python 爬虫 自建免费的代理IP池解决方案
文章目录
动态设置ip代理
- 爬取西刺免费代理IP
def crawl_ips():
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
for i in range(2000):
re = requests.get("http://www.xicidaili.com/nn/{0}".format(i), headers=headers)
selector = Selector(text=re.text)
all_trs = selector.css("#ip_list tr")
ip_list = []
for tr in all_trs[1:]: # 第零个tr是标题,所以从第一个开始取
speed_str = tr.css(".bar::attr(title)").extract()[0]
if speed_str:
speed = float(speed_str.split("秒")[0])
all_texts = tr.css("td::text").extract()
ip = all_texts[0]
port = all_texts[1]
proxy_type = all_texts[5]
ip_list.append((ip, port, proxy_type, speed))
for ip_info in ip_list:
cursor.execute(
"insert proxy_ip(ip, port, speed, proxy_type) VALUES('{0}', '{1}', {2}, 'HTTP')".format(
ip_info[0], ip_info[1], ip_info[3]
)
)
conn.commit()
- 从数据库中删除无效的ip
def delete_ip(self, ip):
delete_sql = """
delete from proxy_ip where ip='{0}'
""".format(ip)
cursor.execute(delete_sql)
conn.commit()
return True
- 判断ip是否可用
def judge_ip(self, ip, port):
http_url = "http://www.baidu.com"
proxy_url = "http://{0}:{1}".format(ip, port)
try:
proxy_dict = {
"http":proxy_url,
}
response = requests.get(http_url, proxies=proxy_dict)
except Exception as e:
print ("invalid ip and port")
self.delete_ip(ip)
return False
else:
code = response.status_code
if code >= 200 and code < 300:
print ("effective ip")
return True
else:
print ("invalid ip and port")
self.delete_ip(ip)
return False
- 从数据库中随机获取一个可用的ip
def get_random_ip(self):
#从数据库中随机获取一个可用的ip
random_sql = """
SELECT ip, port FROM proxy_ip
ORDER BY RAND()
LIMIT 1
"""
result = cursor.execute(random_sql)
for ip_info in cursor.fetchall(): # cursor.fetchall() 返回值是一个元组
ip = ip_info[0]
port = ip_info[1]
judge_re = self.judge_ip(ip, port)
if judge_re:
return "http://{0}:{1}".format(ip, port)
else:
return self.get_random_ip()
- 设置代理IP
class RandomProxyMiddleware(object):
#动态设置ip代理
def process_request(self, request, spider):
get_ip = GetIP()
request.meta["proxy"] = get_ip.get_random_ip()