfile()
profile.set_preference("network.proxy.type", 1)
profile.set_preference("network.proxy.socks", IP)
profile.set_preference("network.proxy.socks_port", PORT)
try:
driver = webdriver.Firefox(firefox_profile=profile)
driver.get("http://www.whatsmyip.org/")
except:
print("Proxy Connection Error")
driver.quit()
else:
time.sleep(random.randint(40, 70))
driver.quit()
my_threads = []
with open("sock2.txt", "r") as fd:
for line in fd.readlines():
line = line.strip()
if not line:
continue
prox = line.split(":")
ip = prox[0]
port = int(prox[1])
print('-> {}:{}'.format(ip, port))
t = threading.Thread(target=e, args=(ip, port,))
t.start()
my_threads.append(t)
for t in my_threads:
t.join()
( I personaly think that a problem is there that when you start a program, it will go to new thread, which will go throught the textfile from beginning, becasue you aint deleting them )
I have cane across the same problem, when I was doing the same thing as you do now. I know you would rather want help with your code, but I am in hurry to test it and want to help you ;) , so here is a code that works for me ... There is even task killer for a chrome ( you just have to edit it to firefox )
If I were you, I would start the thread after opening the file, cuz it looks liek you are opening the same file from 1st line everytime the tread starts
links = [ // Link you want to go to ]
def funk(xxx , website):
link = website
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--proxy-server=%s' % str(xxx))
chromedriver = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'chromedriver')
chrome = webdriver.Chrome(chromedriver, chrome_options=chrome_options)
try :
// Do stuff
except:
print('exception')
chrome.close()
for link in links:
f = open('proxies.txt')
line = f.readline()
x = 1
xx = 0
while line:
if number_of_used_proxies < 10:
print(line)
line = f.readline()
try:
threading.Timer(40, funk, [line, link]).start()
except Exception as e:
print(e)
time.sleep(1)
x += 1
number_of_used_proxies += 1
else:
time.sleep(100)
for x in range(1, 10):
try:
xzxzx = 'os.system("taskkill /f /im chrome.exe")'
os.system("killall 'Google Chrome'")
except:
print("NoMore")
time.sleep(10)
number_of_used_proxies = 0
f.close()
Hope it helps :)
vantuong: Here's how you can solve the problem with ThreadPoolExecutor.
Reference: https://docs.python.org/3/library/concurrent.futures.html
from selenium import webdriver
import time, random
#import threading
import concurrent.futures
MAX_WORKERS = 5
def get_proxys(data_file):
proxys = []
with open(data_file, "r") as fd:
for line in fd.readlines():
line = line.strip()
if not line:
continue
prox = line.split(":")
ip = prox[0]
port = int(prox[1])
proxys.append((ip, port))
return proxys
def e(ip, port):
profile = webdriver.FirefoxProfile()
profile.set_preference("network.proxy.type", 1)
profile.set_preference("network.proxy.socks", IP)
profile.set_preference("network.proxy.socks_port", PORT)
try:
driver = webdriver.Firefox(firefox_profile=profile)
driver.get("http://www.whatsmyip.org/")
except:
print("Proxy Connection Error")
driver.quit()
else:
time.sleep(random.randint(40, 70))
driver.quit()
with concurrent.futures.ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
proxys = get_proxys('sock2.txt')
tasks = {executor.submit(e, proxy[0], proxy[1]): proxy for proxy in proxys}
for task in concurrent.futures.as_completed(tasks):
proxy = tasks[task]
try:
data = task.result()
except Exception as exc:
print('{} generated an exception: {}'.format(proxy, exc))
else:
print('{} completed successfully'.format(proxy))
Fun exercise: Try playing around with different values of MAX_WORKERS.
