tor.py

import socks
import urllib2
import requests
from Queue import Queue
from threading import Thread
import httplib


class SocksiPyConnection(httplib.HTTPConnection):
    def __init__(self, proxytype, proxyaddr, proxyport = None, rdns = True, username = None, password = None, *args, **kwargs):
        self.proxyargs = (proxytype, proxyaddr, proxyport, rdns, username, password)
        httplib.HTTPConnection.__init__(self, *args, **kwargs)

    def connect(self):
        self.sock = socks.socksocket()
        self.sock.setproxy(*self.proxyargs)
        if isinstance(self.timeout, float):
            self.sock.settimeout(self.timeout)
        self.sock.connect((self.host, self.port))

class SocksiPyHandler(urllib2.HTTPHandler):
    def __init__(self, *args, **kwargs):
        self.args = args
        self.kw = kwargs
        urllib2.HTTPHandler.__init__(self)

    def http_open(self, req):
        def build(host, port=None, strict=None, timeout=0):
            conn = SocksiPyConnection(*self.args, host=host, port=port, strict=strict, timeout=timeout, **self.kw)
            return conn
        return self.do_open(build, req)




def fetch_links(q, port):

	while True:

		s = socks.socksocket()
		opener = urllib2.build_opener(SocksiPyHandler(socks.PROXY_TYPE_SOCKS4, "127.0.0.1", port, True))

		index = q.get()
		url = url_format.format(index)
		url = 'http://www.datamungeblog.com/2013/11/anonymous-web-scraping.html'

		h = opener.open(url)
		data = h.read()
		code = h.getcode()

		print len(data)
		print code
		print"----------"
		
		q.task_done()


num_workers = 1
base_port = 9050
num_urls = 1000
workers = []

url_format = 'http://www.imdb.com/user/ur{0}/ratings'

for i in range(num_workers):
	new_port = base_port + i
	worker = Thread(target=fetch_links, args=(q, new_port))
	worker.setDaemon = True
	worker.start()


q = Queue(maxsize=0)

for x in range(1000):
	q.put(x)

q.join()