樊九九：简单python爬虫，爬取西刺高密代理

from urllib import request
import random 
import re	

def get_html(url):#获取西刺网站的html源码
	header = {
		'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
	}
	req = request.Request(url, headers = header)
	response = request.urlopen(req)
	html = response.read().decode()
	
	return html

def get_proxy(html):#利用re，找出每个代理的ip 和端口，存入列表
	firstlist = re.findall(r'<tr class=.*?>(.*?)</tr>',html,re.S)
	print(len(firstlist))
	for i in firstlist:
		ip=re.findall(r'\d+\.\d+\.\d+\.\d+',i,re.S)[0]
		port= re.findall(r'<td>(\d+)</td>',i,re.S)[0]
		proxy = '{}:{}'.format(ip,port)
		proxy_list.append(proxy)
	return proxy_list