I am attempting to use chrome with a user pass proxy this is my code:
def getProxy(string_only=True):
try:
proxy_manager = ProxyManager("proxies.txt")
proxy = proxy_manager.random_proxy()
if string_only:
return proxy.proxy_string
return proxy.get_dict()
except (OSError, IOError, IndexError) as e: # couldn't load the file / file is empty
return None
chrome_options = webdriver.ChromeOptions()
proxy = getProxy()
userpass = proxy[0:proxy.find("#")]
hostport = proxy[proxy.find("#")+1:]
if proxy:
chrome_options.add_argument("--proxy-server=" + hostport)
driver1 = webdriver.Chrome(chrome_options=chrome_options)
wait = WebDriverWait(driver1, 1000000)
if manual == "No":
driver1.get("http://%s#www.google.com"%userpass)
Help is appreciated
I have server and console scripts which keeps on listening on port for console and server requests.
In UNIX environment I made both the server and console script as continuously running daemons which will keep them listening on port.
Is there any way way in windows to keep them running like daemon in UNIX ? I also want them to get up on reboot (should get auto started on reboot)
I read about windows services and followed code written here, but I am getting 404 error on my webpage
__version__ = "0.4"
__all__ = ["RequestHandler"]
import atexit
import BaseHTTPServer
import CGIHTTPServer
import copy
import os
import select
import SimpleHTTPServer
import sys
import time
import threading
import urllib
from signal import SIGTERM
from BaseHTTPServer import HTTPServer, BaseHTTPRequestHandler
from SocketServer import ThreadingMixIn
class ThreadedHTTPServer(ThreadingMixIn, HTTPServer):
pass
class RequestHandler(SimpleHTTPServer.SimpleHTTPRequestHandler):
have_fork = hasattr(os, 'fork')
have_popen2 = hasattr(os, 'popen2')
have_popen3 = hasattr(os, 'popen3')
rbufsize = 0
def do_POST(self):
if self.is_cgi():
self.run_cgi()
else:
self.send_error(501, "Can only POST to CGI scripts")
def send_head(self):
if self.is_cgi():
return self.run_cgi()
else:
return SimpleHTTPServer.SimpleHTTPRequestHandler.send_head(self)
def is_cgi(self):
splitpath = _url_collapse_path_split(self.path)
if splitpath[0] in self.cgi_directories:
self.cgi_info = splitpath
return True
return False
cgi_directories = ['/cgi-bin', '/htbin']
def is_executable(self, path):
return executable(path)
def is_python(self, path):
head, tail = os.path.splitext(path)
return tail.lower() in (".py", ".pyw")
def run_cgi(self):
path = self.path
dir, rest = self.cgi_info
i = path.find('/', len(dir) + 1)
while i >= 0:
nextdir = path[:i]
nextrest = path[i+1:]
scriptdir = self.translate_path(nextdir)
if os.path.isdir(scriptdir):
dir, rest = nextdir, nextrest
i = path.find('/', len(dir) + 1)
else:
break
i = rest.rfind('?')
if i >= 0:
rest, query = rest[:i], rest[i+1:]
else:
query = ''
i = rest.find('/')
if i >= 0:
script, rest = rest[:i], rest[i:]
else:
script, rest = rest, ''
scriptname = dir + '/' + script
scriptfile = self.translate_path(scriptname)
if not os.path.exists(scriptfile):
self.send_error(404, "No such CGI script (%r)" % scriptname)
return
if not os.path.isfile(scriptfile):
self.send_error(403, "CGI script is not a plain file (%r)" %
scriptname)
return
ispy = self.is_python(scriptname)
if not ispy:
if not (self.have_fork or self.have_popen2 or self.have_popen3):
self.send_error(403, "CGI script is not a Python script (%r)" %
scriptname)
return
if not self.is_executable(scriptfile):
self.send_error(403, "CGI script is not executable (%r)" %
scriptname)
