我之前使用过Mechanize模块，现在想要使用Requests模块。
(Python mechanize doesn't work when HTTPS and Proxy Authentication required)
当我访问互联网时，我必须通过代理服务器。
代理服务器需要身份验证。我编写了以下代码。
import requests
from requests.auth import HTTPProxyAuth
proxies = {"http":"192.168.20.130:8080"}
auth = HTTPProxyAuth("username", "password")
r = requests.get("http://www.google.co.jp/", proxies=proxies, auth=auth)
大多数情况下不需要自己实现！ Requests已经内置了对代理和基本验证的支持。
proxies = { 'https' : 'https://user:password@proxyip:port' }
r = requests.get('https://url', proxies=proxies)
在文档中查看更多信息。
如果需要摘要身份验证，HTTPDigestAuth 可能会有所帮助。
或者您可能需要像下面的 yutaka2487 一样扩展它。
注意：必须使用代理服务器的 IP 地址而不是名称！
我编写了一个类，可以用于代理身份验证（基于摘要认证）。
我几乎从 requests.auth.HTTPDigestAuth 中借用了所有的代码。
我编写了一个能够用于代理身份验证的类（基于摘要认证），几乎所有的代码都是从 requests.auth.HTTPDigestAuth 中借鉴而来。
import requests
import requests.auth
class HTTPProxyDigestAuth(requests.auth.HTTPDigestAuth):
def handle_407(self, r):
"""Takes the given response and tries digest-auth, if needed."""
num_407_calls = r.request.hooks['response'].count(self.handle_407)
s_auth = r.headers.get('Proxy-authenticate', '')
if 'digest' in s_auth.lower() and num_407_calls < 2:
self.chal = requests.auth.parse_dict_header(s_auth.replace('Digest ', ''))
# Consume content and release the original connection
# to allow our new request to reuse the same one.
r.content
r.raw.release_conn()
r.request.headers['Authorization'] = self.build_digest_header(r.request.method, r.request.url)
r.request.send(anyway=True)
_r = r.request.response
_r.history.append(r)
return _r
return r
def __call__(self, r):
if self.last_nonce:
r.headers['Proxy-Authorization'] = self.build_digest_header(r.method, r.url)
r.register_hook('response', self.handle_407)
return r
使用方法：
proxies = {
"http" :"192.168.20.130:8080",
"https":"192.168.20.130:8080",
}
auth = HTTPProxyDigestAuth("username", "password")
# HTTP
r = requests.get("http://www.google.co.jp/", proxies=proxies, auth=auth)
r.status_code # 200 OK
# HTTPS
r = requests.get("https://www.google.co.jp/", proxies=proxies, auth=auth)
r.status_code # 200 OK
requests 库现在已经内置了代理支持，例如 proxies = { 'https' : 'https://user:password@ip:port' } ; r = requests.get('https://url', proxies=proxies)，请查看 http://docs.python-requests.org/en/latest/user/advanced/。 - BurnsBArequests 库一起使用。user1和密码password1的HTTP摘要认证，通过HTTP代理1.2.3.4:8080获取页面https://httpbin.org/ip。import requests
from requests_digest_proxy import HTTPProxyDigestAuth
s = requests.Session()
s.proxies = {
'http': 'http://1.2.3.4:8080/',
'https': 'http://1.2.3.4:8080/'
}
s.auth = HTTPProxyDigestAuth('user1', 'password1')
print(s.get('https://httpbin.org/ip').text)
HTTPProxyDigestAuth构造函数：# HTTP Basic authentication for website
s.auth = HTTPProxyDigestAuth(('user1', 'password1'),
auth=requests.auth.HTTPBasicAuth('user1', 'password0'))
print(s.get('https://httpbin.org/basic-auth/user1/password0').text))
# HTTP Digest authentication for website
s.auth = HTTPProxyDigestAuth(('user1', 'password1'),,
auth=requests.auth.HTTPDigestAuth('user1', 'password0'))
print(s.get('https://httpbin.org/digest-auth/auth/user1/password0').text)
requests-toolbelt则失败了。非常感谢！ - robertspierre这个片段适用于两种类型的请求（http 和 https）。已在当前版本的 requests（2.23.0）上进行了测试。
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
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
session = requests.Session()
session.proxies = {
'http': 'http://username:password@proxyhost:proxyport',
'https': 'http://username:password@proxyhost:proxyport'
}
session.trust_env = False
session.mount('http://', HTTPAdapterWithProxyDigestAuth())
session.mount('https://', HTTPSAdapterWithProxyDigestAuth())
response_http = session.get("http://ww3.safestyle-windows.co.uk/the-secret-door/")
print(response_http.status_code)
response_https = session.get("https://dev59.com/dGYr5IYBdhLWcg3wpbyQ")
print(response_https.status_code)
一般来说，代理授权的问题也与其他类型的身份验证（ntlm、kerberos）在使用协议HTTPS进行连接时相关。尽管存在大量问题（自2013年以来，可能还有更早的问题我没有找到）：
在requests中：摘要代理授权, NTLM代理授权, Kerberos代理授权
以及许多其他问题，但这个问题仍未解决。
在模块httplib（python2）/http.client（python3）的函数_tunnel中存在问题的根源。如果连接尝试失败，则会引发一个OSError，但不返回响应代码（我们的情况下为407）和构建授权标头所需的其他数据。Lukasa在这里给出了解释here。 只要urllib3（或requests）的维护者没有解决方案，我们就只能使用各种解决方法（例如，使用@Tey的方法approach或像这样做this）。在我的解决方法版本中，我们通过向代理服务器发送请求并处理接收到的响应来预先准备必要的授权数据。curl完成了它，只需要指示该身份验证类型在代理服务器上被使用，然后curl本身就会找到存储在系统中的所有必要凭据。 - zanuda您可以使用requests.auth.HTTPDigestAuth代替requests.auth.HTTPProxyAuth，以使用摘要认证。
https://toolbelt.readthedocs.org/en/latest/authentication.html#httpproxydigestauth
这对我来说有效。实际上，我不知道这种方法中用户:密码的安全性：
import requests
import os
http_proxyf = 'http://user:password@proxyip:port'
os.environ["http_proxy"] = http_proxyf
os.environ["https_proxy"] = http_proxyf
sess = requests.Session()
# maybe need sess.trust_env = True
print(sess.get('https://some.org').text)
import requests
import os
# in my case I had to add my local domain
proxies = {
'http': 'proxy.myagency.com:8080',
'https': 'user@localdomain:password@proxy.myagency.com:8080',
}
r=requests.get('https://api.github.com/events', proxies=proxies)
print(r.text)
import requests
url = 'https://someaddress-behindproxy.com'
params = {'apikey': '123456789'} #if you need params
proxies = {'https': 'https://proxyaddress.com:3128'} #or some other port
response = requests.get(url, proxies=proxies, params=params)
希望这能帮助到某个人。
HTTPDigestAuth仅支持与最终网站服务器（WWW-Authenticate/Authorization标头，401状态）进行身份验证，而不是代理服务器（Proxy-Authenticate/Proxy-Authorization标头，407状态）。您需要类似于@yutaka2487提供的解决方案，但它仅适用于通过代理联系HTTP服务器，而不是HTTPS服务器，因为requests/urllib3后端在通过隧道传输HTTPS连接时不报告代理错误，因此摘要认证无法正常工作。 - Tey'或者你可能需要像 yutaka2487 下面所做的那样尝试扩展它。 - imbr