How to solve 'RecursionError: maximum recursion depth exceeded' with Eventlet and Requests in Python

Question

我正在尝试实施提到的 Amazon Web Scraper here。但是，我得到下面提到的输出。重复输出，直到以 RecursionError: maximum recursion depth exceeded 停止。我已经尝试将 eventlet 降级到版本 0.17.4，如前所述 here。此外，requests 模块正在修补，如您在 helpers.py.

中所见

helpers.py

import os
import random
from datetime import datetime
from urllib.parse import urlparse

import eventlet

requests = eventlet.import_patched('requests.__init__')
time = eventlet.import_patched('time')
import redis

from bs4 import BeautifulSoup
from requests.exceptions import RequestException

import settings

num_requests = 0

redis = redis.StrictRedis(host=settings.redis_host, port=settings.redis_port, db=settings.redis_db)


def make_request(url, return_soup=True):
    # global request building and response handling

    url = format_url(url)

    if "picassoRedirect" in url:
        return None  # skip the redirect URLs

    global num_requests
    if num_requests >= settings.max_requests:
        raise Exception("Reached the max number of requests: {}".format(settings.max_requests))

    proxies = get_proxy()
    try:
        r = requests.get(url, headers=settings.headers, proxies=proxies)
    except RequestException as e:
        log("WARNING: Request for {} failed, trying again.".format(url))

    num_requests += 1

    if r.status_code != 200:
        os.system('say "Got non-200 Response"')
        log("WARNING: Got a {} status code for URL: {}".format(r.status_code, url))
        return None

    if return_soup:
        return BeautifulSoup(r.text), r.text
    return r


def format_url(url):
    # make sure URLs aren't relative, and strip unnecssary query args
    u = urlparse(url)

    scheme = u.scheme or "https"
    host = u.netloc or "www.amazon.de"
    path = u.path

    if not u.query:
        query = ""
    else:
        query = "?"
        for piece in u.query.split("&"):
            k, v = piece.split("=")
            if k in settings.allowed_params:
                query += "{k}={v}&".format(**locals())
        query = query[:-1]

    return "{scheme}://{host}{path}{query}".format(**locals())


def log(msg):
    # global logging function
    if settings.log_stdout:
        try:
            print("{}: {}".format(datetime.now(), msg))
        except UnicodeEncodeError:
            pass  # squash logging errors in case of non-ascii text


def get_proxy():
    # choose a proxy server to use for this request, if we need one
    if not settings.proxies or len(settings.proxies) == 0:
        return None

    proxy = random.choice(settings.proxies)
    proxy_url = "socks5://{user}:{passwd}@{ip}:{port}/".format(
        user=settings.proxy_user,
        passwd=settings.proxy_pass,
        ip=proxy,
        port=settings.proxy_port,
    )
    return {
        "http": proxy_url,
        "https": proxy_url
    }

if __name__ == '__main__':
    # test proxy server IP masking
    r = make_request('https://api.ipify.org?format=json', return_soup=False)
    print(r.text)

输出

Traceback (most recent call last):
  File "helpers.py", line 112, in <module>
    r = make_request('https://api.ipify.org?format=json', return_soup=False)
  File "helpers.py", line 36, in make_request
    r = requests.get(url, headers=settings.headers, proxies=proxies)
  File "/home/ec2-user/env/lib64/python3.7/site-packages/requests/api.py", line 76, in get
    return request('get', url, params=params, **kwargs)
  File "/home/ec2-user/env/lib64/python3.7/site-packages/requests/api.py", line 61, in request
    return session.request(method=method, url=url, **kwargs)
  File "/home/ec2-user/env/lib64/python3.7/site-packages/requests/sessions.py", line 530, in request
    resp = self.send(prep, **send_kwargs)
  File "/home/ec2-user/env/lib64/python3.7/site-packages/requests/sessions.py", line 643, in send
    r = adapter.send(request, **kwargs)
  File "/home/ec2-user/env/lib64/python3.7/site-packages/requests/adapters.py", line 449, in send
    timeout=timeout
  File "/home/ec2-user/env/lib64/python3.7/site-packages/urllib3/connectionpool.py", line 672, in urlopen
    chunked=chunked,
  File "/home/ec2-user/env/lib64/python3.7/site-packages/urllib3/connectionpool.py", line 376, in _make_request
    self._validate_conn(conn)
  File "/home/ec2-user/env/lib64/python3.7/site-packages/urllib3/connectionpool.py", line 994, in _validate_conn
    conn.connect()
  File "/home/ec2-user/env/lib64/python3.7/site-packages/urllib3/connection.py", line 300, in connect
    conn = self._new_conn()
  File "/home/ec2-user/env/lib64/python3.7/site-packages/urllib3/contrib/socks.py", line 99, in _new_conn
    **extra_kw
  File "/home/ec2-user/env/lib64/python3.7/site-packages/socks.py", line 199, in create_connection
    sock.connect((remote_host, remote_port))
  File "/home/ec2-user/env/lib64/python3.7/site-packages/socks.py", line 47, in wrapper
    return function(*args, **kwargs)
  File "/home/ec2-user/env/lib64/python3.7/site-packages/socks.py", line 774, in connect
    super(socksocket, self).settimeout(self._timeout)
  File "/home/ec2-user/env/lib64/python3.7/site-packages/eventlet/greenio/base.py", line 395, in settimeout
    self.setblocking(True)

这可能是什么问题？

Answer 1

原来删除 eventlet.monkey_patch() 和 import eventlet 解决了问题。

How to solve 'RecursionError: maximum recursion depth exceeded' with Eventlet and Requests in Python

How to solve 'RecursionError: maximum recursion depth exceeded' with Eventlet and Requests in Python

python

proxy

amazon-ec2

web-scraping

eventlet