return
# Reference: http://hoohoo.ncsa.uiuc.edu/cgi/env.html
# XXX Much of the following could be prepared ahead of time!
env = {}
env['SERVER_SOFTWARE'] = self.version_string()
env['SERVER_NAME'] = self.server.server_name
env['GATEWAY_INTERFACE'] = 'CGI/1.1'
env['SERVER_PROTOCOL'] = self.protocol_version
env['SERVER_PORT'] = str(self.server.server_port)
env['REQUEST_METHOD'] = self.command
uqrest = urllib.unquote(rest)
env['PATH_INFO'] = uqrest
env['PATH_TRANSLATED'] = self.translate_path(uqrest)
env['SCRIPT_NAME'] = scriptname
if query:
env['QUERY_STRING'] = query
host = self.address_string()
if host != self.client_address[0]:
env['REMOTE_HOST'] = host
env['REMOTE_ADDR'] = self.client_address[0]
authorization = self.headers.getheader("authorization")
if authorization:
authorization = authorization.split()
if len(authorization) == 2:
import base64, binascii
env['AUTH_TYPE'] = authorization[0]
if authorization[0].lower() == "basic":
try:
authorization = base64.decodestring(authorization[1])
except binascii.Error:
pass
else:
authorization = authorization.split(':')
if len(authorization) == 2:
env['REMOTE_USER'] = authorization[0]
# XXX REMOTE_IDENT
if self.headers.typeheader is None:
env['CONTENT_TYPE'] = self.headers.type
else:
env['CONTENT_TYPE'] = self.headers.typeheader
length = self.headers.getheader('content-length')
if length:
env['CONTENT_LENGTH'] = length
referer = self.headers.getheader('referer')
if referer:
env['HTTP_REFERER'] = referer
accept = []
for line in self.headers.getallmatchingheaders('accept'):
if line[:1] in "\t\n\r ":
accept.append(line.strip())
else:
accept = accept + line[7:].split(',')
env['HTTP_ACCEPT'] = ','.join(accept)
ua = self.headers.getheader('user-agent')
if ua:
env['HTTP_USER_AGENT'] = ua
co = filter(None, self.headers.getheaders('cookie'))
if co:
env['HTTP_COOKIE'] = ', '.join(co)
# XXX Other HTTP_* headers
# Since we're setting the env in the parent, provide empty
# values to override previously set values
for k in ('QUERY_STRING', 'REMOTE_HOST', 'CONTENT_LENGTH',
'HTTP_USER_AGENT', 'HTTP_COOKIE', 'HTTP_REFERER'):
env.setdefault(k, "")
os.environ.update(env)
self.send_response(200, "Script output follows")
decoded_query = query.replace('+', ' ')
if self.have_fork:
# Unix -- fork as we should
args = [script]
if '=' not in decoded_query:
args.append(decoded_query)
nobody = nobody_uid()
self.wfile.flush() # Always flush before forking
pid = os.fork()
if pid != 0:
# Parent
pid, sts = os.waitpid(pid, 0)
# throw away additional data [see bug #427345]
while select.select([self.rfile], [], [], 0)[0]:
if not self.rfile.read(1):
break
if sts:
self.log_error("CGI script exit status %#x", sts)
return
# Child
try:
try:
os.setuid(nobody)
except os.error:
pass
os.dup2(self.rfile.fileno(), 0)
os.dup2(self.wfile.fileno(), 1)
os.execve(scriptfile, args, os.environ)
except:
self.server.handle_error(self.request, self.client_address)
os._exit(127)
else:
# Non Unix - use subprocess
import subprocess
cmdline = [scriptfile]
if self.is_python(scriptfile):
interp = sys.executable
if interp.lower().endswith("w.exe"):
# On Windows, use python.exe, not pythonw.exe
interp = interp[:-5] + interp[-4:]
cmdline = [interp, '-u'] + cmdline
if '=' not in query:
cmdline.append(query)
self.log_message("command: %s", subprocess.list2cmdline(cmdline))
try:
nbytes = int(length)
except (TypeError, ValueError):
nbytes = 0
p = subprocess.Popen(cmdline,
stdin = subprocess.PIPE,
stdout = subprocess.PIPE,
stderr = subprocess.PIPE
)
if self.command.lower() == "post" and nbytes > 0:
data = self.rfile.read(nbytes)
else:
data = None
# throw away additional data [see bug #427345]
while select.select([self.rfile._sock], [], [], 0)[0]:
if not self.rfile._sock.recv(1):
break
stdout, stderr = p.communicate(data)
self.wfile.write(stdout)
if stderr:
self.log_error('%s', stderr)
status = p.returncode
if status:
self.log_error("CGI script exit status %#x", status)
else:
self.log_message("CGI script exited OK")
def _url_collapse_path_split(path):
path_parts = []
for part in path.split('/'):
if part == '.':
path_parts.append('')
else:
path_parts.append(part)
