linux启动简单python脚本
不点
阅读:619
2021-04-01 11:06:14
评论:0
1.python脚本
#!/usr/bin/python
# -*- coding: utf-8 -*-
import requests
import logging
import time
"""
weilai
200200813
解析商品详细页面
"""
# 第一步,创建一个logger
logger = logging.getLogger()
logger.setLevel(logging.INFO) # Log等级总开关
# 第二步,创建一个handler,用于写入日志文件
logfile = './logs/crawler_' + time.strftime('%Y-%m-%d', time.localtime()) + '.log'
fh = logging.FileHandler(logfile, mode='a', encoding="UTF-8")
fh.setLevel(logging.INFO) # 用于写到file的等级开关
# 第三步,再创建一个handler,用于输出到控制台
ch = logging.StreamHandler()
ch.setLevel(logging.INFO) # 输出到console的log等级的开关
# 第四步,定义handler的输出格式
formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')
fh.setFormatter(formatter)
ch.setFormatter(formatter)
# 第五步,将logger添加到handler里面
logger.addHandler(fh)
logger.addHandler(ch)
def getProductInfo(a):
# header = {
# 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36',
# 'token':'test-token-for-superuser'
# }
# url = 'http://123.xx.xx.xxx:8022/yszc-service/all/account/getUserInfo'
# requests.adapters.DEFAULT_RETRIES = 10
# proxies = {
# # 'http': '192.168.2.101:8118'
# }
# # url = 'https://www.aliexpress.com/item/Camera-Lens-Protection-Phone-Case-on-For-iPhone-11-Pro-Max-8-7-6-6s-Plus/4001039633127.html?scm=1007.26694.140541.0&scm_id=1007.26694.140541.0&scm-url=1007.26694.140541.0&pvid=8c8535a3-95ed-4271-a14b-7e17c4de32be&fromRankId=1766446&_t=fromRankId:1766446'
# req=requests.get(url,headers=header,proxies=proxies,timeout=5)
# # req=requests.get(url,headers=header,timeout=5)
# print(req.text)
header = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
URL1 = "https://www.aliexpress.com/item/32946430734.html?spm=a2g0o.ams_97944.topranking.1.64adUYFqUYFqk4&scm=1007.26694.140541.0&scm_id=1007.26694.140541.0&scm-url=1007.26694.140541.0&pvid=e473e5f3-b2da-4b93-bda5-694e9ef0658f&fromRankId=24800&_t=fromRankId:24800"
URL2 = "https://www.aliexpress.com/item/4001064703276.html?spm=a2g0o.ams_97944.topranking.1.33f9RDINRDINiC&scm=1007.26694.140541.0&scm_id=1007.26694.140541.0&scm-url=1007.26694.140541.0&pvid=d13fb323-04aa-4c76-ac9a-59fe52c7b409&fromRankId=1791960&_t=fromRankId:1791960"
URL3 = "https://www.aliexpress.com/item/32980948859.html?spm=a2g0o.ams_97944.topranking.7.33f9RDINRDINiC&scm=1007.26694.140541.0&scm_id=1007.26694.140541.0&scm-url=1007.26694.140541.0&pvid=d13fb323-04aa-4c76-ac9a-59fe52c7b409&fromRankId=1791960&_t=fromRankId:1791960"
URL4 = "https://www.aliexpress.com/item/4000585676274.html?spm=a2g0o.ams_97944.topranking.2.4fc2Mn6IMn6I0c&scm=1007.26694.140541.0&scm_id=1007.26694.140541.0&scm-url=1007.26694.140541.0&pvid=22b89b07-2ddc-44ca-a770-4c58087cf8a8&fromRankId=3159115&_t=fromRankId:3159115"
URL5 = "https://www.aliexpress.com/item/4000563401073.html?spm=a2g0o.ams_97944.topranking.1.4f303h5z3h5zNb&scm=1007.26694.140541.0&scm_id=1007.26694.140541.0&scm-url=1007.26694.140541.0&pvid=3cd7a77a-baef-4c29-8562-ab31718aacfc&fromRankId=3153027&_t=fromRankId:3153027"
