Skip to content

Z
zzsn_spider
提交 637feb1a 作者: LiuLiYuan
操作

Merge remote-tracking branch 'origin/master'

上级 03fc29ea 903604f5
正在显示 包含 3395 行增加 和 232 行删除
base/BaseCore.py
...@@ -556,9 +556,18 @@ class BaseCore: ...@@ -556,9 +556,18 @@ class BaseCore:
self.cursor.execute(query) self.cursor.execute(query)
token_list = self.cursor.fetchall() token_list = self.cursor.fetchall()
self.cnx.commit() self.cnx.commit()
token = token_list[random.randint(0, len(token_list) - 1)][0] try:
token = token_list[random.randint(0, len(token_list) - 1)][0]
except:
token = ''
return token return token
# 删除失效的token
def delete_token(self, token):
deletesql = f"delete from QCC_token where token='{token}' "
self.cursor.execute(deletesql)
self.cnx.commit()
# 获取天眼查token # 获取天眼查token
def GetTYCToken(self): def GetTYCToken(self):
query = 'select token from TYC_token' query = 'select token from TYC_token'
......
base/RedisPPData.py
This source diff could not be displayed because it is too large. You can view the blob instead.
comData/BaseInfo_qcc/base_info.py
...@@ -9,7 +9,8 @@ import json ...@@ -9,7 +9,8 @@ import json
from kafka import KafkaProducer from kafka import KafkaProducer
from base.BaseCore import BaseCore from base.BaseCore import BaseCore
from getQccId import find_id_by_name from getQccId import find_id_by_name
import urllib3
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
baseCore = BaseCore() baseCore = BaseCore()
cnx_ = baseCore.cnx cnx_ = baseCore.cnx
cursor_ = baseCore.cursor cursor_ = baseCore.cursor
...@@ -323,20 +324,28 @@ if __name__ == '__main__': ...@@ -323,20 +324,28 @@ if __name__ == '__main__':
'Accept-Encoding': 'gzip, deflate, br,' 'Accept-Encoding': 'gzip, deflate, br,'
} }
name_list = []
#从redis里拿数据 #从redis里拿数据
while True: while True:
# TODO:需要隔两个小时左右抓包修改,token从数据库中获得 # 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() token = baseCore.GetToken()
list_weicha = [] if token:
list_all_info = [] pass
name_list = [] else:
log.info('==========已无token==========')
time.sleep(30)
continue
start_time = time.time() start_time = time.time()
# 获取企业信息 # 获取企业信息
# social_code = baseCore.redicPullData('BaseInfoEnterprise:gnqy_socialCode') # social_code = baseCore.redicPullData('BaseInfoEnterprise:gnqy_socialCode')
social_code = '91330000734530895W' social_code = '91130800757548430L'
if social_code == '': if social_code == '' or social_code is None:
time.sleep(20) time.sleep(20)
continue continue
if '搜索不到' in social_code:
continue
else:
pass
dic_info = baseCore.getInfomation(social_code) dic_info = baseCore.getInfomation(social_code)
log.info(f'----当前企业{social_code}--开始处理---') log.info(f'----当前企业{social_code}--开始处理---')
count = dic_info[14] count = dic_info[14]
...@@ -350,10 +359,16 @@ if __name__ == '__main__': ...@@ -350,10 +359,16 @@ if __name__ == '__main__':
company_id = find_id_by_name(start_time,token,social_code) company_id = find_id_by_name(start_time,token,social_code)
else: else:
company_id = find_id_by_name(start_time,token,com_name) 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: if not company_id:
log.info(com_name + "：企业ID获取失败===重新放入redis") log.info(com_name + "：企业ID获取失败===重新放入redis")
list_weicha.append(com_name + "：企业ID获取失败")
baseCore.rePutIntoR('BaseInfoEnterprise:gnqy_socialCode',social_code) 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) time.sleep(20)
continue continue
else: else:
...@@ -367,27 +382,32 @@ if __name__ == '__main__': ...@@ -367,27 +382,32 @@ if __name__ == '__main__':
except: except:
log.info(f'====={social_code}=====获取基本信息失败，重新放入redis=====') log.info(f'====={social_code}=====获取基本信息失败，重新放入redis=====')
baseCore.rePutIntoR('BaseInfoEnterprise:gnqy_social_code', social_code) baseCore.rePutIntoR('BaseInfoEnterprise:gnqy_social_code', social_code)
baseCore.delete_token(token)
log.info('=====已重新放入redis,失效token已删除======')
continue continue
if post_data_list: if post_data_list:
pass pass
else: else:
log.info(f'======{social_code}====企查查token失效====')
time.sleep(20) time.sleep(20)
continue continue
for post_data in post_data_list: for post_data in post_data_list:
list_all_info.append(post_data)
if post_data is None: if post_data is None:
print(com_name + "：企业信息获取失败") log.info(com_name + "：企业信息获取失败")
list_weicha.append(com_name + "：企业信息获取失败")
continue continue
get_name = post_data['name'] get_name = post_data['name']
get_socialcode = post_data['socialCreditCode'] get_socialcode = post_data['socialCreditCode']
# todo:将信用代码或企业名称更新到表中
# updatesocialcode = f"update Global100 set SocialCode = '{get_socialcode}' where CompanyName = '{com_name}'"
# cursor_.execute(updatesocialcode)
# cnx_.commit()
name_compile = { name_compile = {
'yuan_name':com_name, 'yuan_name':com_name,
'get_name':get_name 'get_name':get_name
} }
name_list.append(name_compile) name_list.append(name_compile)
nowtime = baseCore.getNowTime(1).replace('-', '_')[:10]
baseCore.writerToExcel(name_list, f'企业名称对比.xlsx')
log.info(f'采集{com_name}成功=======耗时{baseCore.getTimeCost(start_time,time.time())}') log.info(f'采集{com_name}成功=======耗时{baseCore.getTimeCost(start_time,time.time())}')
try: try:
producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'], api_version=(2, 0, 2)) producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'], api_version=(2, 0, 2))
...@@ -403,12 +423,6 @@ if __name__ == '__main__': ...@@ -403,12 +423,6 @@ if __name__ == '__main__':
runType = 'BaseInfoRunCount' runType = 'BaseInfoRunCount'
count += 1 count += 1
baseCore.updateRun(social_code, runType, count) baseCore.updateRun(social_code, runType, count)
nowtime = baseCore.getNowTime(1).replace('-','_')[:10]
companyName = pd.DataFrame(name_list)
companyName.to_excel(f'./data/企业名称对比_{nowtime}.xlsx',index=False)
false_com = pd.DataFrame(list_weicha)
false_com.to_excel(f'./data/采集失败企业名单_{nowtime}.xlsx',index=False)
......