# Filter out blank non trailing parts before consuming the '..'.
path_parts = [part for part in path_parts[:-1] if part] + path_parts[-1:]
if path_parts:
tail_part = path_parts.pop()
else:
tail_part = ''
head_parts = []
for part in path_parts:
if part == '..':
head_parts.pop()
else:
head_parts.append(part)
if tail_part and tail_part == '..':
head_parts.pop()
tail_part = ''
return ('/' + '/'.join(head_parts), tail_part)
nobody = None
def nobody_uid():
"""Internal routine to get nobody's uid"""
global nobody
if nobody:
return nobody
try:
import pwd
except ImportError:
return -1
try:
nobody = pwd.getpwnam('nobody')[2]
except KeyError:
nobody = 1 + max(map(lambda x: x[2], pwd.getpwall()))
return nobody
def executable(path):
"""Test for executable file."""
try:
st = os.stat(path)
except os.error:
return False
return st.st_mode & 0111 != 0
Handler = RequestHandler
PORT = 7998
ADDRESS = "0.0.0.0"
httpd = ThreadedHTTPServer((ADDRESS, PORT), Handler)
print "serving at %s:%s" % (ADDRESS, PORT)
import os
import SocketServer
import BaseHTTPServer
import SimpleHTTPServer
import xmlrpclib
import SimpleXMLRPCServer
import socket
import httplib
import inspect
import win32service
import win32serviceutil
import win32api
import win32con
import win32event
import win32evtlogutil
class XMLRPCServerService(win32serviceutil.ServiceFramework):
_svc_name_ = "XMLRPCServerService"
_svc_display_name_ = "XMLRPCServerService"
_svc_description_ = "Tests Python service framework by receiving and echoing messages over a named pipe"
def __init__(self, args):
win32serviceutil.ServiceFramework.__init__(self, args)
self.hWaitStop = win32event.CreateEvent(None, 0, 0, None)
def SvcStop(self):
self.ReportServiceStatus(win32service.SERVICE_STOP_PENDING)
self.ReportServiceStatus(win32service.SERVICE_STOPPED)
win32event.SetEvent(self.hWaitStop)
def SvcDoRun(self):
import servicemanager
servicemanager.LogMsg(servicemanager.EVENTLOG_INFORMATION_TYPE,servicemanager.PYS_SERVICE_STARTED,(self._svc_name_, ''))
self.timeout = 100
while 1:
rc = win32event.WaitForSingleObject(self.hWaitStop, self.timeout)
if rc == win32event.WAIT_OBJECT_0:
servicemanager.LogInfoMsg("XMLRPCServerService - STOPPED")
break
else:
httpd.serve_forever()
servicemanager.LogInfoMsg("XMLRPCServerService - is alive and well")
def ctrlHandler(ctrlType):
return True
if __name__ == '__main__':
win32api.SetConsoleCtrlHandler(ctrlHandler, True)
win32serviceutil.HandleCommandLine(XMLRPCServerService)
Any clues where I am going wrong ? Or good way to implement it (May be w/o using service).
Strict Note:
Solution must be in Python 2.6 (Project requirements).
Updates:
I saw some weird thing in log:python service.py debug
127.0.0.1 - - [04/Apr/2014 09:41:04] command: C:\Python27\Lib\site-packages\win3
2\**pythonservice.exe** -u C:\CONSOLE-CGI\cgi-bin\login.py ""
Why is executing CGI script using pythonservice.exe?
