import json
import re
from utils import get_page
from pyquery import PyQuery as pq

# 元类
class ProxyMetaclass(type):
 def __new__(cls, name, bases, attrs):
  count = 0
  attrs['__CrawlFunc__'] = []
  for k, v in attrs.items():
   if 'crawl_' in k:
    attrs['__CrawlFunc__'].append(k)
    count += 1
  attrs['__CrawlFuncCount__'] = count
  return type.__new__(cls, name, bases, attrs)

class Crawler(object, metaclass=ProxyMetaclass):
 def get_proxies(self, callback):
  proxies = []
  for proxy in eval("self.{}()".format(callback)):
   print('成功获取到代理', proxy)
   proxies.append(proxy)
  return proxies

 def crawl_daili66(self, page_count=4):
  start_url = 'http://www.66ip.cn/{}.html'
  urls = [start_url.format(page) for page in range(1, page_count + 1)]
  for url in urls:
   print('Crawling', url)
   html = get_page(url)
   if html:
    doc = pq(html)
    trs = doc('.containerbox table tr:gt(0)').items()
    for tr in trs:
     ip = tr.find('td:nth-child(1)').text()
     port = tr.find('td:nth-child(2)').text()
     yield ':'.join([ip, port])

 def crawl_xicidaili(self):
  for i in range(1, 3):
   start_url = 'http://www.xicidaili.com/nn/{}'.format(i)
   headers = {
    'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'Host':'www.xicidaili.com',
    'Referer':'http://www.xicidaili.com/nn/3',
    'Upgrade-Insecure-Requests':'1',
   }
   html = get_page(start_url, options=headers)
   if html:
    find_trs = re.compile('<tr class.*?>(.*"IP">(.*"PORT">(.*"htmlcode">

import requests
from requests.exceptions import ConnectionError

base_headers = {
 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36',
 'Accept-Encoding': 'gzip, deflate, sdch',
 'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7'
}

def get_page(url, options={}):

 headers = dict(base_headers, **options)
 print('正在抓取', url)
 try:
  response = requests.get(url, headers=headers)
  print('抓取成功', url, response.status_code)
  if response.status_code == 200:
   return response.text
 except ConnectionError:
  print('抓取失败', url)
  return None


抓取网页内容的方法，访问链接成功后返回整个网页 HTML 内容，便于后续对网页具体内容的提取。封装成一个方法，让上面的 crawler 在抓取各个网站时调用
进行抓取


getter.py


from crawler import Crawler
from setting import *
import sys

class Getter():
 def __init__(self):
  self.crawler = Crawler()
 
 def run(self):
  print('获取器开始执行')
  for callback_label in range(self.crawler.__CrawlFuncCount__):
   callback = self.crawler.__CrawlFunc__[callback_label]
   # 获取代理
   all_ip = self.crawler.get_proxies(callback)

if __name__ == '__main__':
 get = Getter()
 get.run()


运行结果：

网站上的免费 IP 就被成功抓取下来了，至于能不能用，就有待验证了
整个过程其实就是一个普通的爬虫，而且没什么反爬措施，能到用代理 IP 的地步，代码里面的访问、抓取部分的细节应该都看得懂


以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。