4
Tor를 사용하는 스크레이퍼에서 작업하고 있습니다.이 예제에서는 단순화 된 버전 인 https://github.com/khpeek/scraper-compose입니다. 나는 Scrapy extension으로 활성화 한 settings.py에서Tor의 스템 콘트롤러에서 "제어 소켓 (소켓 클로즈) : 빈 소켓 콘텐트"수신 중 오류가 발생했습니다.
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 # Wait 2 seconds (actually a random time between 1 and 3 seconds) between downloading pages
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
, : quotes_spider.py 정의는 Scrapy Tutorial에 따라 매우 간단한 일이다
.
├── docker-compose.yml
├── privoxy
│ ├── config
│ └── Dockerfile
├── scraper
│ ├── Dockerfile
│ ├── requirements.txt
│ ├── tutorial
│ │ ├── scrapy.cfg
│ │ └── tutorial
│ │ ├── extensions.py
│ │ ├── __init__.py
│ │ ├── items.py
│ │ ├── middlewares.py
│ │ ├── pipelines.py
│ │ ├── settings.py
│ │ ├── spiders
│ │ │ ├── __init__.py
│ │ │ └── quotes_spider.py
│ │ └── tor_controller.py
│ └── wait-for
│ └── wait-for
└── tor
├── Dockerfile
└── torrc
거미 :이 프로젝트는 다음 (간체) 구조를 가지고 extensions.py이
EXTENSIONS = {
'tutorial.extensions.TorRenewIdentity': 1,
}
로그에 따라 성공적으로 IP 주소를 변경하고 긁어 계속 : I 작동 확장으로 대형, docker-compose up 다음 docker-compose build를 사용하여 크롤링을 시작하면
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) # Randomize the item count to confound traffic analysis
self._item_count = item_count # Also remember the given item count for future randomizations
self.items_scraped = 0
# Connect the extension object to signals
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's 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) # Instantiate the extension object
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() # Change IP address (cf. https://stem.torproject.org/faq.html#how-do-i-request-a-new-identity-from-tor)
self.items_scraped = 0 # Reset the counter
self.item_count = self.randomize(self._item_count) # Generate a new random number of items to scrape before changing identity again
self.crawler.engine.unpause()
및 tor_controller.py는
import logging
import sys
import socket
import time
import requests
import stem
import stem.control
# Tor settings
TOR_ADDRESS = socket.gethostbyname("tor") # The Docker-Compose service in which this code is running should be linked to the "tor" service.
TOR_CONTROL_PORT = 9051 # This is configured in /etc/tor/torrc by the line "ControlPort 9051" (or by launching Tor with "tor -controlport 9051")
TOR_PASSWORD = "foo" # The Tor password is written in the docker-compose.yml file. (It is passed as a build argument to the 'tor' service).
# Privoxy settings
PRIVOXY_ADDRESS = "privoxy" # This assumes this code is running in a Docker-Compose service linked to the "privoxy" service
PRIVOXY_PORT = 8118 # This is determined by the "listen-address" in Privoxy's "config" file
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()
입니다. 날 irks 무엇
그러나, 나는 그런
scraper_1 | 2017-05-12 16:35:06 [stem] INFO: Error while receiving a control message (SocketClosed): empty socket content
과 같은 오류 메시지가 이러한 오류의 원인이 무엇
scraper_1 | 2017-05-12 16:35:06 [stem] INFO: Error while receiving a control message (SocketClosed): received exception "peek of closed file"
다음을 참조 기간 동안 엔진이 일시 정지 된 것입니다? 그들은 레벨이 INFO이므로 어쩌면 무시할 수 있습니까? (나는 Stem의 소스 코드를 https://gitweb.torproject.org/stem.git/으로 보았지만 지금까지 무슨 일이 일어나고 있는지에 대한 핸들을 얻을 수 없었다.)