What am I missing Here?
More updates:
Code snippet from daemon process python script
#Non Unix - use subprocess
import subprocess
cmdline = [scriptfile]
if self.is_python(scriptfile):
#interp = sys.executable // here it return pythonservice.exe
interp = "python.exe" // if I hardcode it to python.exe all goes fine
if interp.lower().endswith("w.exe"): #On Windows,use python.exe,not pythonw.exe
interp = interp[: -5] + interp[-4: ]
cmdline = [interp, '-u'] + cmdline
Any clues why is so??
You may need to redirect all the output since Windows scheduler has some issues doing this in pythonw case. Process does start properly, but no action being done and server does not respond without redirecting stdout and stderr.
import http.server
import socketserver
import sys
PORT = 1234
Handler = http.server.SimpleHTTPRequestHandler
if __name__ == '__main__':
sys.stdout = open('out.txt', 'w')
sys.stderr = open('err.txt', 'w')
with socketserver.TCPServer(("", PORT), Handler) as httpd:
print("serving at port %d" % PORT, flush=True)
httpd.serve_forever()
I have created my own CGI python server script (that serves on port 8000) by following a tutorial. The server works beautifully if I want to generate web pages from python scripts, or serve a native HTML page BUT it doesn't work for when I make an AJAX POST request?
If I make an AJAX request to the python file aaa.py (using the javascript below) my server prints out the following error text:
Code 501, message can only POST to to CGI scripts
"POST /aaa.py HTTP/1.1" 501 -
What do you think I need to do to allow my python cgi server to allow/handle AJAX requests?
My CGI server:
__version__ = "0.4"
__all__ = ["CGIHTTPRequestHandler"]
import os
import sys
import urllib
import BaseHTTPServer
import SimpleHTTPServer
import select
class CGIHTTPRequestHandler(SimpleHTTPServer.SimpleHTTPRequestHandler):
"""Complete HTTP server with GET, HEAD and POST commands.
GET and HEAD also support running CGI scripts.
The POST command is *only* implemented for CGI scripts.
"""
# Determine platform specifics
have_fork = hasattr(os, 'fork')
have_popen2 = hasattr(os, 'popen2')
have_popen3 = hasattr(os, 'popen3')
# pretend we don't have these to force execution in process
have_fork = 0
# Make rfile unbuffered -- we need to read one line and then pass
# the rest to a subprocess, so we can't use buffered input.
rbufsize = 0
def do_POST(self):
"""Serve a POST request.
This is only implemented for CGI scripts.
"""
if self.is_cgi():
self.run_cgi()
else:
self.send_error(501, "Can only POST to CGI scripts")
def send_head(self):
"""Version of send_head that support CGI scripts"""
if self.is_cgi():
return self.run_cgi()
else:
return SimpleHTTPServer.SimpleHTTPRequestHandler.send_head(self)
def is_cgi(self):
"""Test whether self.path corresponds to a CGI script.
Return a tuple (dir, rest) if self.path requires running a
CGI script, None if not. Note that rest begins with a
slash if it is not empty.
The default implementation tests whether the path
begins with one of the strings in the list
self.cgi_directories (and the next character is a '/'
or the end of the string).
"""
path = self.path
for x in self.cgi_directories:
i = len(x)
if path[:i] == x and (not path[i:] or path[i] == '/'):
self.cgi_info = path[:i], path[i+1:]
return True
return False
cgi_directories = ['/cgi-bin', '/htbin']
def is_executable(self, path):
"""Test whether argument path is an executable file."""
return executable(path)
def is_python(self, path):
"""Test whether argument path is a Python script."""
head, tail = os.path.splitext(path)
return tail.lower() in (".py", ".pyw")
def run_cgi(self):
"""Execute a CGI script."""
dir, rest = self.cgi_info
i = rest.rfind('?')
