这篇文章主要介绍了python如何基于redis实现ip代理池,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友可以参考下
使用apscheduler库定时爬取ip,定时检测ip删除ip,做了2层检测,第一层爬取后放入redis——db0进行检测,成功的放入redis——db1再次进行检测,确保获取的代理ip的可用性
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
|
import requests, redis
import pandas
import random
from apscheduler.schedulers.blocking import BlockingScheduler
import datetime
import logging
db_conn = redis.ConnectionPool(host = "*.*.*.*" , port = 6379 , password = "123456" )
redis_conn_0 = redis.Redis(connection_pool = db_conn, max_connections = 10 ,db = 0 )
redis_conn_1 = redis.Redis(connection_pool = db_conn, max_connections = 10 ,db = 1 )
# 删除redis数据库里的ip
def remove_ip(ip,redis_conn):
redis_conn.zrem( "IP" , ip)
print ( "已删除 %s..." % ip)
# 获取redis数据库里一共有多少ip
def get_ip_num(redis_conn):
num = redis_conn.zcard( "IP" )
return num
# 获取ip的端口
def get_port(ip,redis_conn):
port = redis_conn.zscore( "IP" , ip)
port = str (port).replace( ".0" , "")
return port
# 添加ip和端口到数据库里
def add_ip(ip, port,redis_conn):
# nx: 不要更新已有的元素。总是添加新的元素,只有True,False
redis_conn.zadd( "IP" , {ip: port}, nx = 55 )
print ( "已添加 %s %s...ok" % (ip, port))
# 列出所有的ip
def get_all_ip(redis_conn):
all_ip = redis_conn.zrange( "IP" , 0 , - 1 )
return all_ip
# 随机获取一个ip
def get_random_ip(redis_conn):
end_num = get_ip_num(redis_conn)
num = random.randint( 0 , end_num)
random_ip = redis_conn.zrange( "IP" , num, num)
if not random_ip:
return " "," "
random_ip = str (random_ip[ 0 ]).replace( "b" , ' ').replace("' ", "")
port = get_port(random_ip,redis_conn)
return random_ip, port
# 获取代理ip
def spider_ip(x,redis_conn):
print (datetime.datetime.now().strftime( '%Y-%m-%d %H:%M:%S' ), x)
for p in range ( 1 , 20 ):
res = pandas.read_html( "http://www.89ip.cn/index_{}.html" . format (p))
# print(res)
# print(type(res[0]))
for i in range ( len (res[ 0 ])):
ip = res[ 0 ].iloc[i, 0 ]
port = res[ 0 ].iloc[i, 1 ]
print ( "ip" , ip)
print ( "port" , port)
add_ip( str (ip), str (port),redis_conn)
logging.basicConfig(level = logging.INFO,
format = '%(asctime)s %(filename)s[line:%(lineno)d] %(levelname)s %(message)s' ,
datefmt = '%Y-%m-%d %H:%M:%S' ,
filename = 'log1.txt' ,
filemode = 'a' )
def aps_detection_ip(x,redis_conn):
print (datetime.datetime.now().strftime( '%Y-%m-%d %H:%M:%S' ), x)
res = get_random_ip(redis_conn)
ip = res[ 0 ]
port = res[ 1 ]
try :
requests.get( "http://www.baidu.com" ,proxies = { 'https' : '{ip}:{port}' . format (ip = ip,port = port)})
print ( "可用" ,ip,port,res)
if redis_conn! = redis_conn_1:
add_ip( str (ip), str (port), redis_conn_1)
except Exception:
# ip错误失效就删除
remove_ip(ip,redis_conn)
scheduler = BlockingScheduler()
scheduler.add_job(func = aps_detection_ip, args = ( '检测循环任务0' ,redis_conn_0), trigger = 'interval' , seconds = 3 , id = 'aps_detection_ip_task0' ,max_instances = 10 )
scheduler.add_job(func = spider_ip, args = ( '获取循环任务0' ,redis_conn_0), trigger = 'interval' , seconds = 60 * 60 * 2 , id = 'spider_ip_task0' ,max_instances = 10 )
scheduler.add_job(func = aps_detection_ip, args = ( '检测循环任务1' ,redis_conn_1), trigger = 'interval' , seconds = 3 , id = 'aps_detection_ip_task1' ,max_instances = 10 )
scheduler._logger = logging
# scheduler.start()
if __name__ = = '__main__' :
# print(get_ip_num())
# spider_ip("获取循环任务")
scheduler.start()
# aps_detection_ip("检测循环任务")
|
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服务器之家。
原文链接:https://www.cnblogs.com/angelyan/p/12157374.html