Python requests ip代理爬虫报错 HTTPSConnectionPool(host=‘xxxxx‘, port=443): Max retries exceed...

• 本人系统：macOS10.15.6 Catalina
• 场景：使用Python requests 包+ip代理池爬取网站数据
• 出现报错：HTTPSConnectionPool(host=‘xxxxx’, port=443): Max retries exceeded with url:xxxxxxxx (Caused by Ne…

具体情况下面这个博主已经基本提到了：

点击这里

但是依然出现这个报错。

import time
import random
import requests


USER_AGENTS = [
    "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
    "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
    "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
    "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10"
]

headers = {
   "User-Agent": ""
}
# 借助上面的USER-AGENT反爬
s = requests.session()
s.keep_alive = False
requests.adapters.DEFAULT_RETRIES = 10

url = "https://baike.baidu.com/item/人工智能/9180?fromtitle=AI&fromid=25417&fr=aladdin"
for i in range(10):
    proxys = {
    # news_ip是已经读取好的ip 就不放上面代码了
        "https": "http://"+ new_ips[i],
        "http": "http://" + new_ips[i]
    }
    headers['User-Agent'] = random.choice(USER_AGENTS)
    print(proxys)
    print(headers['User-Agent'])
    req = requests.get(url, headers=headers, verify = False, proxies = proxys, timeout = 20).content.decode('utf-8')
    print(req)
    
    time.sleep(5)

首先需要确认自己的的IP地址是否可行。这里参考
传送门
给出的方式，确认不是IP不可行的问题。

后来在知乎上看到有人在传入proxy给proxies的时候，

$将字典中的"https"和"http"全部大写了，尝试之后确实可行了$.

for i in range(10):
    proxys = {
        "HTTPS": "HTTP://"+ new_ips[i],
        "HTTP": "HTTP://" + new_ips[i]
        # 在这里全部大写了！
        
    }
    headers['User-Agent'] = random.choice(USER_AGENTS)
    print(proxys)
    print(headers['User-Agent'])
    req = requests.get(url, headers=headers, verify = False, proxies = proxys, timeout = 20).content.decode('utf-8')
    print(req)
    
    time.sleep(5)

记录一下今晚踩的几个雷：

• 注意字典proxy中，对于每个value无论key是HTTP还是HTTPS，都用HTTP开头！只有key用HTTPS！
• 如果requests想要爬取的网站是https:// ，那么一定一定需要在requests里加上verify = False这句话
• 这里是我用的免费ip代理池，勉强能用。下面把这个网站的爬取ip的代码放在这：

# 获取可用的IP代理
import re
import requests
header = {
#     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    "User-Agent" : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36" 
}

response = requests.get("http://www.66ip.cn/areaindex_11/1.html", headers = header)

encode_content = response.content.decode('gb18030', 'replace')

ips = re.findall("<td>(?:[0-9]{1,3}\.){3}[0-9]{1,3}</td><td>[0-9]{1,5}</td>", encode_content)
new_ips = []
# proxies = []

for i in ips:
#     print(i)
    new_ips.append(i.replace("</td><td>", ":"))
#     print(i)
                   
for i in range(len(new_ips)):
    new_ips[i] = new_ips[i].replace("<td>", "")
    new_ips[i] = new_ips[i].replace("</td>", "")
for i in new_ips:
    print(i)