I am working on a scraper that uses Tor, of which a simplified version is in this sample project: https://github.com/khpeek/scraper-compose . The project has the following (simplified) structure:
.
βββ docker-compose.yml
βββ privoxy
β βββ config
β βββ Dockerfile
βββ scraper
β βββ Dockerfile
β βββ requirements.txt
β βββ tutorial
β β βββ scrapy.cfg
β β βββ tutorial
β β βββ extensions.py
β β βββ __init__.py
β β βββ items.py
β β βββ middlewares.py
β β βββ pipelines.py
β β βββ settings.py
β β βββ spiders
β β β βββ __init__.py
β β β βββ quotes_spider.py
β β βββ tor_controller.py
β βββ wait-for
β βββ wait-for
βββ tor
βββ Dockerfile
βββ torrc
Spider defined quotes_spider.py, very simple, based on Scrapy Tutorial :
import scrapy
from tutorial.items import QuoteItem
class QuotesSpider(scrapy.Spider):
name = "quotes"
start_urls = ['http://quotes.toscrape.com/page/{n}/'.format(n=n) for n in range(1, 3)]
custom_settings = {
'TOR_RENEW_IDENTITY_ENABLED': True,
'TOR_ITEMS_TO_SCRAPE_PER_IDENTITY': 5
}
download_delay = 2
def parse(self, response):
for quote in response.css('div.quote'):
item = QuoteItem()
item['text'] = quote.css('span.text::text').extract_first()
item['author'] = quote.css('small.author::text').extract_first()
item['tags'] = quote.css('div.tags a.tag::text').extract()
yield item
In settings.pyI activated the Scrapy extension with lines
EXTENSIONS = {
'tutorial.extensions.TorRenewIdentity': 1,
}
where extensions.pyis
import logging
import random
from scrapy import signals
from scrapy.exceptions import NotConfigured
import tutorial.tor_controller as tor_controller
logger = logging.getLogger(__name__)
class TorRenewIdentity(object):
def __init__(self, crawler, item_count):
self.crawler = crawler
self.item_count = self.randomize(item_count)
self._item_count = item_count
self.items_scraped = 0
self.crawler.signals.connect(self.item_scraped, signal=signals.item_scraped)
@staticmethod
def randomize(item_count, min_factor=0.5, max_factor=1.5):
'''Randomize the number of items scraped before changing identity. (A similar technique is applied to Scrapy DOWNLOAD_DELAY setting).'''
randomized_item_count = random.randint(int(min_factor*item_count), int(max_factor*item_count))
logger.info("The crawler will scrape the following (randomized) number of items before changing identity (again): {}".format(randomized_item_count))
return randomized_item_count
@classmethod
def from_crawler(cls, crawler):
if not crawler.settings.getbool('TOR_RENEW_IDENTITY_ENABLED'):
raise NotConfigured
item_count = crawler.settings.getint('TOR_ITEMS_TO_SCRAPE_PER_IDENTITY', 50)
return cls(crawler=crawler, item_count=item_count)
def item_scraped(self, item, spider):
'''When item_count items are scraped, pause the engine and change IP address.'''
self.items_scraped += 1
if self.items_scraped == self.item_count:
logger.info("Scraped {item_count} items. Pausing engine while changing identity...".format(item_count=self.item_count))
self.crawler.engine.pause()
tor_controller.change_identity()
self.items_scraped = 0
self.item_count = self.randomize(self._item_count)
self.crawler.engine.unpause()
and tor_controller.pyhave
import logging
import sys
import socket
import time
import requests
import stem
import stem.control
TOR_ADDRESS = socket.gethostbyname("tor")
TOR_CONTROL_PORT = 9051
TOR_PASSWORD = "foo"
PRIVOXY_ADDRESS = "privoxy"
PRIVOXY_PORT = 8118
HTTP_PROXY = 'http://{address}:{port}'.format(address=PRIVOXY_ADDRESS, port=PRIVOXY_PORT)
logger = logging.getLogger(__name__)
class TorController(object):
def __init__(self):
self.controller = stem.control.Controller.from_port(address=TOR_ADDRESS, port=TOR_CONTROL_PORT)
self.controller.authenticate(password=TOR_PASSWORD)
self.session = requests.Session()
self.session.proxies = {'http': HTTP_PROXY}
def request_ip_change(self):
self.controller.signal(stem.Signal.NEWNYM)
def get_ip(self):
'''Check what the current IP address is (as seen by IPEcho).'''
return self.session.get('http://ipecho.net/plain').text
def change_ip(self):
'''Signal a change of IP address and wait for confirmation from IPEcho.net'''
current_ip = self.get_ip()
logger.debug("Initializing change of identity from the current IP address, {current_ip}".format(current_ip=current_ip))
self.request_ip_change()
while True:
new_ip = self.get_ip()
if new_ip == current_ip:
logger.debug("The IP address is still the same. Waiting for 1 second before checking again...")
time.sleep(1)
else:
break
logger.debug("The IP address has been changed from {old_ip} to {new_ip}".format(old_ip=current_ip, new_ip=new_ip))
return new_ip
def __enter__(self):
return self
def __exit__(self, *args):
self.controller.close()
def change_identity():
with TorController() as tor_controller:
tor_controller.change_ip()
If I start scanning with the help docker-compose buildthat follows docker-compose up, the extension basically works: according to the logs, it successfully changes the IP address and continues to clear.
, , , ,
scraper_1 | 2017-05-12 16:35:06 [stem] INFO: Error while receiving a control message (SocketClosed): empty socket content
scraper_1 | 2017-05-12 16:35:06 [stem] INFO: Error while receiving a control message (SocketClosed): received exception "peek of closed file"
? INFO, , ? ( Stem https://gitweb.torproject.org/stem.git/, , ).