comData/BaseInfo_qcc/base_info_1101.py 0 → 100644
# -*- 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)
comData/BaseInfo_qcc/getQccId.py
...@@ -46,15 +46,19 @@ def find_id_by_name(start,token,name): ...@@ -46,15 +46,19 @@ def find_id_by_name(start,token,name):
KeyNo = False 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())}') 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 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: try:
if resp_dict['result']['Result']: if resp_dict['result']['Result']:
result_dict = resp_dict['result']['Result'][0] result_dict = resp_dict['result']['Result'][0]
KeyNo = result_dict['KeyNo'] KeyNo = result_dict['KeyNo']
Name = result_dict['Name'].replace('<em>', '').replace('</em>', '').strip() Name = result_dict['Name'].replace('<em>', '').replace('</em>', '').strip()
if Name == '': if Name == '':
KeyNo = '' KeyNo = 'null'
else: else:
KeyNo = '' KeyNo = 'null'
except: except:
KeyNo = False KeyNo = False
log.info(f'====token失效====时间{baseCore.getTimeCost(start,time.time())}') log.info(f'====token失效====时间{baseCore.getTimeCost(start,time.time())}')
......
comData/Tyc/tyc_qydt_add.py
...@@ -158,6 +158,8 @@ def beinWork(tyc_code, social_code,start_time): ...@@ -158,6 +158,8 @@ def beinWork(tyc_code, social_code,start_time):
contentText = smart.extract_by_url(link).text contentText = smart.extract_by_url(link).text
#不带标签正文 #不带标签正文
content = smart.extract_by_url(link).cleaned_text content = smart.extract_by_url(link).cleaned_text
if len(content) < 300:
continue
# time.sleep(3) # time.sleep(3)
except Exception as e: except Exception as e:
contentText = '' contentText = ''
......
comData/annualReport/fbs_annualreport.py
...@@ -58,7 +58,7 @@ if __name__ == '__main__': ...@@ -58,7 +58,7 @@ if __name__ == '__main__':
'Accept-Encoding': 'gzip, deflate, br', 'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6', 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
} }
query = "SELECT * FROM clb_sys_attachment WHERE type_id=1 AND source='证监会'" query = "SELECT * FROM clb_sys_attachment WHERE type_id=1 AND source='证监会' AND id = '18703822757'"
cursor_.execute(query) cursor_.execute(query)
results = cursor_.fetchall() results = cursor_.fetchall()
for result in results: for result in results:
......
comData/annualReport1014/BaseCore.py
...@@ -666,7 +666,7 @@ class BaseCore: ...@@ -666,7 +666,7 @@ class BaseCore:
self.cnx_.commit() self.cnx_.commit()
# 插入到att表 返回附件id # 插入到att表 返回附件id
def tableUpdate(self, retData, com_name, year, pdf_name, num, pub_time,origin): def tableUpdate(self, retData, year, pdf_name, num, pub_time,origin):
item_id = retData['item_id'] item_id = retData['item_id']
type_id = retData['type_id'] type_id = retData['type_id']
group_name = retData['group_name'] group_name = retData['group_name']
......
comData/annualReport1014/report.py
...@@ -28,8 +28,8 @@ pathType = 'QYYearReport/' ...@@ -28,8 +28,8 @@ pathType = 'QYYearReport/'
type_id = 1 type_id = 1
create_by = 'XueLingKun' create_by = 'XueLingKun'
taskType = '企业年报' taskType = '企业年报'
#付俊雪的需要改为巨潮资讯网1_福布斯2000_PDF_60_付
file_path = 'D:\\年报\\福布斯2000强_年报补充_20231018' file_path = 'D:\\年报\\欧盟记分牌2500_年报补充_718_20231018'
log.info(f'=============当前pid为{baseCore.getPID()}==============') log.info(f'=============当前pid为{baseCore.getPID()}==============')
def sendKafka(dic_news): def sendKafka(dic_news):
...@@ -146,9 +146,9 @@ if __name__=='__main__': ...@@ -146,9 +146,9 @@ if __name__=='__main__':
social_code = data[1] social_code = data[1]
ename = data[2] ename = data[2]
cname = data[3] cname = data[3]
file_name = cname + ':' + file_year + '年年度报告' + '.pdf' file_name = ename + ':' + file_year + '年年度报告' + '.pdf'
content = '' content = ''
origin = cname + '官网' origin = ename + '官网'
#解析文件页数和内容 #解析文件页数和内容
log.info(f"-----------正在处理{file_name}--------------") log.info(f"-----------正在处理{file_name}--------------")
with open(pdf_path, 'rb') as file: with open(pdf_path, 'rb') as file:
......
comData/annualReport1014/report1.py
...@@ -3,7 +3,9 @@ ...@@ -3,7 +3,9 @@
""" """
import json import json
import os import os
import re
import time import time
import uuid
from kafka import KafkaProducer from kafka import KafkaProducer
from obs import ObsClient from obs import ObsClient
...@@ -24,12 +26,15 @@ baseCore = BaseCore.BaseCore() ...@@ -24,12 +26,15 @@ baseCore = BaseCore.BaseCore()
log = baseCore.getLogger() log = baseCore.getLogger()
cnx = baseCore.cnx cnx = baseCore.cnx
cursor = baseCore.cursor cursor = baseCore.cursor
cnx_ = baseCore.cnx_
cursor_ = baseCore.cursor_
pathType = 'QYYearReport/' pathType = 'QYYearReport/'
type_id = 1 type_id = 1
create_by = 'XueLingKun' create_by = 'XueLingKun'
taskType = '企业年报' taskType = '企业年报'
#付俊雪的需要改为巨潮资讯网 #付俊雪的需要改为巨潮资讯网
file_path = 'D:\\BaiduNetdiskDownload\\1_福布斯2000_PDF_50_郑' file_path = 'D:\\年报\\年度报告\\中石化炼化工程年度报告'
log.info(f'=============当前pid为{baseCore.getPID()}==============') log.info(f'=============当前pid为{baseCore.getPID()}==============')
def sendKafka(dic_news): def sendKafka(dic_news):
...@@ -66,6 +71,10 @@ def sendKafka(dic_news): ...@@ -66,6 +71,10 @@ def sendKafka(dic_news):
log.info(dic_result) log.info(dic_result)
return False return False
def getuuid():
get_timestamp_uuid = uuid.uuid1() # 根据 时间戳生成 uuid , 保证全球唯一
return get_timestamp_uuid
def uptoOBS(retData, pathType, taskType, start_time,file_name,pdf_path): def uptoOBS(retData, pathType, taskType, start_time,file_name,pdf_path):
""" """
retData = {'state': False, 'type_id': type_id, 'item_id': social_code, 'group_name': '', 'path': '', retData = {'state': False, 'type_id': type_id, 'item_id': social_code, 'group_name': '', 'path': '',
...@@ -92,7 +101,8 @@ def uptoOBS(retData, pathType, taskType, start_time,file_name,pdf_path): ...@@ -92,7 +101,8 @@ def uptoOBS(retData, pathType, taskType, start_time,file_name,pdf_path):
'category': category, 'file_size': file_size, 'status': status, 'create_by': create_by, 'category': category, 'file_size': file_size, 'status': status, 'create_by': create_by,
