Merge remote-tracking branch 'origin/master'

base/RedisPPData.py

@@ -449,6 +449,21 @@ def omeng():
         # r.rpush('gnOMEnterprise_socialcode:Notice', item)
     closeSql(cnx, cursor)
 
+#单项冠军
+def danxiangguanjun():
+    pass
+
+#科改示范
+def kegaishifan():
+    pass
+
+#双百企业
+def shuangbaiqiye():
+    pass
+
+#专精特新
+def zhuangjingtexind():
+    pass
 
 if __name__ == "__main__":
     start = time.time()

comData/Tyc/CorePerson.py

@@ -46,8 +46,8 @@ def doJob():
             if tycid == None or tycid == '':
                 try:
                     retData = getTycIdByXYDM(xydm)
-                    if retData:
-                        tycid = retData['id']
+                    if retData['state']:
+                        tycid = retData['tycData']['id']
                         # todo:写入数据库
                         updateSql = f"update EnterpriseInfo set TYCID = '{tycid}' where SocialCode = '{xydm}'"
                         cursor_.execute(updateSql)

comData/annualReport_US/annualreportUS.py

@@ -101,8 +101,8 @@ def spider(com_name,cik,up_okCount):
     #解析页面
     for nnn in range(0,4):
         try:
-            req = requests.get(url=url_json,headers=header,proxies=ip_dic,verify=False,timeout=30)
-            # req = requests.get(url=url_json, headers=header, verify=False, timeout=30)
+            # req = requests.get(url=url_json,headers=header,proxies=ip_dic,verify=False,timeout=30)
+            req = requests.get(url=url_json, headers=header, verify=False, timeout=30)
             break
         except:
             time.sleep(2)

comData/dfcfwGpdm/NQenterprise/新三板--公告.py

-
+
@@ -41,6 +41,14 @@ type_map = {
     '9605':'公司公告',
     '9533':'公司公告',
 }
+type_id_map = {
+    '公司公告': '8',
+    '股转公告': '9',
+    '挂牌审核': '10',
+    '自律监管措施': '11',
+    '问询函': '12',
+    '纪律处分': '13'
+}
 
 def secrchATT(item_id, name, type_id):
     sel_sql = '''select id from clb_sys_attachment where item_id = %s and name = %s and type_id=%s '''
@@ -157,7 +165,7 @@ def InsterInto(short_name, social_code, pdf_url):
         return insert
 
 
-def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_name,num):
+def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_name,num,kfkid):
     #上传至文件服务器
     retData = baseCore.upLoadToServe(pdf_url,8,social_code)
     #附件插入att数据库
@@ -192,7 +200,7 @@ def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_na
         'sourceAddress': pdf_url,  # 原文链接
         'summary': '',
         'title': pdf_name,
-        'type': 3,
+        'type': kfkid,
         'socialCreditCode': social_code,
         'year': year
     }
@@ -241,6 +249,7 @@ def SpiderByZJH(url, dic_info, start_time,num):  # dic_info 数据库中获取
             pdf_url = 'https://www.neeq.com.cn' + rp['destFilePath']
             name_pdf = rp['disclosureTitle']
             rp_type = type_map[rp['disclosureType']]
+            kfkid = type_id_map[rp_type]
             publishDate = rp['publishDate']
             year = publishDate[:4]
             # 数据入库
@@ -250,7 +259,7 @@ def SpiderByZJH(url, dic_info, start_time,num):  # dic_info 数据库中获取
                 #     okCount = okCount + 1
                 # 解析PDF内容，先获取PDF链接 下载 解析成功，解析失败 ，传输成功，传输失败
                 log.info(f'======={short_name}===========插入公告库成功')
-                result = GetContent(pdf_url, name_pdf, social_code, year, publishDate, start_time, com_name, num)
+                result = GetContent(pdf_url, name_pdf, social_code, year, publishDate, start_time, com_name, num,kfkid)
 
                 if result:
                     # 公告信息列表
@@ -300,17 +309,18 @@ if __name__ == '__main__':
     while True:
         start_time = time.time()
         # # 获取企业信息
-        # # social_code = baseCore.redicPullData('NoticeEnterpriseFbs:gnqy_socialCode')
-        social_code = '9110000071092841XX'
-        com_code = '430045'
-        short_name = '超毅网络'
+        social_code = baseCore.redicPullData('NQEnterprise:nq_finance')
+        # social_code = '9110000071092841XX'
+        # com_code = '430045'
+        # short_name = '超毅网络'
         dic_info = {}
         # # 判断 如果Redis中已经没有数据，则等待
-        # if social_code == None:
-        #     time.sleep(20)
-        #     continue
-        # dic_info = baseCore.getInfomation(social_code)
-        # count = dic_info[16]
+        if social_code == None:
+            time.sleep(20)
+            continue
+        data = baseCore.getInfomation(social_code)
+        com_code = data[3]
+        short_name = data[4]
         url = 'https://www.neeq.com.cn/disclosureInfoController/productInfoResult.do'
         #翻页 page 0~ 25  totalPages
 

comData/weixin_solo/get_tokenCookies.py

@@ -56,7 +56,7 @@ if __name__=="__main__":
     url = "https://mp.weixin.qq.com/"
     browser.get(url)
     # 可改动
-    time.sleep(60)
+    time.sleep(20)
 
     s = requests.session()
     #获取到token和cookies