将普通程序加入代理池功能，如有指导~感谢

L-茉遇

描述：想要一个普通的豆瓣抓取代码（抓什么的都行）然后把这个代理功能加进入。
问题：现在就是大概可以看懂代理池这个代码，想把这个功能用到真正抓取的功能里边
老师上课的代码：

1. # https://blog.csdn.net/qq_40418612/article/details/82595140
   
2. import random, requests, os
   
3. from selenium import webdriver
   
4. from lxml import etree
   
5. import time
   
6. def req(url):
   
7.     # 设置多个 user-agent
   
8.     User_Agent = random.choice([
   
9.         "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
   
10.         "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
    
11.         "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
    
12.         "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
    
13.         "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
    
14.         "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
    
15.         "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
    
16.         "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
    
17.         "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
    
18.         "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
    
19.         "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
    
20.         "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
    
21.         "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
    
22.         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
    
23.         "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
    
24.         "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
    
25.         'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
    
26.     ])
    
27.     # 从https://www.zdaye.com爬取代理，并存储到http_list.txt和https_list.txt的文件中
    
28.     l = os.listdir(os.getcwd())
    
29.     if "http_list.txt" not in l:
    
30.         proxy_url = 'https://www.zdaye.com/dayProxy/ip/324679.html'
    
31.         driver = webdriver.Chrome()
    
32.         driver.get(proxy_url)
    
33.         time.sleep(2)
    
34.         t = driver.page_source
    
35.         # driver.quit()
    
36. 
    
37.         html = etree.HTML(t)
    
38.         print(t)
    
39.         http_list = []
    
40.         https_list = []
    
41.         wholeProxys = html.xpath("//*[@class='cont']/text()")
    
42.         # print(len(wholeProxys))
    
43.         for each in wholeProxys:
    
44.             wholeProxy=each[:each.find('#')]  #通过索引访问字符串；下同。
    
45.             ip=wholeProxy[:wholeProxy.find(':')]
    
46.             port=wholeProxy[wholeProxy.find(':')+1:wholeProxy.find('@')]
    
47.             protocol=wholeProxy[wholeProxy.find('@')+1:]
    
48.             # print(wholeProxy)
    
49.             print(ip,'--',port,'--',protocol)
    
50. 
    
51.             if protocol == "HTTP":
    
52.                 http_list.append(protocol + r"://" + ip + ":" + port)
    
53.             if protocol == "HTTPS":
    
54.                 https_list.append(protocol + r"://" + ip + ":" + port)
    
55.         with open("http_list.txt", "w") as p:
    
56.             p.write(str(http_list))
    
57.         with open("https_list.txt", "w") as p:
    
58.             p.write(str(https_list))
    
59.     else:
    
60.         with open("http_list.txt") as f:
    
61.             http_list = eval(f.read())
    
62.         with open("https_list.txt") as f:
    
63.             https_list = eval(f.read())
    
64. 
    
65.     try:
    
66.         proxies = {"http": random.choice(http_list), "https": random.choice(https_list)}
    
67.         headers = {"User-Agent": User_Agent, "cookie": revert_cookie(cookie)}
    
68.         r = requests.get(url, proxies=proxies, headers=headers)
    
69.         print(r.status_code)
    
70.         return r.text
    
71.     except:
    
72.         print("当前所使用的代理已失效，更换代理重试中...")
    
73.         while True:
    
74.             for n in range(100):
    
75.                 # proxies = {"http": random.choice(list(http_list)), "https": random.choice(list(https_list))}
    
76.                 proxies = {"http": random.choice(list(http_list))}  #暂不处理https
    
77.                 headers = {"User-Agent": User_Agent, }
    
78.                 r = requests.get(url, proxies=proxies, headers=headers)
    
79.                 if r.status_code == 200:
    
80.                     print("更换代理成功，已获取到网页源码；当前所用代理为：",proxies)
    
81.                     print(r.text)
    
82.                     return r
    
83.                 else:
    
84.                     continue
    
85.             print('在代理池中更换了n个代理，但还是无法连接服务器...')
    
86. 
    
87. 
    
88. if __name__ == '__main__':
    
89.     url = "http://httpbin.org/ip"
    
90.     print(req(url))

复制代码

没找到悬赏在哪...

wp231957

免费代理就不要玩了