11/23

base/RedisPPData.py

@@ -122,6 +122,33 @@ def NoticeEnterprise_task():
         print('定时采集异常', e)
         pass
 
+# 东方财富网公告 美股 港股
+def NoticeDF():
+    cnx, cursor = connectSql()
+    # 获取美股企业
+    mg_query = "SELECT a.SocialCode From EnterpriseInfo a ,EnterpriseType b WHERE a.SocialCode = b.SocialCode AND b.type=2 AND a.Place=0 AND SecuritiesCode is not null AND SecuritiesCode not LIKE '%.%'"
+    cursor.execute(mg_query)
+    cnx.commit()
+    mg_result = cursor.fetchall()
+    mg_social_list = [item[0] for item in mg_result]
+    print('=======')
+    for item in mg_social_list:
+        r.rpush('NoticeEnterprise:mgqy_socialCode_add', item)
+
+    # 获取港股企业
+    gg_query = "SELECT a.SocialCode From EnterpriseInfo a ,EnterpriseType b WHERE a.SocialCode = b.SocialCode AND b.type=2 And SecuritiesCode like '%.HK'"
+    cursor.execute(gg_query)
+    cnx.commit()
+    gg_result = cursor.fetchall()
+    gg_social_list = [item[0] for item in gg_result]
+    print('=======')
+    for item in gg_social_list:
+        r.rpush('NoticeEnterprise:ggqy_socialCode_add', item)
+
+    closeSql(cnx, cursor)
+
+
+
 #企业基本信息
 def BaseInfoEnterprise():
     cnx,cursor = connectSql()
@@ -564,7 +591,8 @@ if __name__ == "__main__":
     # kegaishifan()
     # shuangbaiqiye()
     # zhuangjingtexind()
-    NoticeEnterprise()
+    # NoticeEnterprise()
+    NoticeDF()
     # AnnualEnterpriseIPO()
     # AnnualEnterprise()
     # BaseInfoEnterprise()

comData/Tyc/CorePerson2.py

@@ -27,14 +27,15 @@ requests.adapters.DEFAULT_RETRIES = 5
 def doJob():
     while True:
         # 根据从Redis中拿到的社会信用代码,在数据库中获取对应基本信息
-        social_code = baseCore.redicPullData('CorPersonEnterprise:gnqy_socialCode')
+        # social_code = baseCore.redicPullData('CorPersonEnterprise:gnqy_socialCode')
         # 判断 如果Redis中已经没有数据，则等待
-        # social_code = '92640302MA76KNNT0D'
-        if 'ZZSN' in social_code:
-            continue
+        social_code = '91510000207312079C'
+
         if social_code == None:
             time.sleep(20)
             continue
+        if 'ZZSN' in social_code:
+            continue
         start = time.time()
         try:
             # data = baseCore.getInfomation(social_code)

comData/annualReport1023/updateyear.py

+# -*- coding: utf-8 -*-
+import json
+import re
+import threading
+import time
+import uuid
+
+import fitz
+import redis
+import requests
+from bs4 import BeautifulSoup
+from obs import ObsClient
+from retry import retry
+from elasticsearch import Elasticsearch
+from base import BaseCore
+
+baseCore = BaseCore.BaseCore()
+log = baseCore.getLogger()
+baseCore = BaseCore.BaseCore()
+
+cnx_ = baseCore.cnx_
+cursor_ = cnx_.cursor()
+
+lock = threading.Lock()
+pathType_ = 'QYResearchReport/'
+taskType = '企业研报/东方财富网'
+
+pool = redis.ConnectionPool(host="114.115.236.206", port=6379, password='clbzzsn', db=6)
+
+obsClient = ObsClient(
+        access_key_id='VEHN7D0TJ9316H8AHCAV',  # 你的华为云的ak码
+        secret_access_key='heR353lvSWVPNU8pe2QxDtd8GDsO5L6PGH5eUoQY',  # 你的华为云的sk
+        server='https://obs.cn-north-1.myhuaweicloud.com'  # 你的桶的地址
+    )
+
+class EsMethod(object):
+
+    def __init__(self):
+        # 创建Elasticsearch对象，并提供账号信息
+        self.es = Elasticsearch(['http://114.116.19.92:9700'], http_auth=('elastic', 'zzsn9988'), timeout=300)
+        self.index_name = 'researchreportdata'
+
+    def queryatt(self,index_name,id):
+       body = {
+               "query": {
+                "match": {
+                       "id": id
+                   }
+               }
+
+       }
+
+       filter_path = ['hits.hits._id',
+                      'hits.total.value',
+                      'hits.hits._source.title',
+                      'hits.hits._source.origin',
+                      'hits.hits._source.sourceAddress',
+                      'hits.hits._source.createDate',
+                      'hits.hits._source.publishDate',
+                      ]  # 字段2
+       result = self.es.search(index=index_name
+                               , doc_type='_doc'
+                               , filter_path=filter_path
+                               , body=body)
+       # log.info(result)
+       return result
+
+    def updateaunn(self,index_name,id,u_publishDate):
+        body = {
+            'doc': {
+                'publishDate':u_publishDate
+            }
+        }
+        result = self.es.update(index=index_name
+                                ,id=id
+                                ,body=body)
+        log.info('更新结果:%s' % result)
+
+
+if __name__ == "__main__":
+    esMethod = EsMethod()
+    redis_conn = redis.Redis(connection_pool=pool)
+    while True:
+        id_ = redis_conn.lpop('YanBao:up')
+
+        # id = "23112104300"
+        if id:
+            pass
+        else:
+            log.info('已无数据')
+        id = id_.decode()
+        result_ = esMethod.queryatt(index_name=esMethod.index_name, id=id)
+        result = result_['hits']['hits'][0]
+        num = 0
+        publishDate = result['_source']['publishDate']
+        u_publishDate = '2023-08-31' #+ publishDate.split('T')[1]
+        esMethod.updateaunn(esMethod.index_name, str(id), u_publishDate)