证监会公告脚本维护

comData/noticeReport/证监会-公告.py

-"""
-"""
-证监会公告采集，只能按照搜索企业来采，从上市库里拿企业数据，sys_enterprise_ipo_copy1
-craw_state:已采集过表示为True,未采集表示为0，拿取数据表示为ing，解析失败表示为400
-update_state：为1 表示需要更新，用来增量循环
-如何统计出来该报告采到了没有，dt_error库统计失败的信息
-"""
+import json
 import json
 import re
 import time
-
-import fitz
-import pymysql
 import requests
 from bs4 import BeautifulSoup
 from kafka import KafkaProducer
-from datetime import datetime
 from base import BaseCore
-# from fdfs_client.client import get_tracker_conf, Fdfs_client
 
 baseCore = BaseCore.BaseCore()
 log = baseCore.getLogger()
@@ -25,8 +14,6 @@ cursor = baseCore.cursor
 
 cnx_ = baseCore.cnx_
 cursor_ = baseCore.cursor_
-# tracker_conf = get_tracker_conf('./client.conf')
-# client = Fdfs_client(tracker_conf)
 
 taskType = '企业公告/证监会'
 
@@ -431,7 +418,7 @@ if __name__ == '__main__':
         com_name = dic_info[1]
         dic_parms = getUrl(code, url_parms, Catagory2_parms)
         dic_parms_ls = getUrl(code, url_parms_ls, Catagory2_parms_ls)
-        if len(dic_parms) > 0:
+        if dic_parms:
             start_time_cj = time.time()
             SpiderByZJH(dic_parms["url"], dic_parms["payload"], dic_info, start_time,num)
             log.info(f'{code}==========={short_name},{com_name},发行公告,耗时{baseCore.getTimeCost(start_time_cj, time.time())}')