if i >= 0:
rest, query = rest[:i], rest[i+1:]
else:
query = ''
# i = rest.find('/')
# if i >= 0:
# script, rest = rest[:i], rest[i:]
# else:
# script, rest = rest, ''
script = rest
scriptname = dir + '/' + script
scriptfile = self.translate_path(scriptname)
if not os.path.exists(scriptfile):
self.send_error(404, "No such CGI script (%s)" % `scriptname`)
return
if not os.path.isfile(scriptfile):
self.send_error(403, "CGI script is not a plain file (%s)" %
`scriptname`)
return
ispy = self.is_python(scriptname)
if not ispy:
if not (self.have_fork or self.have_popen2 or self.have_popen3):
self.send_error(403, "CGI script is not a Python script (%s)" %
`scriptname`)
return
if not self.is_executable(scriptfile):
self.send_error(403, "CGI script is not executable (%s)" %
`scriptname`)
return
# Reference: http://hoohoo.ncsa.uiuc.edu/cgi/env.html
# XXX Much of the following could be prepared ahead of time!
env = {}
env['SERVER_SOFTWARE'] = self.version_string()
env['SERVER_NAME'] = self.server.server_name
env['GATEWAY_INTERFACE'] = 'CGI/1.1'
env['SERVER_PROTOCOL'] = self.protocol_version
env['SERVER_PORT'] = str(self.server.server_port)
env['REQUEST_METHOD'] = self.command
uqrest = urllib.unquote(rest)
env['PATH_INFO'] = uqrest
env['PATH_TRANSLATED'] = self.translate_path(uqrest)
env['SCRIPT_NAME'] = scriptname
if query:
env['QUERY_STRING'] = query
host = self.address_string()
if host != self.client_address[0]:
env['REMOTE_HOST'] = host
env['REMOTE_ADDR'] = self.client_address[0]
# XXX AUTH_TYPE
# XXX REMOTE_USER
# XXX REMOTE_IDENT
if self.headers.typeheader is None:
env['CONTENT_TYPE'] = self.headers.type
else:
env['CONTENT_TYPE'] = self.headers.typeheader
length = self.headers.getheader('content-length')
if length:
env['CONTENT_LENGTH'] = length
accept = []
for line in self.headers.getallmatchingheaders('accept'):
if line[:1] in "\t\n\r ":
accept.append(line.strip())
else:
accept = accept + line[7:].split(',')
env['HTTP_ACCEPT'] = ','.join(accept)
ua = self.headers.getheader('user-agent')
if ua:
env['HTTP_USER_AGENT'] = ua
co = filter(None, self.headers.getheaders('cookie'))
if co:
env['HTTP_COOKIE'] = ', '.join(co)
# XXX Other HTTP_* headers
if not self.have_fork:
# Since we're setting the env in the parent, provide empty
# values to override previously set values
for k in ('QUERY_STRING', 'REMOTE_HOST', 'CONTENT_LENGTH',
'HTTP_USER_AGENT'):
###, 'HTTP_COOKIE' -- removed by S.
