提交 903604f5 作者: 薛凌堃

获取企查查id

上级 c1e02a33
# -*- coding: utf-8 -*-
import time
from urllib.parse import quote
import requests
import json
import urllib3
from kafka import KafkaProducer
from base.BaseCore import BaseCore
baseCore = BaseCore()
log = baseCore.getLogger()
cnx_ = baseCore.cnx
cursor_ = baseCore.cursor
# 通过企业名称或信用代码获取企查查id
def find_id_by_name(start,token,social_code):
urllib3.disable_warnings()
qcc_key = social_code
t = str(int(time.time()) * 1000)
headers['Qcc-Timestamp'] = t
url = f"https://xcx.qcc.com/mp-weixin/forwardApp/v3/base/advancedSearch?token={token}&t={t}&pageIndex=1&needGroup=yes&insuredCntStart=&insuredCntEnd=&startDateBegin=&startDateEnd=&registCapiBegin=&registCapiEnd=&countyCode=&province=&sortField=&isSortAsc=&searchKey={quote(qcc_key)}&searchIndex=default&industryV3="
for lll in range(1, 6):
try:
resp_dict = requests.get(url=url, headers=headers, verify=False).json()
break
except:
print('重试')
time.sleep(5)
continue
time.sleep(2)
# {'status': 40101, 'message': '无效的sessionToken!'} {'status': 401, 'message': '您的账号访问超频,请升级小程序版本'}
if resp_dict['status'] == 40101:
KeyNo = False
log.info(f'====token失效====时间{baseCore.getTimeCost(start, time.time())}')
return KeyNo
if resp_dict['status'] == 401:
KeyNo = False
log.info(f'=======您的账号访问超频,请升级小程序版本=====时间{baseCore.getTimeCost(start, time.time())}')
return KeyNo
if resp_dict['status'] == 40102:
KeyNo = False
log.info(f'=======无效的session=====时间{baseCore.getTimeCost(start, time.time())}')
return KeyNo
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 = 'null'
else:
KeyNo = 'null'
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
# 判断字符串里是否含数字
def str_have_num(str_num):
panduan = False
for str_1 in str_num:
ppp = str_1.isdigit()
if ppp:
panduan = ppp
return panduan
# 通过企查查id获取企业官网
def info_by_id(com_id,com_name):
aa_dict_list = []
t = str(int(time.time()) * 1000)
headers['Qcc-Timestamp'] = t
url = "https://xcx.qcc.com/mp-weixin/forwardApp/v1/ent/detail?token={}&t={}&unique={}".format(token, t, com_id)
resp_dict = requests.get(url=url, headers=headers, verify=False).json()
time.sleep(2)
try:
result_dict = resp_dict['result']['Company']
except:
print(com_name + ":获取失败")
try:
WebSite = result_dict['companyExtendInfo']['WebSite']
except:
WebSite = None
if WebSite is None:
try:
WebSite = result_dict['ContactInfo']['WebSite'][0]['Url']
except:
WebSite = ''
print(com_name + ":爬取完成")
return WebSite
if __name__ == '__main__':
taskType = '基本信息/企查查/id'
headers = {
'Host': 'xcx.qcc.com',
'Connection': 'keep-alive',
'Qcc-Platform': 'mp-weixin',
'Qcc-Timestamp': '',
'Qcc-Version': '1.0.0',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36 MicroMessenger/7.0.9.501 NetType/WIFI MiniProgramEnv/Windows WindowsWechat',
'content-type': 'application/json',
'Referer': 'https://servicewechat.com/wx395200814fcd7599/166/page-frame.html',
'Accept-Encoding': 'gzip, deflate, br,'
}
name_list = []
#从redis里拿数据
while True:
# TODO:需要隔两个小时左右抓包修改,token从数据库中获得
token = baseCore.GetToken()
if token:
pass
else:
log.info('==========已无token==========')
time.sleep(30)
continue
start_time = time.time()
# 获取企业信息
social_code = baseCore.redicPullData('BaseInfoEnterprise:gnqy_socialCode')
# social_code = '91130800757548430L'
if social_code == '' or social_code is None:
time.sleep(20)
continue
if '搜索不到' in social_code:
continue
else:
pass
dic_info = baseCore.getInfomation(social_code)
log.info(f'----当前企业{social_code}--开始处理---')
count = dic_info[14]
com_name = dic_info[1]
social_code = dic_info[2]
#企查查id
company_id = dic_info[12]
#如果没有信用代码 就通过名字搜索 如果有信用代码 就通过信用代码
if company_id == '' or company_id == None:
if social_code:
company_id = find_id_by_name(start_time,token,social_code)
else:
company_id = find_id_by_name(start_time,token,com_name)
if company_id == 'null':
log.info('=====搜索不到该企业====')
#todo:搜不到的企业没有信用代码 传输不过去 生成一个信用代码
baseCore.rePutIntoR('BaseInfoEnterprise:gnqy_socialCode', social_code + ':搜索不到')
continue
if not company_id:
log.info(com_name + ":企业ID获取失败===重新放入redis")
baseCore.rePutIntoR('BaseInfoEnterprise:gnqy_socialCode',social_code)
baseCore.delete_token(token)
log.info('=====已重新放入redis,失效token已删除======')
time.sleep(20)
continue
else:
log.info(f'====={social_code}===={company_id}=====获取企业id成功=====')
# todo:写入数据库
updateSql = f"update EnterpriseInfo set QCCID = '{company_id}' where SocialCode = '{social_code}'"
cursor_.execute(updateSql)
cnx_.commit()
log.info(f'----企查查id已更新-----')
# 信息采集完成后将该企业的采集次数更新
runType = 'BaseInfoRunCount'
count += 1
baseCore.updateRun(social_code, runType, count)
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论