'create_time': create_time, 'page_size': page_size, 'content': content} 'create_time': create_time, 'page_size': page_size, 'content': content}
try: try:
result = getOBSres(pathType, file_name, pdf_path) name = str(getuuid()) + '.pdf'
result = getOBSres(pathType, name, pdf_path)
except: except:
log = baseCore.getLogger() log = baseCore.getLogger()
log.error(f'OBS发送失败') log.error(f'OBS发送失败')
...@@ -117,6 +127,13 @@ def getOBSres(pathType, name, response): ...@@ -117,6 +127,13 @@ def getOBSres(pathType, name, response):
result = obsClient.putFile('zzsn', pathType+name, file_path=response) result = obsClient.putFile('zzsn', pathType+name, file_path=response)
return result return result
def secrchATT(item_id, year, type_id):
sel_sql = '''select id from clb_sys_attachment where item_id = %s and year = %s and type_id=%s'''
cursor_.execute(sel_sql, (item_id, year, type_id))
selects = cursor_.fetchone()
return selects
if __name__=='__main__': if __name__=='__main__':
log.info(f'-----------当前文件{file_path}---------------') log.info(f'-----------当前文件{file_path}---------------')
file_list = os.listdir(file_path) file_list = os.listdir(file_path)
...@@ -126,19 +143,27 @@ if __name__=='__main__': ...@@ -126,19 +143,27 @@ if __name__=='__main__':
start_time = time.time() start_time = time.time()
pdf_path = file_path + '/'+file pdf_path = file_path + '/'+file
file_rank = int(file.split('-')[0]) # file_name_ = file.split('-')[0].replace('公司','')
file_year = file.split('-')[1] file_year = re.findall('\d{4}', file)[0]
file_name_ = file.split(file_year)[0]
#file_rank 对应上企业信用代码 #file_rank 对应上企业信用代码
selectsql = f"select * from rankandcode where id = {file_rank}" selectsql = f"select * from 500Report where com_name = '{file_name_}'"
cursor.execute(selectsql) cursor.execute(selectsql)
data = cursor.fetchone() data = cursor.fetchone()
cnx.commit() cnx.commit()
social_code = data[1] social_code = data[2]
ename = data[2]
cname = data[3] file_name = file_name_ + ':' + file_year + '年年度报告' + '.pdf'
file_name = cname + ':' + file_year + '年年度报告' + '.pdf'
content = '' content = ''
origin = file_name_ + '官网'
selects = secrchATT(social_code,file_year,1)
if selects:
# self.getLogger().info(f'com_name:{com_name}--{year}已存在')
log.info(f'===={file_name}--年报已存在===')
continue
#解析文件页数和内容 #解析文件页数和内容
log.info(f"-----------正在处理{file_name}--------------") log.info(f"-----------正在处理{file_name}--------------")
with open(pdf_path, 'rb') as file: with open(pdf_path, 'rb') as file:
...@@ -153,7 +178,7 @@ if __name__=='__main__': ...@@ -153,7 +178,7 @@ if __name__=='__main__':
content += page.get_text() content += page.get_text()
# print(content) # print(content)
except Exception as e: except Exception as e:
log.info(f'文件已损坏:{cname}') log.info(f'文件已损坏:{file_name}')
continue continue
#解析文件大小 #解析文件大小
file_size = os.path.getsize(pdf_path) file_size = os.path.getsize(pdf_path)
...@@ -168,8 +193,9 @@ if __name__=='__main__': ...@@ -168,8 +193,9 @@ if __name__=='__main__':
retData_f = uptoOBS(retData, pathType, taskType, start_time,file_name,pdf_path) retData_f = uptoOBS(retData, pathType, taskType, start_time,file_name,pdf_path)
if retData_f['state']: if retData_f['state']:
#retData, com_name, year, pdf_name, num, pub_time #retData, com_name, year, pdf_name, num, pub_time
att_id= baseCore.tableUpdate(retData_f, cname,file_year,file_name, num,file_year+'-12-31') att_id= baseCore.tableUpdate(retData_f,file_year,file_name, num,file_year+'-12-31',origin)
if att_id: if att_id:
detect_language = baseCore.detect_language(content)
dic_news = { dic_news = {
'attachmentIds': att_id, 'attachmentIds': att_id,
'author': '', 'author': '',
...@@ -179,8 +205,8 @@ if __name__=='__main__': ...@@ -179,8 +205,8 @@ if __name__=='__main__':
'deleteFlag': '0', 'deleteFlag': '0',
'id': '', 'id': '',
'keyWords': '', 'keyWords': '',
'lang': 'zh', 'lang': detect_language,
'origin': '企业官网', 'origin': origin,
'publishDate': file_year + '-12-31', 'publishDate': file_year + '-12-31',
'sid': '1684032033495392257', 'sid': '1684032033495392257',
'sourceAddress': '', # 原文链接 'sourceAddress': '', # 原文链接
...@@ -191,13 +217,15 @@ if __name__=='__main__': ...@@ -191,13 +217,15 @@ if __name__=='__main__':
'year': file_year 'year': file_year
} }
if sendKafka(dic_news): if sendKafka(dic_news):
log.info(f'成功-{file_rank}--{file_name}----{att_id}---{social_code}') log.info(f'成功---{file_name}----{att_id}---{social_code}')
num += 1 num += 1
else: else:
log.info(f'失败-{file_rank}--{file_name}----{att_id}---{social_code}') log.info(f'失败---{file_name}----{att_id}---{social_code}')
# 删除插入的数据 400表示发送数据失败 # 删除插入的数据 400表示发送数据失败
baseCore.deliteATT(att_id) baseCore.deliteATT(att_id)
log.info(f'已删除插入附件表的数据---{file_name}-----{social_code}') log.info(f'已删除插入附件表的数据---{file_name}-----{social_code}')
else:
log.info(f'-----年报已存在--{social_code}--{file_name}-----')
except Exception as e: except Exception as e:
log.info(f'error------{e}') log.info(f'error------{e}')
\ No newline at end of file
comData/caiwushuju/东方财富网财务数据.py
""" """
...@@ -465,8 +465,9 @@ def getReportTime(): ...@@ -465,8 +465,9 @@ def getReportTime():
def job(taskType): def job(taskType):
# 将上市企业库中的全部A股代码存入list # 将上市企业库中的全部A股代码存入list
# 需要提供股票代码、企业信用代码 # 需要提供股票代码、企业信用代码
flag = 0
while True: while True:
flag = 0
# 从redis中获取企业信用代码 # 从redis中获取企业信用代码
social_code = baseCore.redicPullData('FinanceFromEast:finance_socialCode') social_code = baseCore.redicPullData('FinanceFromEast:finance_socialCode')
# social_code = '91420300178856869P' # social_code = '91420300178856869P'
...@@ -487,6 +488,7 @@ def job(taskType): ...@@ -487,6 +488,7 @@ def job(taskType):
except: except:
time.sleep(1) time.sleep(1)
print(res_.text) print(res_.text)
flag = 0
continue continue
log.info(f'==========正在采集{social_code}============') log.info(f'==========正在采集{social_code}============')
sql_sel = f'''select securities_code,exchange from sys_base_enterprise_ipo where category = '1' and social_credit_code='{social_code}' ''' sql_sel = f'''select securities_code,exchange from sys_base_enterprise_ipo where category = '1' and social_credit_code='{social_code}' '''
......
