How to make urllib2 requests through Tor in Python?

Admin 1
Viewed 48047

I'm trying to crawl websites using a crawler written in Python. I want to integrate Tor with Python meaning I want to crawl the site anonymously using Tor.

I tried doing this. It doesn't seem to work. I checked my IP it is still the same as the one before I used tor. I checked it via python.

import urllib2
proxy_handler = urllib2.ProxyHandler({"tcp":"http://127.0.0.1:9050"})
opener = urllib2.build_opener(proxy_handler)
urllib2.install_opener(opener)
tor python
12 Answers

You are trying to connect to a SOCKS port - Tor rejects any non-SOCKS traffic. You can connect through a middleman - Privoxy - using Port 8118.

Example:

proxy_support = urllib2.ProxyHandler({"http" : "127.0.0.1:8118"})
opener = urllib2.build_opener(proxy_support) 
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
print opener.open('http://www.google.com').read()

Also please note properties passed to ProxyHandler, no http prefixing the ip:port

user_1036470

Using privoxy as http-proxy in front of tor works for me - here's a crawler-template:


import urllib2
import httplib

from BeautifulSoup import BeautifulSoup
from time import sleep

class Scraper(object):
    def __init__(self, options, args):
        if options.proxy is None:
            options.proxy = "http://localhost:8118/"
        self._open = self._get_opener(options.proxy)

    def _get_opener(self, proxy):
        proxy_handler = urllib2.ProxyHandler({'http': proxy})
        opener = urllib2.build_opener(proxy_handler)
        return opener.open

    def get_soup(self, url):
        soup = None
        while soup is None:
            try:
                request = urllib2.Request(url)
                request.add_header('User-Agent', 'foo bar useragent')
                soup = BeautifulSoup(self._open(request))
            except (httplib.IncompleteRead, httplib.BadStatusLine,
                    urllib2.HTTPError, ValueError, urllib2.URLError), err:
                sleep(1)
        return soup

class PageType(Scraper):
    _URL_TEMPL = "http://foobar.com/baz/%s"

    def items_from_page(self, url):
        nextpage = None
        soup = self.get_soup(url)

        items = []
        for item in soup.findAll("foo"):
            items.append(item["bar"])
            nexpage = item["href"]

        return nextpage, items

    def get_items(self):
        nextpage, items = self._categories_from_page(self._START_URL % "start.html")
        while nextpage is not None:
            nextpage, newitems = self.items_from_page(self._URL_TEMPL % nextpage)
            items.extend(newitems)
        return items()

pt = PageType()
print pt.get_items()
Admin1

The following solution works for me in Python 3. Adapted from CiroSantilli's answer:

With urllib (name of urllib2 in Python 3):

import socks
import socket
from urllib.request import urlopen

url = 'http://icanhazip.com/'

socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, '127.0.0.1', 9150)
socket.socket = socks.socksocket

response = urlopen(url)
print(response.read())

With requests:

import socks
import socket
import requests

url = 'http://icanhazip.com/'

socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, '127.0.0.1', 9150)
socket.socket = socks.socksocket

response = requests.get(url)
print(response.text)

With Selenium + PhantomJS:

from selenium import webdriver

url = 'http://icanhazip.com/'

service_args = [ '--proxy=localhost:9150', '--proxy-type=socks5', ]
phantomjs_path = '/your/path/to/phantomjs'

driver = webdriver.PhantomJS(
    executable_path=phantomjs_path, 
    service_args=service_args)

driver.get(url)
print(driver.page_source)
driver.close()

Note: If you are planning to use Tor often, consider making a donation to support their awesome work!

user_58022890

Perhaps you're having some network connectivity issues? The above script worked for me (I substituted a different URL - I used http://stackoverflow.com/ - and I get the page as expected:

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd" >
 <html> <head>

<title>Stack Overflow</title>        
<link rel="stylesheet" href="/content/all.css?v=3856">

(etc.)

user_1189030

Thought I would just share a solution that worked for me (python3, windows10):

Step 1: Enable your Tor ControlPort at 9151.

Tor service runs at default port 9150 and ControlPort on 9151. You should be able to see local address 127.0.0.1:9150 and 127.0.0.1:9151 when you run netstat -an.

[go to windows terminal]
cd ...\Tor Browser\Browser\TorBrowser\Tor
tor --service remove
tor --service install -options ControlPort 9151
netstat -an

Step 2: Python script as follow.

# library to launch and kill Tor process
import os
import subprocess

# library for Tor connection
import socket
import socks
import http.client
import time
import requests
from stem import Signal
from stem.control import Controller

# library for scraping
import csv
import urllib
from bs4 import BeautifulSoup
import time

def launchTor():
    # start Tor (wait 30 sec for Tor to load)
    sproc = subprocess.Popen(r'.../Tor Browser/Browser/firefox.exe')
    time.sleep(30)
    return sproc

def killTor(sproc):
    sproc.kill()

def connectTor():
    socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, "127.0.0.1", 9150, True)
    socket.socket = socks.socksocket
    print("Connected to Tor")

def set_new_ip():
    # disable socks server and enabling again
    socks.setdefaultproxy()
    """Change IP using TOR"""
    with Controller.from_port(port=9151) as controller:
        controller.authenticate()
        socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, "127.0.0.1", 9150, True)
        socket.socket = socks.socksocket
        controller.signal(Signal.NEWNYM)

def checkIP():
    conn = http.client.HTTPConnection("icanhazip.com")
    conn.request("GET", "/")
    time.sleep(3)
    response = conn.getresponse()
    print('current ip address :', response.read())

# Launch Tor and connect to Tor network
sproc = launchTor()
connectTor()

# list of url to scrape
url_list = [list of all the urls you want to scrape]

for url in url_list:
    # set new ip and check ip before scraping for each new url
    set_new_ip()
    # allow some time for IP address to refresh
    time.sleep(5)
    checkIP()

    '''
    [insert your scraping code here: bs4, urllib, your usual thingy]
    '''

# remember to kill process 
killTor(sproc)

This script above will renew IP address for every URL that you want to scrape. Just make sure to sleep it long enough for IP to change. Last tested yesterday. Hope this helps!

user_91831440
Related