env.setdefault(k, "")
# for key in env.keys():
# print key + " '" + env[key] + "'"
os.environ.update(env)
self.send_response(200, "Script output follows")
decoded_query = query.replace('+', ' ')
if self.have_fork:
# Unix -- fork as we should
args = [script]
if '=' not in decoded_query:
args.append(decoded_query)
nobody = nobody_uid()
self.wfile.flush() # Always flush before forking
pid = os.fork()
if pid != 0:
# Parent
pid, sts = os.waitpid(pid, 0)
# throw away additional data [see bug #427345]
while select.select([self.rfile], [], [], 0)[0]:
if not self.rfile.read(1):
break
if sts:
self.log_error("CGI script exit status %#x", sts)
return
# Child
try:
try:
os.setuid(nobody)
except os.error:
pass
os.dup2(self.rfile.fileno(), 0)
os.dup2(self.wfile.fileno(), 1)
os.execve(scriptfile, args, os.environ)
except:
self.server.handle_error(self.request, self.client_address)
os._exit(127)
elif self.have_popen2 or self.have_popen3:
# Windows -- use popen2 or popen3 to create a subprocess
import shutil
if self.have_popen3:
popenx = os.popen3
else:
popenx = os.popen2
cmdline = scriptfile
if self.is_python(scriptfile):
interp = sys.executable
if interp.lower().endswith("w.exe"):
# On Windows, use python.exe, not pythonw.exe
interp = interp[:-5] + interp[-4:]
cmdline = "%s -u \"%s\"" % (interp, cmdline)
if '=' not in query and '"' not in query:
cmdline = '%s "%s"' % (cmdline, query)
self.log_message("command: %s", cmdline)
try:
nbytes = int(length)
except (TypeError, ValueError):
nbytes = 0
files = popenx(cmdline, 'b')
fi = files[0]
fo = files[1]
if self.have_popen3:
fe = files[2]
if self.command.lower() == "post" and nbytes > 0:
data = self.rfile.read(nbytes)
fi.write(data)
# throw away additional data [see bug #427345]
while select.select([self.rfile._sock], [], [], 0)[0]:
if not self.rfile._sock.recv(1):
break
fi.close()
shutil.copyfileobj(fo, self.wfile)
if self.have_popen3:
errors = fe.read()
fe.close()
if errors:
self.log_error('%s', errors)
sts = fo.close()
if sts:
self.log_error("CGI script exit status %#x", sts)
else:
self.log_message("CGI script exited OK")
else:
# Other O.S. -- execute script in this process
save_argv = sys.argv
save_stdin = sys.stdin
save_stdout = sys.stdout
save_stderr = sys.stderr
try:
try:
sys.argv = [scriptfile]
if '=' not in decoded_query:
sys.argv.append(decoded_query)
sys.stdout = self.wfile
sys.stdin = self.rfile
execfile(scriptfile, {"__name__": "__main__"})
finally:
sys.argv = save_argv
sys.stdin = save_stdin
sys.stdout = save_stdout
sys.stderr = save_stderr
except SystemExit, sts:
self.log_error("CGI script exit status %s", str(sts))
else:
self.log_message("CGI script exited OK")
nobody = None
def nobody_uid():
"""Internal routine to get nobody's uid"""
global nobody
if nobody:
return nobody
try:
import pwd
except ImportError:
return -1
try:
nobody = pwd.getpwnam('nobody')[2]
except KeyError:
nobody = 1 + max(map(lambda x: x[2], pwd.getpwall()))
return nobody
def executable(path):
"""Test for executable file."""
try:
st = os.stat(path)
except os.error:
return False
return st.st_mode & 0111 != 0
def test(HandlerClass = CGIHTTPRequestHandler,
ServerClass = BaseHTTPServer.HTTPServer):
SimpleHTTPServer.test(HandlerClass, ServerClass)
if __name__ == '__main__':
test()
Code in aaa.py:
#!/usr/bin/env python
import cgitb; cgitb.enable()
import cgi
import os
print "Content-Type: text/html\n"
input_data = cgi.FieldStorage()
print "hello"
My AJAX/ Javascript:
function onTest( dest, params )
{
var xmlhttp;
if (window.XMLHttpRequest)
{// code for IE7+, Firefox, Chrome, Opera, Safari
xmlhttp=new XMLHttpRequest();
}
else
{// code for IE6, IE5
xmlhttp=new ActiveXObject("Microsoft.XMLHTTP");
}
xmlhttp.onreadystatechange=function()
{
if (xmlhttp.readyState==4 && xmlhttp.status==200)
{
document.getElementById( "bb" ).innerHTML = xmlhttp.responseText;
}
}
xmlhttp.open("POST",dest,true);
xmlhttp.setRequestHeader("Content-type","application/x-www-form-urlencoded");
xmlhttp.send( params );
}
when you use the python http cgi server, cgi scripts have to be under the subdir (from you server script ) /cgi-bin