代理訪問https網站報ssl錯誤

系統環境

• Debian 3.16.7-ckt11-1+deb8u3 (2015-08-04) x86_64 GNU/Linux
• Python 3.4.2
• requests (2.4.3)
  

代碼

# -*- coding: utf-8 -*-
"""python3提取api連接並使用requests庫進行http代理"""
import requests
import random

page_url = "https://dev.kdlapi.com/testproxy"  # 要訪問的目標網頁
# API接口，返回格式爲json。快代理提供
api_url = "http://kps.kdlapi.com/api/getkps/?orderid=968347822535999&num=1&pt=1&format=json&sep=1"

# API接口返回的ip
proxy_ip = requests.get(api_url).json()['data']['proxy_list']

# 用戶名和密碼(私密代理/獨享代理)
proxies = {
    "http": "http://%(proxy)s/" % {'proxy': random.choice(proxy_ip)},
    "https": "https://%(proxy)s/" % {'proxy': random.choice(proxy_ip)}
}
print(proxies)
headers = {
    "Accept-Encoding": "Gzip",  # 使用gzip壓縮傳輸數據讓訪問更快
}
r = requests.get(page_url, headers=headers)
# 發送post請求
# r = requests.post("http://dev.kdlapi.com/testproxy", data={"info": "send post request"}, headers=headers)
print(r.status_code)  # 獲取Response的返回碼

if r.status_code == 200:
    r.enconding = "utf-8"  # 設置返回內容的編碼
    # 獲取頁面內容
    print(r.content)

異常信息：

Traceback (most recent call last):
  File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 516, in urlopen
    body=body, headers=headers)
  File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 304, in _make_request
    self._validate_conn(conn)
  File "/usr/lib/python3/dist-packages/urllib3/connectionpool.py", line 724, in _validate_conn
    conn.connect()
  File "/usr/lib/python3/dist-packages/urllib3/connection.py", line 237, in connect
    ssl_version=resolved_ssl_version)
  File "/usr/lib/python3/dist-packages/urllib3/util/ssl_.py", line 123, in ssl_wrap_socket
    return context.wrap_socket(sock, server_hostname=server_hostname)
  File "/usr/lib/python3.4/ssl.py", line 364, in wrap_socket
    _context=self)
  File "/usr/lib/python3.4/ssl.py", line 577, in __init__
    self.do_handshake()
  File "/usr/lib/python3.4/ssl.py", line 804, in do_handshake
    self._sslobj.do_handshake()
ssl.SSLError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:600)

如何修改

requests.packages.urllib3.disable_warnings() 關閉告警信息
verify=False 不驗證certificate

修正後代碼

# -*- coding: utf-8 -*-
"""python3提取api連接並使用requests庫進行http代理"""
import requests
import random

requests.packages.urllib3.disable_warnings() # 關閉告警信息
page_url = "https://dev.kdlapi.com/testproxy"  # 要訪問的目標網頁
# API接口，返回格式爲json。快代理提供
api_url = "http://kps.kdlapi.com/api/getkps/?orderid=968347822535999&num=1&pt=1&format=json&sep=1"

# API接口返回的ip
proxy_ip = requests.get(api_url).json()['data']['proxy_list']

# 用戶名和密碼(私密代理/獨享代理)
proxies = {
    "http": "http://%(proxy)s/" % {'proxy': random.choice(proxy_ip)},
    "https": "https://%(proxy)s/" % {'proxy': random.choice(proxy_ip)}
}
print(proxies)
headers = {
    "Accept-Encoding": "Gzip",  # 使用gzip壓縮傳輸數據讓訪問更快
}
r = requests.get(page_url, headers=headers, verify=False) # 不驗證certificate
# 發送post請求
# r = requests.post("http://dev.kdlapi.com/testproxy", data={"info": "send post request"}, headers=headers)
print(r.status_code)  # 獲取Response的返回碼

if r.status_code == 200:
    r.enconding = "utf-8"  # 設置返回內容的編碼
    # 獲取頁面內容
    print(r.content)
    # print(r.text)

運行結果

不過我在win10環境下使用同樣的代碼不會引起ssl錯誤，目前懷疑是系統環境ssl的問題。不過最簡單粗暴的辦法就是不驗證，也是最快的方法。

進階學習

• 代理IP的使用