comData/caiwushuju/经营分析.py 0 → 100644
import pymysql
import pymysql
import redis
import requests
import pandas as pd
from bs4 import BeautifulSoup
import re
import time
import numpy as np
import json
import datetime
import BaseCore
baseCore = BaseCore.BaseCore()
log = baseCore.getLogger()
import concurrent.futures
import random
from datetime import datetime
cnx = pymysql.connect(host='114.116.44.11', user='caiji', password='f7s0&7qqtK', db='clb_project', charset='utf8mb4')
cursor= cnx.cursor()
# log = baseCore.getLogger()
# 将采集后的股票代码对应的报告期保存进redis
# def add_date(com_code,i):
# r = redis.Redis(host="114.115.236.206", port=6379, password='clbzzsn',db=3)
# # json_cwsj = json.dumps(dic_cwsj)
# res = r.sadd('com_jingyingfenxi_code::'+com_code, i) # 注意是 保存set的方式
#
# def get_i():
# r = redis.Redis(host="114.115.236.206", port=6379, password='clbzzsn', db=3)
# i = r.get('com_jingyingfenxi_code::'+com_code)
def operate_analysis(i,com_code,social_code):
com_start = time.time()
list_code = [] # 股票代码
list_time = [] # 数据时间
list_zygc = [] # 主营构成
list_income = [] # 主营收入
list_income_sca = [] # 收入比例
list_chengben = [] # 主营成本
list_chengben_sca = [] # 成本比例
list_lirun = [] # 主营利润
list_lirun_sca = [] # 利润比例
list_maolilv = [] # 毛利率
list_category = [] # 类别
url_com = 'https://emweb.eastmoney.com/PC_HSF10/BusinessAnalysis/PageAjax?code={}'.format(com_code)
json_com = requests.get(url_com).json()
try:
list_all_info = json_com['zygcfx']
except:
list_all_info = ''
log.info(f'{com_code}---->{url_com}')
if list_all_info:
for one_info in list_all_info:
if "2017" in one_info['REPORT_DATE']: # 只要19年之后的数据
break
if one_info['MAINOP_TYPE'] == '1':
list_category.append('按行业分类')
if one_info['MAINOP_TYPE'] == '2':
list_category.append('按产品分类')
if one_info['MAINOP_TYPE'] == '3':
list_category.append('按地区分类')
select_sql = f'''select stock_code from operation_analysis_copy1 where stock_code = %s and date = '{one_info['REPORT_DATE'][:10]}' '''
y = cursor.execute(select_sql, com_code[2:])
if y:
i += 1
log.info(f'{com_code}--{one_info["REPORT_DATE"][:10]}--已入库')
# log.info('=========================')
continue
else:
log.info(f'{com_code}--{one_info["REPORT_DATE"][:10]}--开始采集')
try:
list_code.append(com_code[2:])
except:
list_code.append("--")
try:
list_time.append(one_info['REPORT_DATE'][:10])
except:
list_time.append("--")
try:
list_zygc.append(one_info['ITEM_NAME'])
except:
list_zygc.append("--")
try:
list_income.append(str(one_info['MAIN_BUSINESS_INCOME']) + "元")
except:
list_income.append("--")
try:
list_income_sca.append(str(str(round(one_info['MBI_RATIO'] * 100, 2)) + "%"))
except:
list_income_sca.append("--")
try:
list_chengben.append(str(one_info['MAIN_BUSINESS_COST']) + "元")
except:
list_chengben.append("--")
try:
list_chengben_sca.append(str(str(round(one_info['MBC_RATIO'] * 100, 2)) + "%"))
except:
list_chengben_sca.append("--")
try:
list_lirun.append(str(one_info['MAIN_BUSINESS_RPOFIT']) + "元")
except:
list_lirun.append("--")
try:
list_lirun_sca.append(str(str(round(one_info['MBR_RATIO'] * 100, 2)) + "%"))
except:
list_lirun_sca.append("--")
try:
list_maolilv.append(str(str(round(one_info['GROSS_RPOFIT_RATIO'] * 100, 2)) + "%"))
except:
list_maolilv.append("--")
com_end = time.time()
log.info(f'{com_code} 企业采集用时：{com_end-com_start}')
list_updata = []
send_start = time.time()
for code, zygc, income, income_sca, chengben, chengben_sca, lirun, lirun_sca, maolilv, time_, category in zip(
list_code, list_zygc, list_income,
list_income_sca, list_chengben, list_chengben_sca, list_lirun, list_lirun_sca, list_maolilv, list_time,
list_category):
dic_cwsj = {
"stockCode": code,
"mainComposition": zygc,
"mainIncome": income,
"incomeRatio": income_sca,
"mainCost": chengben,
"costRatio": chengben_sca,
"mainProfit": lirun,
"profitRatio": lirun_sca,
"grossProfitMargin": maolilv,
"date": time_,
"category": category,
}
# for nnn in range(0, 3):
# try:
# add_date(com_code,dic_cwsj)
# break
# except Exception as e:
# log.error(e)
# time.sleep(1)
list_updata.append(dic_cwsj)
print(list_updata)
print("{}---{}:获取完成".format(i,com_code))
time.sleep(1)
json_updata = json.dumps(list_updata)
#192.168.1.77 114.115.236.206
try:
response = requests.post('http://114.115.236.206:9988/datapull/sync/operationAnalysis', data=json_updata,
timeout=300,
verify=False)
time.sleep(3)
print(f'{com_code}',response.text)
except Exception as e:
print(e)
send_end = time.time()
log.info(f'{com_code} 传入接口用时：{send_end-send_start}')
return com_code,list_code, list_zygc, list_income,list_income_sca, list_chengben, list_chengben_sca, list_lirun, list_lirun_sca, list_maolilv, list_time,list_category
else:
return
df_all = pd.read_excel('D:/kkwork/zzsn_spider/data/上市企业(有财务数据)清单.xlsx',dtype=str)
list_non = []
i = 1
while True:
if i>=len(df_all):
log.info('采集已完成')
break
start_time = time.time()
com_code_ = df_all['股票代码'][i]
social_code = df_all['信用代码'][i]
num = len(com_code_)
if 'HK' in com_code_:
# com_code = com_code_.split('.')[0]
i+=1
continue
else:
if num != 6:
com_code1 = '0' * (6 - num) + com_code_
else:
com_code1 = com_code_
# 股票代码0、2、3开头的为深圳交易所，6、9开头的为上海交易所，8开头的为北京交易所
if com_code1[0] == '2' or com_code1[0] == '0' or com_code1[0] == '3':
com_code = 'sz' + com_code1
elif com_code1[0] == '9' or com_code1[0] == '6':
com_code = 'sh' + com_code1
elif com_code1[0] == '8' or com_code1[0] == '4':
com_code = 'bj' + com_code1
else:
log.error(f'{com_code_},{social_code}：无法获取正确的股票代码！')
list_updata = []
# # 判断该条信息是否已经采集过
# select_sql = '''select stock_code from operation_analysis_copy1 where stock_code = %s'''
# y = cursor.execute(select_sql, com_code[2:])
# if y:
# i += 1
# log.info(f'{com_code}----已入库')
# log.info('=========================')
# continue
#开始采集
try:
com_code,list_code, list_zygc, list_income,list_income_sca, list_chengben, list_chengben_sca, list_lirun, list_lirun_sca, list_maolilv, list_time,list_category = operate_analysis(i,com_code,social_code)
except Exception as e:
log.info(f'{com_code}----该企业无信息')
dic_non = {
'股票代码': com_code,
'信用代码': social_code
}
list_non.append(dic_non)
i += 1
continue
k=1
