Python爬虫使用代理IP的实现

from urllib.error import URLError
import urllib.request
from urllib.request import ProxyHandler, build_opener

# 获取IP
ip_response = urllib.request.urlopen("http://localhost:5555/random")
ip = ip_response.read().decode('utf-8')

proxy_handler = ProxyHandler({
  'http': 'http://' + ip,
  'https': 'https://' + ip
})
opener = build_opener(proxy_handler)
try:
  response = opener.open('http://httpbin.org/get')
  print(response.read().decode('utf-8'))
except URLError as e:
  print(e.reason)

{
 "args": {},
 "headers": {
  "Accept-Encoding": "identity",
  "Host": "httpbin.org",
  "User-Agent": "Python-urllib/3.7"
 },
 "origin": "108.61.201.231, 108.61.201.231",
 "url": "https://httpbin.org/get"
} 

import requests

# 获取IP
ip_response = requests.get("http://localhost:5555/random")
ip = ip_response.text

proxies = {
  'http': 'http://' + ip,
  'https': 'https://' + ip,
}
try:
  response = requests.get('http://httpbin.org/get', proxies=proxies)
  print(response.text)
except requests.exceptions.ConnectionError as e:
  print('Error', e.args)

{
 "args": {},
 "headers": {
  "Accept": "*/*",
  "Accept-Encoding": "gzip, deflate",
  "Host": "httpbin.org",
  "User-Agent": "python-requests/2.21.0"
 },
 "origin": "47.90.28.54, 47.90.28.54",
 "url": "https://httpbin.org/get"
}

import requests
from selenium import webdriver
import time

# 借助requests库获取IP
ip_response = requests.get("http://localhost:5555/random")
ip = ip_response.text

chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--proxy-server=http://' + ip)
browser = webdriver.Chrome(chrome_options=chrome_options)
browser.get('http://httpbin.org/get')
time.sleep(5)