python(版本2.23.0)爬虫程序使用代理IP,代理服务器返回407错误,这种情况下一般是认证信息传递失败导致,是因为httplib(python2)/http.client(python3) 模块的函数中,如果连接尝试不成功,它会引发 OSError , 需要进行方法封装专门对代理服务器的请求进行处理,用于设置认证信息传递,如下所示:
import re
import requests
from requests.utils import get_auth_from_url
from requests.auth import HTTPDigestAuth
from requests.utils import parse_dict_header
from urllib3.util import parse_url
def get_proxy_autorization_header(proxy, method):
username, password = get_auth_from_url(proxy)
auth = HTTPProxyDigestAuth(username, password)
proxy_url = parse_url(proxy)
proxy_response = requests.request(method, proxy_url, auth=auth)
return proxy_response.request.headers['Proxy-Authorization']
class HTTPSAdapterWithProxyDigestAuth(requests.adapters.HTTPAdapter):
def proxy_headers(self, proxy):
headers = {}
proxy_auth_header = get_proxy_autorization_header(proxy, 'CONNECT')
headers['Proxy-Authorization'] = proxy_auth_header
return headers
class HTTPAdapterWithProxyDigestAuth(requests.adapters.HTTPAdapter):
def proxy_headers(self, proxy):
return {}
def add_headers(self, request, **kwargs):
proxy = kwargs['proxies'].get('http', '')
if proxy:
proxy_auth_header = get_proxy_autorization_header(proxy, request.method)
request.headers['Proxy-Authorization'] = proxy_auth_header
class HTTPProxyDigestAuth(requests.auth.HTTPDigestAuth):
def init_per_thread_state(self):
# Ensure state is initialized just once per-thread
if not hasattr(self._thread_local, 'init'):
self._thread_local.init = True
self._thread_local.last_nonce = ''
self._thread_local.nonce_count = 0
self._thread_local.chal = {}
self._thread_local.pos = None
self._thread_local.num_407_calls = None
def handle_407(self, r, **kwargs):
"""
Takes the given response and tries digest-auth, if needed.
:rtype: requests.Response
"""
# If response is not 407, do not auth
if r.status_code != 407:
self._thread_local.num_407_calls = 1
return r
s_auth = r.headers.get('proxy-authenticate', '')
if 'digest' in s_auth.lower() and self._thread_local.num_407_calls < 2:
self._thread_local.num_407_calls += 1
pat = re.compile(r'digest ', flags=re.IGNORECASE)
self._thread_local.chal = requests.utils.parse_dict_header(
pat.sub('', s_auth, count=1))
# Consume content and release the original connection
# to allow our new request to reuse the same one.
r.content
r.close()
prep = r.request.copy()
requests.cookies.extract_cookies_to_jar(prep._cookies, r.request, r.raw)
prep.prepare_cookies(prep._cookies)
prep.headers['Proxy-Authorization'] = self.build_digest_header(prep.method, prep.url)
_r = r.connection.send(prep, **kwargs)
_r.history.append(r)
_r.request = prep
return _r
self._thread_local.num_407_calls = 1
return r
session = requests.Session()
def __call__(self, r):
# Initialize per-thread state, if needed
self.init_per_thread_state()
# If we have a saved nonce, skip the 407
if self._thread_local.last_nonce:
r.headers['Proxy-Authorization'] = self.build_digest_header(r.method, r.url)
r.register_hook('response', self.handle_407)
self._thread_local.num_407_calls = 1
return r
# 代理服务器(产品官网 www.16yun.cn)
proxyHost = "t.16yun.cn"
proxyPort = "31111"
# 代理验证信息
proxyUser = "username"
proxyPass = "password"
proxyMeta = "http://%(user)s:%(pass)s@%(host)s:%(port)s" % {
"host" : proxyHost,
"port" : proxyPort,
"user" : proxyUser,
"pass" : proxyPass,
}
session.proxies = {
'http': proxyMeta,
'https':proxyMeta,
}
session.trust_env = False
session.mount('http://', HTTPAdapterWithProxyDigestAuth())
session.mount('https://', HTTPSAdapterWithProxyDigestAuth())
response_http = session.get("http://www.baidu.com/")
print(response_http.status_code)
response_https = session.get("https://www.baidu.com")
print(response_https.status_code)
上面代码这段代码定义了一系列用于HTTP 代理服务器进行身份验证的类。例如,它定义了 HTTPSAdapterWithProxyDigestAuth 类,该类可用于代理服务器进行 HTTPS 请求的身份验证。它还定义了 HTTPAdapterWithProxyDigestAuth 类,该类可用于代理服务器进行 HTTP 请求的身份验证。此外,它还定义了 HTTPProxyDigestAuth 类,该类继承自 requests.auth.HTTPDigestAuth 类,并扩展了它,以便支持在处理 407 错误响应时进行多次身份验证。
欢迎私信联系索取更多资料