You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
57 lines
1.6 KiB
57 lines
1.6 KiB
#!/usr/bin/python3
|
|
"""这是爬虫的主程序主程序
|
|
作者：陈进钱
|
|
日期：2023/11/03
|
|
"""
|
|
|
|
import pymysql
|
|
import datetime
|
|
import time
|
|
from apscheduler.schedulers.blocking import BlockingScheduler
|
|
from properties import Properties
|
|
from crawler import Crawler
|
|
import sys
|
|
|
|
print(
|
|
"""采购信息采集器 v1.0
|
|
===================================================================================
|
|
这个程序用于获取各大招投标网站的采购信息
|
|
version: 1.0
|
|
作者：陈进钱
|
|
日期：2023-11-04
|
|
===================================================================================""")
|
|
|
|
# 设置运行环境。如果当前是测试环境，则将is_test设置为true
|
|
is_test = False
|
|
print(sys.platform)
|
|
host = '116.62.210.190'
|
|
user = 'root'
|
|
password = 'Guoyan83086775'
|
|
if is_test:
|
|
database = 'guoyantest'
|
|
file_path = "./jdbc.test.properties"
|
|
else:
|
|
database = 'guoyan'
|
|
file_path = "./jdbc.properties"
|
|
|
|
# 打开数据连接
|
|
connect = pymysql.connect(host = host, user = user, password = password, database = database)
|
|
|
|
# 获取采购信息，并填写到数据库中
|
|
crawler = Crawler(connect)
|
|
#crawler.filter()
|
|
#print(crawler.is_hit('asdfjaslkf工程设计奥森囧(abc工程设计abc公司)'))
|
|
crawler.Crawl()
|
|
#crawler.CrawlPage_ygcg_nbcqjy_org(1, {"announcementCode": "21", "announcementType":"采购公告"})
|
|
#print(crawler.Check())
|
|
|
|
# 启动自动爬取任务
|
|
#def crawl_job_func():
|
|
# crawler.Crawl()
|
|
|
|
#sched = BlockingScheduler()
|
|
#sched.add_job(crawl_job_func, 'interval', hours=1, jitter=120)
|
|
#sched.start()
|
|
|
|
# 关闭数据库连接
|
|
connect.close()
|
|
|