# for code, zygc, income, income_sca, chengben, chengben_sca, lirun, lirun_sca, maolilv, time_, category in zip(
# list_code, list_zygc, list_income,
# list_income_sca, list_chengben, list_chengben_sca, list_lirun, list_lirun_sca, list_maolilv, list_time,
# list_category):
# timestamp = time.time()
# create_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(timestamp))
# current_time = datetime.now()
# # random_number = random.randint(100,999)
# if k<10:
#
# id = f"{current_time.strftime('%Y%m%d%H%M%S%f')}{'00'}{k}"
# elif k<100:
# id = f"{current_time.strftime('%Y%m%d%H%M%S%f')}{'0'}{k}"
# else:
# id = f"{current_time.strftime('%Y%m%d%H%M%S%f')}{k}"
# # milliseconds = 100
# # seconds = milliseconds / 1000
# # time.sleep(seconds)
# k+=1
# dic_cwsj = {
# "id":id,
# "stockCode": code,
# "mainComposition": zygc,
# "mainIncome": income,
# "incomeRatio": income_sca,
# "mainCost": chengben,
# "costRatio": chengben_sca,
# "mainProfit": lirun,
# "profitRatio": lirun_sca,
# "grossProfitMargin": maolilv,
# "date": time_,
# "category": category,
# "create_time":create_time
# }
# # dic_cwsj = [
# # id,
# # code,
# # zygc,
# # income,
# # income_sca,
# # chengben,
# # chengben_sca,
# # lirun,
# # lirun_sca,
# # maolilv,
# # time_,
# # category,
# # create_time
# # ]
# #
# list_updata.append(dic_cwsj)
# log.info(f'当前数据量-----------{len(list_updata)}')
# # if len(list_updata)==0:
# # dic_non = {
# # '股票代码':com_code,
# # '信用代码':social_code
# # }
# # list_non.append(dic_non)
# # send_start = time.time()
# #插入数据
#
# # for info in list_updata:
# # try:
# # insert_sql = '''insert into operation_analysis (id,stock_code,main_composition,main_income,income_ratio,main_cost,cost_ratio,main_profit,profit_ratio,gross_profit_margin,date,category,create_time) values (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'''
# # cursor.execute(insert_sql, info)
# # cnx.commit()
# # except Exception as e:
# # current_time = datetime.now()
# # id = f"{current_time.strftime('%Y%m%d%H%M%S%f')}{'000'}"
# # insert_sql = '''insert into operation_analysis (id,stock_code,main_composition,main_income,income_ratio,main_cost,cost_ratio,main_profit,profit_ratio,gross_profit_margin,date,category,create_time) values (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'''
# # cursor.execute(insert_sql, info)
# # cnx.commit()
# # # print(e)
# # print("{}---{}:获取完成".format(i, com_code))
# # time.sleep(1)
# json_updata = json.dumps(list_updata)
# # 192.168.1.77 114.115.236.206
# send_start = time.time()
# for nnn in range(0,5):
# try:
# response = requests.post('http://114.115.236.206:9988/datapull/sync/operationAnalysis', data=json_updata)
# break
# except Exception as e:
# time.sleep(60)
# print(f'{com_code}', response.text)
#
# send_end = time.time()
# log.info(f'{com_code} 传入接口用时：{send_end - send_start}')
# # log.info(f'{com_code} 插入数据库用时：{send_end - send_start}')
# log.info('==========================')
# i += 1
# end_time = time.time()
# log.info(f'企业经营分析采集用时：{end_time-start_time}')
break
# df_non = pd.DataFrame(list_non)
# df_non.to_excel('无经营分析数据企业.xlsx',index=False)
comData/negative_news/creditchina.py
...@@ -28,6 +28,8 @@ log = baseCore.getLogger() ...@@ -28,6 +28,8 @@ log = baseCore.getLogger()
cnx = baseCore.cnx cnx = baseCore.cnx
cursor = baseCore.cursor cursor = baseCore.cursor
r = redis.Redis(host="114.115.236.206", port=6379, password='clbzzsn', db=0) r = redis.Redis(host="114.115.236.206", port=6379, password='clbzzsn', db=0)
import urllib3
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
taskType = '企业负面新闻' taskType = '企业负面新闻'
def sendKafka(dic_news): def sendKafka(dic_news):
start_time = time.time() start_time = time.time()
...@@ -93,7 +95,7 @@ def dishonesty(headers,com_name,social_code): ...@@ -93,7 +95,7 @@ def dishonesty(headers,com_name,social_code):
pass pass
else: else:
log.info(f'该企业{com_name}无严重失信信息') log.info(f'该企业{com_name}无严重失信信息')
return list_dishonesty return url,list_dishonesty
for page in range(1,total_size+1): for page in range(1,total_size+1):
param_page = { param_page = {
'tableName': 'credit_zgf_fr_sxbzxr', 'tableName': 'credit_zgf_fr_sxbzxr',
...@@ -172,7 +174,7 @@ def punish(headers,com_name,social_code): ...@@ -172,7 +174,7 @@ def punish(headers,com_name,social_code):
pass pass
else: else:
log.info(f'该企业{com_name}无行政处罚信息') log.info(f'该企业{com_name}无行政处罚信息')
return list_punish return url,list_punish
for page in range(1,total_size+1): for page in range(1,total_size+1):
param_page = { param_page = {
'tableName': 'credit_xyzx_fr_xzcf_new', 'tableName': 'credit_xyzx_fr_xzcf_new',
...@@ -250,7 +252,7 @@ def abnormal(headers,com_name,social_code): ...@@ -250,7 +252,7 @@ def abnormal(headers,com_name,social_code):
pass pass
else: else:
log.info(f'该企业{com_name}无经营异常信息') log.info(f'该企业{com_name}无经营异常信息')
return list_abhormal return url,list_abhormal
for page in range(1, total_size+1): for page in range(1, total_size+1):
param_page = { param_page = {
'tableName': 'credit_xyzx_fr_xzcf_new', 'tableName': 'credit_xyzx_fr_xzcf_new',
...@@ -293,7 +295,7 @@ def abnormal(headers,com_name,social_code): ...@@ -293,7 +295,7 @@ def abnormal(headers,com_name,social_code):
def dic_data(com_name,listData,type,detailurl): def dic_data(com_name,listData,type,detailurl):
dic_news = { dic_news = {
'title':com_name + type, 'title':com_name + type,
'structuredData':listData, 'structuredData':listData[:1],
'ynStructure':1, 'ynStructure':1,
'content': '', 'content': '',
'contentHtml': '', 'contentHtml': '',
...@@ -303,6 +305,11 @@ def dic_data(com_name,listData,type,detailurl): ...@@ -303,6 +305,11 @@ def dic_data(com_name,listData,type,detailurl):
} }
return dic_news return dic_news
def insertinto(dic_):
sql = "INSERT INTO zhejiangfmnews (title, structuredData, source) VALUES (%s, %s, %s)"
cursor.execute(sql, (dic_["title"], str(dic_["structuredData"]), dic_["source"]))
cnx.commit()
if __name__=='__main__': if __name__=='__main__':
headers = { headers = {
...@@ -315,21 +322,39 @@ if __name__=='__main__': ...@@ -315,21 +322,39 @@ if __name__=='__main__':
'sec-ch-ua-mobile': '?0', 'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"' 'sec-ch-ua-platform': '"Windows"'
} }
com_name = '石家庄交投集团工程服务有限责任公司' query = "select * from zhejiang "
social_code = '91130100MA7EK14C8L' cursor.execute(query)
url_dishonesty,list_dishonesty = dishonesty(headers,com_name,social_code) results = cursor.fetchall()
dic_dishonesty = dic_data(com_name,list_dishonesty,'严重违法失信信息',url_dishonesty) for result in results:
sendKafka(dic_dishonesty) com_name = result[1]
log.info(f'------------正在采集{com_name}----------------')
social_code = result[0]
try:
url_dishonesty,list_dishonesty = dishonesty(headers,com_name,social_code)
except:
list_dishonesty = []
log.info(f'error-------{com_name}')
continue
if list_dishonesty:
dic_dishonesty = dic_data(com_name,list_dishonesty,'严重违法失信信息',url_dishonesty)
# sendKafka(dic_dishonesty)
insertinto(dic_dishonesty)
log.info(f'----{com_name}---新增')
url_punish,list_punish = punish(headers,com_name,social_code) url_punish,list_punish = punish(headers,com_name,social_code)
dic_punish = dic_data(com_name, list_punish, '行政处罚信息', url_punish) if list_punish:
# print(dic_punish) dic_punish = dic_data(com_name, list_punish, '行政处罚信息', url_punish)
sendKafka(dic_punish) insertinto(dic_punish)
log.info(f'----{com_name}---新增')
# sendKafka(dic_punish)
url_abnormal,list_abnormal = abnormal(headers,com_name,social_code) url_abnormal,list_abnormal = abnormal(headers,com_name,social_code)
dic_abnormal = dic_data(com_name, list_abnormal, '经营异常信息', url_abnormal) if list_abnormal:
# print(dic_abnormal) dic_abnormal = dic_data(com_name, list_abnormal, '经营异常信息', url_abnormal)
sendKafka(dic_abnormal) insertinto(dic_abnormal)
log.info(f'----{com_name}---新增')
