爬取免费代理,并且解析代理是否可用 网址为:
http://www.ip3366.net/?stype=1&page=1
#1.确认爬取的地址
#2.发送地址请求
#3.数据解析
#4.数据保存
import requests
import parsel
import time
def check_ip(proxiles_list):
"""检测代理可用性"""
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36"
}
can_use = []
for proxies in proxiles_list:
try:
response = requests.get(url='https://www.baidu.com',headers=headers,
proxies=proxies,timeout=2)
if response.status_code == 200:
can_use.append(proxies)
except:
print('当前代理:',proxies,'请求超时,代理不可用')
else:
print('当前代理:',proxies,'****代理可用****')
return can_use
proxy_list = []
for page in range(1,11):
time.sleep(2)
#1.确认爬取的地址
url = f"http://www.ip3366.net/?stype=1&page={page}"
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36"}
#2.发送地址请求
response = requests.get(url=url,headers=headers)
response.encoding = response.apparent_encoding #自动识别响应体的编码
html_data = response.text
#print(html_data)
#3.数据解析 xpath 专门用来提取html数据
selector = parsel.Selector(html_data) #数据转换
trs = selector.xpath('//table[@class="table table-bordered table-striped"]/tbody/tr')
for tr in trs: #二次提取
ip = tr.xpath('./td[1]/text()').get() #ip
port = tr.xpath('./td[2]/text()').get() #端口
#print(ip,port)
ip_proxy = ip + ':' + port
proxies_dict = {
"http": "http://" + ip_proxy,
"https": "https://" + ip_proxy,
}
print('保存完成',proxies_dict)
proxy_list.append(proxies_dict)
print(proxy_list)
print('获取到的代理数量:',len(proxy_list))
print('***************************正在检测代理***************************')
can_use = check_ip(proxy_list)
print('可用的代理有:',can_use)
print('可用的代理数量:',len(can_use))