URL6 = "https://www.aliexpress.com/item/32595636496.html?spm=a2g0o.ams_97944.topranking.8.4f303h5z3h5zNb&scm=1007.26694.140541.0&scm_id=1007.26694.140541.0&scm-url=1007.26694.140541.0&pvid=3cd7a77a-baef-4c29-8562-ab31718aacfc&fromRankId=3153027&_t=fromRankId:3153027"
URL7 = "https://www.aliexpress.com/item/32793775351.html?spm=a2g0o.ams_97944.topranking.1.35fdOvpaOvpa4l&scm=1007.26694.140541.0&scm_id=1007.26694.140541.0&scm-url=1007.26694.140541.0&pvid=f9ba2610-6dc6-4704-ac91-d0ae4a90eace&fromRankId=1793385&_t=fromRankId:1793385"
URL8 = "https://www.aliexpress.com/item/32868448064.html?spm=a2g0o.ams_97944.topranking.4.35fdOvpaOvpa4l&scm=1007.26694.140541.0&scm_id=1007.26694.140541.0&scm-url=1007.26694.140541.0&pvid=f9ba2610-6dc6-4704-ac91-d0ae4a90eace&fromRankId=1793385&_t=fromRankId:1793385"
URL9 = "https://www.aliexpress.com/item/4000776415795.html?spm=a2g0o.ams_97944.topranking.9.29c3O1DIO1DINB&scm=1007.26694.140541.0&scm_id=1007.26694.140541.0&scm-url=1007.26694.140541.0&pvid=ee4c55a9-51b8-41b6-be06-1586ee30ef91&fromRankId=1766078&_t=fromRankId:1766078"
URL10 = "https://www.aliexpress.com/item/4001110195225.html?spm=a2g0o.ams_97944.topranking.2.311b01fM01fMcg&scm=1007.26694.140541.0&scm_id=1007.26694.140541.0&scm-url=1007.26694.140541.0&pvid=4c84d8ee-7e5f-4ee1-8d44-8b05e5ed1166&fromRankId=2050963&_t=fromRankId:2050963"
requests.adapters.DEFAULT_RETRIES = 5
r = requests.get(URL1, headers=header)
a+=1
logger.info('a=='+str(a)+',status=='+str(r.status_code))
r = requests.get(URL2, headers=header)
a+=1
logger.info('a=='+str(a)+',status=='+str(r.status_code))
r = requests.get(URL3, headers=header)
a+=1
logger.info('a=='+str(a)+',status=='+str(r.status_code))
r = requests.get(URL4, headers=header)
a+=1
logger.info('a=='+str(a)+',status=='+str(r.status_code))
r = requests.get(URL5, headers=header)
a+=1
logger.info('a=='+str(a)+',status=='+str(r.status_code))
r = requests.get(URL6, headers=header)
a+=1
logger.info('a=='+str(a)+',status=='+str(r.status_code))
r = requests.get(URL7, headers=header)
a+=1
logger.info('a=='+str(a)+',status=='+str(r.status_code))
r = requests.get(URL8, headers=header)
a+=1
logger.info('a=='+str(a)+',status=='+str(r.status_code))
r = requests.get(URL9, headers=header)
a+=1
logger.info('a=='+str(a)+',status=='+str(r.status_code))
r = requests.get(URL10, headers=header)
a+=1
logger.info('a=='+str(a)+',status=='+str(r.status_code))
return a
if __name__ == '__main__':
a =0
while True:
a = getProductInfo(a)
2.启动脚本start.sh
nohup python testProxy.py >/dev/null 2>&1 &
3.停止脚本shutdown.sh
ps aux|grep testProxy.py|grep -v grep|awk '{print $2}'|xargs kill -9
4.重启脚本restart.sh
sh ./shutdown.sh
echo shutdown ...
sh ./start.sh
echo start ...
声明
1.本站遵循行业规范,任何转载的稿件都会明确标注作者和来源;2.本站的原创文章,请转载时务必注明文章作者和来源,不尊重原创的行为我们将追究责任;3.作者投稿可能会经我们编辑修改或补充。