2023/8/12

base/BaseCore.py

@@ -364,14 +364,14 @@ class BaseCore:
         return str
 
     # 繁体字转简体字
-    def hant_2_hans(hant_str: str):
+    def hant_2_hans(self,hant_str: str):
         '''
         Function: 将 hant_str 由繁体转化为简体
         '''
         return zhconv.convert(hant_str, 'zh-hans')
 
     # 判断字符串里是否含数字
-    def str_have_num(str_num):
+    def str_have_num(self,str_num):
         panduan = False
 
         for str_1 in str_num:
@@ -463,6 +463,7 @@ class BaseCore:
         # token = '67ec7402166df1da84ae83c4b95cefc0'  # 需要隔两个小时左右抓包修改
         self.cursor.execute(query)
         token = self.cursor.fetchone()[0]
+        return token
 
     #检测语言
     def detect_language(self, text):

comData/BaseInfo_qcc/getQccId.py

@@ -5,8 +5,10 @@ import time
 from urllib.parse import quote
 import requests
 import urllib3
+from base.BaseCore import BaseCore
 
-
+baseCore = BaseCore()
+log = baseCore.getLogger()
 headers = {
         'Host': 'xcx.qcc.com',
         'Connection': 'keep-alive',
@@ -19,7 +21,7 @@ headers = {
         'Accept-Encoding': 'gzip, deflate, br,'
     }
 # 通过企业名称或信用代码获取企查查id
-def find_id_by_name(name):
+def find_id_by_name(start,token,name):
     urllib3.disable_warnings()
 
     qcc_key = name
@@ -35,14 +37,19 @@ def find_id_by_name(name):
             time.sleep(5)
             continue
     time.sleep(2)
-    if resp_dict['result']['Result']:
-        result_dict = resp_dict['result']['Result'][0]
-        KeyNo = result_dict['KeyNo']
-        Name = result_dict['Name'].replace('<em>', '').replace('</em>', '').strip()
-        if Name == '':
+    try:
+        if resp_dict['result']['Result']:
+            result_dict = resp_dict['result']['Result'][0]
+            KeyNo = result_dict['KeyNo']
+            Name = result_dict['Name'].replace('<em>', '').replace('</em>', '').strip()
+            if Name == '':
+                KeyNo = ''
+        else:
             KeyNo = ''
-    else:
-        KeyNo = ''
+    except:
+        KeyNo = False
+        log.info(f'====token失效====时间{baseCore.getTimeCost(start,time.time())}')
+        return KeyNo
 
     print("{}，企业代码为:{}".format(qcc_key, KeyNo))
     return KeyNo
\ No newline at end of file

comData/annualReport_ZJH/证监会-年报.py

-
+
@@ -123,6 +123,8 @@ def SpiderByZJH(url, payload, dic_info, num, start_time):
             report_type = td_list[4].text.strip()
             # print(report_type)
             if report_type == '年报':
+                if '摘要' in name_pdf:
+                    continue
                 # 年份还从pdf名称里抽取
                 try:
                     year = re.findall('\d{4}\s*年', name_pdf)[0].replace('年', '')

comData/tcyQydt/test.py

@@ -5,26 +5,19 @@ import langid
 
 from base.BaseCore import BaseCore
 baseCore =BaseCore()
+import pymysql
 # print(baseCore.detect_language("是对jhjjhjhhjjhjhjh的浮点数"))
+# cnx_ = baseCore.cnx
+# cursor_ = baseCore.cursor
+cnx_ = pymysql.connect(host='114.115.159.144', user='root', password='zzsn9988', db='caiji',
+                                   charset='utf8mb4')
+cursor_ = cnx_.cursor()
+updateBeginSql = f"update Tfbs set state3=%s where col3=%s "
+# print(updateBeginSql)
+cursor_.execute(updateBeginSql,(200,'91350000158142711F'))
+cnx_.commit()
 
 
-#
-# def detect_language(text):
-#     # 使用langid.py判断文本的语言
-#     lang, confidence = langid.classify(text)
-#     print(lang,confidence)
-#     return lang
-# detect_language("123")
 
-from textblob import TextBlob
-
-def detect_language(text):
-    blob = TextBlob(text)
-    lang = blob.detect_language()
-    return lang
-
-text = "Hello, how are you?"
-language = detect_language(text)
-print(language)
 
 

comData/weixin_solo/oneWeixin.py

 '''
-补充智库动态没有公众号信息数据的公众号
-从库中读取信息，根据域名找到属于公众号的链接，
-设置time.sleep 等待到每天执行
+记录一天能采多少公众号
 '''
 
-
-import requests, time, re, datetime, random, json, pymysql, redis
+import requests, time, random, json, pymysql, redis
 import pandas as pd
 import urllib3
 from bs4 import BeautifulSoup
@@ -216,7 +213,7 @@ if __name__=="__main__":
     # browser2.get(url)
     # browser3.get(url)
     # 可改动
-    time.sleep(50)
+    time.sleep(30)
     num_b = 0
     browser_run = list_b[0]
     log.info('======刷新浏览器=====')
@@ -313,13 +310,13 @@ if __name__=="__main__":
             count = 0
             try:
                 ip = get_proxy()[random.randint(0, 3)]
-                json_search = s.get(url_search, headers=baseCore.getRandomUserAgent(), proxies=ip,
+                json_search = s.get(url_search, headers=headers, proxies=ip,
                                     verify=False).json()  # , proxies=ip, verify=False
                 time.sleep(2)
                 break
             except:
                 log.info(f'===公众号{origin}请求失败！当前时间：{baseCore.getNowTime(1)}===')
-                error_text = str(json_search)
+                # error_text = str(json_search)
                 json_search = ''
                 aa = time.sleep(600)
                 log.info(f'======等待时间{aa}=======')