def qyjcxx(self):
try:
a = Mysql.qiyexx_url(bh='1')[0] # 从复爬表
if a == None:
print('没有数据可以爬取')
time.sleep(10)
else:
self.qyid = a[0] #eid
self.z = a[2] #公司名字
qw = self.gx_qyid() #这个东西可以优化，在失败或者加载不出东西可以尝试更新，不用每次加载
self.qyid1 = qw #qyid
if a[7] == '1':
self.jichu12() # 基础信息的爬取
else:
print('基础信息爬取完毕')
if a[8] == '1':
self.qyzz() # 资质信息的爬取
else:
print('资质信息爬取完毕')
if a[9] == '1':
self.qy_user() # 人员信息的爬取
else:
print('人员信息爬取完毕')
# self.gcxmxx()
a = Mysql.qiyexx_url(bh='1')[0]
if a[7] == '0' and (a[8] == '0'
or a[8] == '404') and (a[9] == '0'
or a[9] == '404'):
Mysql.gxqy_fupa(cx_state='0', eid=self.qyid)
print('状态更新完毕')
except Exception as e:
print(e, 'jgfufh')
def gx_qyid(z, eid):
print('开始更新企业id')
qyurl = f'http://jzsc.mohurd.gov.cn/api/webApi/dataservice/query/comp/list?complexname={z}&pg=0&pgsz=15&total=0'
resp1 = requests.get(url=qyurl, headers=headers)
asddd2 = jd_nx(data=f'{resp1.text}')
if len(asddd2['data']['list']) == 0:
print('没有这个公司异常')
Mysql.gxqy_fupa(cx_state='3', eid=eid)
else:
qyid = asddd2['data']['list'][0]['QY_ID']
Mysql.update_qyid(qyurl=qyid, eid=eid) # 更新企业id
return qyid
def gx_qyid(self):
try:
print('开始更新企业id')
qyurl = f'http://jzsc.mohurd.gov.cn/api/webApi/dataservice/query/comp/list?complexname={self.z}&pg=0&pgsz=15&total=0'
resp1 = requests.get(url=qyurl,
headers=self.headers,
proxies=self.ipz(),
timeout=10)
ew = resp1.text
if str(ew).find('服务器繁忙，请稍后重试') != -1:
print('服务器繁忙，请稍后重试')
else:
asddd2 = self.jd_nx(data=f'{resp1.text}')
if len(asddd2['data']['list']) == 0:
print('没有这个公司异常')
Mysql.gxqy_fupa(cx_state='3', eid=self.qyid)
else:
qyid = asddd2['data']['list'][0]['QY_ID']
Mysql.update_qyid(qyurl=qyid, eid=self.qyid) #更新企业id
print('企业更新完毕')
return qyid
except Exception as e:
qq = str(e)
if qq.find("HTTPConnectionPool") != -1:
print('ip失效')
Mysql.dele_token(token=self.jichu)
print('token删除成功')
Mysql.token(token=self.jichu)
self.jichu = self.jichutoken()[0]
self.ip = {
"http": "http://" + self.jichutoken()[1],
"https": "https://" + self.jichutoken()[1]
}
else:
print('不存在')
print(e, '基础信息错误')