# sendKafka(dic_abnormal)
# 报告链接 # 报告链接
# url_report = f'https://public.creditchina.gov.cn/credit-check/pdf/clickDownload?companyName={com_name}&entityType=1&uuid=&tyshxydm={social_code}' # url_report = f'https://public.creditchina.gov.cn/credit-check/pdf/clickDownload?companyName={com_name}&entityType=1&uuid=&tyshxydm={social_code}'
......
comData/newlist/china100/BaseCore.py 0 → 100644
# 核心工具包
import os
import random
import socket
import sys
import time
import fitz
import logbook
import logbook.more
import pandas as pd
import requests
import zhconv
import pymysql
import redis
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from openpyxl import Workbook
import langid
#创建连接池
import pymysql
from pymysql import connections
from DBUtils.PooledDB import PooledDB
# 注意 程序退出前 调用BaseCore.close() 关闭相关资源
class BaseCore:
# 序列号
__seq = 0
# 代理池 数据库连接
# __cnx_proxy =None
# __cursor_proxy = None
cnx = None
cursor = None
cnx_ = None
cursor_ = None
r = None
# agent 池
__USER_AGENT_LIST = [
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.29 Safari/525.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/531.4 (KHTML, like Gecko) Chrome/3.0.194.0 Safari/531.4',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.11 Safari/534.16',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.50 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.7 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727; Lunascape 5.0 alpha2)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.222.7 Safari/532.2',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; ru-RU) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.11 Safari/534.16',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.10 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Maxthon;',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.1 (KHTML, like Gecko) Chrome/2.0.169.0 Safari/530.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; ja-JP; rv:1.7) Gecko/20040614 Firefox/0.9',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.810.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.0 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.3.4000 Chrome/30.0.1599.101 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.6 (KHTML, like Gecko) Chrome/7.0.500.0 Safari/534.6',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; TencentTraveler)',
'Mozilla/5.0 (Windows NT 6.0; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.4 (KHTML, like Gecko) Chrome/6.0.481.0 Safari/534.4',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.370.0 Safari/533.4',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US; rv:1.7.5) Gecko/20041107 Firefox/1.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.4.154.31 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB; rv:1.9.1.17) Gecko/20110123 (like Firefox/3.x) SeaMonkey/2.0.12',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB) AppleWebKit/534.1 (KHTML, like Gecko) Chrome/6.0.428.0 Safari/534.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; de-DE) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/7.0.540.0 Safari/534.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; de-DE) Chrome/4.0.223.3 Safari/532.2',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/12.0.702.0 Safari/534.24',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.42 Safari/525.19',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.3 (KHTML, like Gecko) Chrome/4.0.227.0 Safari/532.3',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.8 (KHTML, like Gecko) Chrome/16.0.912.63 Safari/535.8',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.460.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.463.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/528.9 (KHTML, like Gecko) Chrome/2.0.157.0 Safari/528.9',
'Mozilla/5.0 (Windows NT 5.2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.794.0 Safari/535.1',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.694.0 Safari/534.24',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5',
'Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:15.0) Gecko/20120427 Firefox/15.0a1',
'Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.7.5) Gecko/20041107 Firefox/1.0',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Maxthon; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.223.4 Safari/532.2',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.65 Safari/535.11',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.21 (KHTML, like Gecko) Chrome/11.0.682.0 Safari/534.21',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/530.0 (KHTML, like Gecko) Chrome/2.0.182.0 Safari/531.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.9 (KHTML, like Gecko) Chrome/7.0.531.0 Safari/534.9',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; WOW64; Trident/6.0)',
'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.811.0 Safari/535.1',
'ozilla/5.0 (Windows; U; Windows NT 5.0; de-DE; rv:1.7.5) Gecko/20041108 Firefox/1.0',
'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
'Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.375.127 Safari/533.4',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E) QQBrowser/6.9.11079.201',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; zh-cn) Opera 8.50',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/7.0.0 Safari/700.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.4 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.53 Safari/525.19',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.6 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.1 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.7.5) Gecko/20041107 Firefox/0.9.2 StumbleUpon/1.994',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-GB; rv:1.9.0.11) Gecko/2009060215 Firefox/3.0.11 (.NET CLR 3.5.30729)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.7.5) Gecko/20041110 Firefox/1.0',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1467.0 Safari/537.36',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; en) Opera 8.0',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1 QQBrowser/6.9.11079.201',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2',
'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:2.0b4pre) Gecko/20100815 Minefield/4.0b4pre',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.6 Safari/530.5',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; .NET CLR 1.0.3705)',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.21 Safari/532.0',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.792.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.1 (KHTML, like Gecko) Chrome/2.0.168.0 Safari/530.1',
'Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20040913 Firefox/0.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.8 (KHTML, like Gecko) Chrome/2.0.177.1 Safari/530.8',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/533.17.8 (KHTML, like Gecko) Version/5.0.1 Safari/533.17.8',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.40 Safari/530.5',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.24 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/528.10 (KHTML, like Gecko) Chrome/2.0.157.2 Safari/528.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.223.2 Safari/532.2',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.75 Safari/535.7',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; T312461)',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.461.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.0; rv:1.7.3) Gecko/20041001 Firefox/0.10.1',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; de-DE) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.202.2 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.2; Win64; x64; rv:16.0) Gecko/16.0 Firefox/16.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/531.3 (KHTML, like Gecko) Chrome/3.0.193.2 Safari/531.3',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; .NET CLR 1',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.864.0 Safari/535.2',
'Mozilla/5.0 (Windows NT 5.2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.813.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.6 Safari/532.0',
'Mozilla/5.0 (Windows NT 5.1; rv:2.1.1) Gecko/20110415 Firefox/4.0.2pre Fennec/4.0.1',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.801.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.212.0 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.697.0 Safari/534.24',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/7.0.548.0 Safari/534.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.17 (KHTML, like Gecko) Chrome/11.0.652.0 Safari/534.17',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.62 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/8.0.552.224 Safari/534.10 ChromePlus/1.5.2.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.219.0 Safari/532.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.7 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/533.2 (KHTML, like Gecko) Chrome/5.0.342.2 Safari/533.2',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.219.4 Safari/532.1',
'Mozilla/5.0 (Windows NT 6.0; rv:2.1.1) Gecko/20110415 Firefox/4.0.2pre Fennec/4.0.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.2.153.0 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; sv-SE; rv:1.7.5) Gecko/20041108 Firefox/1.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.462.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; de-DE; rv:1.7.5) Gecko/20041122 Firefox/1.0',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; uZardWeb/1.0; Server_JP)',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; HCI0449; .NET CLR 1.0.3705)',
'Mozilla/4.0 (compatible; MSIE 5.0; Windows 98; DigExt); Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1);',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.23 Safari/530.5',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.208.0 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.0; rv:14.0) Gecko/20100101 Firefox/14.0.1',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.7 (KHTML, like Gecko) Chrome/2.0.176.0 Safari/530.7',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.21 (KHTML, like Gecko) Chrome/11.0.678.0 Safari/534.21',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.21 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322)',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; InfoPath.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.55 Safari/525.19',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0a1) Gecko/20110623 Firefox/7.0a1 Fennec/7.0a1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.30 (KHTML, like Gecko) Chrome/12.0.724.100 Safari/534.30',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.472.33 Safari/534.3 SE 2.X MetaSr 1.0',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; WOW64; SV1; uZardWeb/1.0; Server_HK)',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0.1) Gecko/20100101 Firefox/7.0.1',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)',
'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E)',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.0) yi; AppleWebKit/345667.12221 (KHTML, like Gecko) Chrome/23.0.1271.26 Safari/453667.1221',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.2 (KHTML, like Gecko) Chrome/3.0.191.3 Safari/531.2',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.39 Safari/530.5',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.1 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.38 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.27 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8b) Gecko/20050118 Firefox/1.0+',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; ja-JP; rv:1.7) Gecko/20040707 Firefox/0.9.2',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.202.0 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.4 (KHTML, like Gecko) Chrome/2.0.171.0 Safari/530.4',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648)',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; nl-NL; rv:1.7.5) Gecko/20041202 Firefox/1.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.204.0 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.222.6 Safari/532.2',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/528.8 (KHTML, like Gecko) Chrome/1.0.156.0 Safari/528.8',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/6.0)',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; SV1; .NET CLR 1.0.3705; .NET CLR 2.0.50727; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.517.43 Safari/534.7',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.15 Safari/534.13',
'Mozilla/5.0 (ipad Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.6 (KHTML, like Gecko) Chrome/7.0.498.0 Safari/534.6',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.43 Safari/530.5',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.208.0 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.66 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.19 (KHTML, like Gecko) Chrome/11.0.661.0 Safari/534.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-CA) AppleWebKit/534.13 (KHTML like Gecko) Chrome/9.0.597.98 Safari/534.13',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.2 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.201.1 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.201.1 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.213.1 Safari/532.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/530.6 (KHTML, like Gecko) Chrome/2.0.174.0 Safari/530.6',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.3.154.6 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.599.0 Safari/534.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.8 (KHTML, like Gecko) Chrome/7.0.521.0 Safari/534.8',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.1b2pre) Gecko/20081015 Fennec/1.0a1',
'Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5'
]
#Android agent池
__USER_PHONE_AGENT_LIST = ['Mozilla/5.0 (Linux; Android 7.1.1; OPPO R9sk) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.111 Mobile Safari/537.36']
def __init__(self):
# self.__cnx_proxy = pymysql.connect(host='114.115.159.144', user='caiji', password='zzsn9988', db='clb_project',
# charset='utf8mb4')
# self.__cursor_proxy = self.__cnx_proxy.cursor()
self.cnx = pymysql.connect(host='114.115.159.144', user='caiji', password='zzsn9988', db='caiji',
charset='utf8mb4')
self.cursor = self.cnx.cursor()
#11数据库
self.cnx_ = pymysql.connect(host='114.116.44.11', user='caiji', password='f7s0&7qqtK', db='clb_project',
charset='utf8mb4')
self.cursor_ = self.cnx_.cursor()
# 连接到Redis
self.r = redis.Redis(host="114.115.236.206", port=6379, password='clbzzsn', db=6)
self.pool_caiji = PooledDB(
creator=pymysql,
maxconnections=5,
mincached=2,
maxcached=5,
blocking=True,
host='114.115.159.144',
port=3306,
user='caiji',
password='zzsn9988',
database='caiji',
charset='utf8mb4'
)
def close(self):
try:
self.cursor.close()
self.cnx.close()
except :
pass
# 计算耗时
def getTimeCost(self,start, end):
seconds = int(end - start)
m, s = divmod(seconds, 60)
h, m = divmod(m, 60)
if (h > 0):
return "%d小时%d分钟%d秒" % (h, m, s)
elif (m > 0):
return "%d分钟%d秒" % (m, s)
elif (seconds > 0):
return "%d秒" % (s)
else:
ms = int((end - start) * 1000)
return "%d毫秒" % (ms)
# 当前时间格式化
# 1 : 2001-01-01 12:00:00 %Y-%m-%d %H:%M:%S
# 2 : 010101120000 %y%m%d%H%M%S
# 时间戳 3:1690179526555 精确到秒
def getNowTime(self, type):
now_time = ""
if type == 1:
now_time = time.strftime("%Y-%m-%d %H:%M:%S")
if type == 2:
now_time = time.strftime("%y%m%d%H%M%S")
if type == 3:
now_time = int(time.time() * 1000)
return now_time
# 获取流水号
def getNextSeq(self):
self.__seq += 1
if self.__seq > 1000:
self.__seq = 0
return self.getNowTime(2) + str(self.__seq).zfill(3)
# 获取信用代码
def getNextXydm(self):
self.__seq += 1
if self.__seq > 1000:
self.__seq = 0
return "ZZSN" + self.getNowTime(2) + str(self.__seq).zfill(3)
# 日志格式
def logFormate(self,record, handler):
formate = "[{date}] [{level}] [{filename}] [{func_name}] [{lineno}] {msg}".format(
date=record.time, # 日志时间
level=record.level_name, # 日志等级
filename=os.path.split(record.filename)[-1], # 文件名
func_name=record.func_name, # 函数名
lineno=record.lineno, # 行号
msg=record.message # 日志内容
)
return formate
# 获取logger
def getLogger(self,fileLogFlag=True, stdOutFlag=True):
dirname, filename = os.path.split(os.path.abspath(sys.argv[0]))
dirname = os.path.join(dirname, "logs")
filename = filename.replace(".py", "") + ".log"
if not os.path.exists(dirname):
os.mkdir(dirname)
logbook.set_datetime_format('local')
logger = logbook.Logger(filename)
logger.handlers = []
if fileLogFlag: # 日志输出到文件
logFile = logbook.TimedRotatingFileHandler(os.path.join(dirname, filename), date_format='%Y-%m-%d',
bubble=True, encoding='utf-8')
logFile.formatter = self.logFormate
logger.handlers.append(logFile)
if stdOutFlag: # 日志打印到屏幕
logStd = logbook.more.ColorizedStderrHandler(bubble=True)
logStd.formatter = self.logFormate
logger.handlers.append(logStd)
return logger
# 获取随机的userAgent
def getRandomUserAgent(self):
return random.choice(self.__USER_AGENT_LIST)
# 获取代理
def get_proxy(self):
sql = "select proxy from clb_proxy"
self.cursor.execute(sql)
proxy_lists = self.cursor.fetchall()
ip_list = []
for proxy_ in proxy_lists:
ip_list.append(str(proxy_).replace("('", '').replace("',)", ''))
proxy_list = []
for str_ip in ip_list:
str_ip_list = str_ip.split('-')
proxyMeta = "http://%(host)s:%(port)s" % {
"host": str_ip_list[0],
"port": str_ip_list[1],
}
proxy = {
"HTTP": proxyMeta,
"HTTPS": proxyMeta
}
proxy_list.append(proxy)
return proxy_list[random.randint(0, 3)]
#字符串截取
def getSubStr(self,str,beginStr,endStr):
if beginStr=='':
pass
else:
begin=str.rfind(beginStr)
if begin==-1:
begin=0
str=str[begin:]
if endStr=='':
pass
else:
end=str.rfind(endStr)
if end==-1:
pass
else:
str = str[0:end+1]
return str
# 繁体字转简体字
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(self,str_num):
panduan = False
for str_1 in str_num:
ppp = str_1.isdigit()
if ppp:
panduan = ppp
return panduan
# # 从Redis的List中获取并移除一个元素
# def redicPullData(self,type,key):
# #1 表示国内 2 表示国外
# if type == 1:
# gn_item = self.r.lpop(key)
# return gn_item.decode() if gn_item else None
# if type == 2:
# gw_item = self.r.lpop(key)
# return gw_item.decode() if gw_item else None
# 从Redis的List中获取并移除一个元素
def redicPullData(self,key):
item = self.r.lpop(key)
return item.decode() if item else None
# 获得脚本进程PID
def getPID(self):
PID = os.getpid()
return PID
# 获取本机IP
def getIP(self):
IP = socket.gethostbyname(socket.gethostname())
return IP
def mkPath(self,path):
folder = os.path.exists(path)
if not folder: # 判断是否存在文件夹如果不存在则创建为文件夹
os.makedirs(path) # makedirs 创建文件时如果路径不存在会创建这个路径
else:
pass
# 生成google模拟浏览器 必须传入值为googledriver位置信息
# headless用于决定是否为无头浏览器,初始默认为无头浏览器
# 正常浏览器可用于开始对页面解析使用或一些网站无头时无法正常采集
# 无头浏览器用于后续对信息采集时不会有浏览器一直弹出，
def buildDriver(self, path, headless=True):
service = Service(path)
chrome_options = webdriver.ChromeOptions()
if headless:
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
chrome_options.add_experimental_option(
"excludeSwitches", ["enable-automation"])
chrome_options.add_experimental_option('useAutomationExtension', False)
chrome_options.add_argument('lang=zh-CN,zh,zh-TW,en-US,en')
chrome_options.add_argument('user-agent=' + self.getRandomUserAgent())
# 'user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36')
driver = webdriver.Chrome(options=chrome_options, service=service)
# with open(r'F:\zzsn\zzsn_spider\base\stealth.min.js') as f:
# js = f.read()
#
# driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
# "source": js
# })
return driver
# 根据社会信用代码获取企业信息
def getInfomation(self, social_code):
data = []
try:
sql = f"SELECT * FROM China100 WHERE SocialCode = '{social_code}'"
# self.cursor.execute(sql)
# data = self.cursor.fetchone()
conn = self.pool_caiji.connection()
cursor = conn.cursor()
cursor.execute(sql)
data = cursor.fetchone()
conn.commit()
data = list(data)
cursor.close()
conn.close()
except:
log = self.getLogger()
log.info('=========数据库操作失败========')
return data
# 更新企业采集次数
def updateRun(self, social_code, runType, count):
try:
sql_update = f"UPDATE EnterpriseInfo SET {runType} = {count} WHERE SocialCode = '{social_code}'"
# self.cursor.execute(sql_update)
# self.cnx.commit()
conn = self.pool_caiji.connection()
cursor = conn.cursor()
cursor.execute(sql_update)
conn.commit()
cursor.close()
conn.close()
except:
log = self.getLogger()
log.info('======更新数据库失败======')
# 保存日志入库
def recordLog(self, xydm, taskType, state, takeTime, url, e):
try:
createTime = self.getNowTime(1)
ip = self.getIP()
pid = self.getPID()
sql = "INSERT INTO LogTable(SocialCode,TaskType,state,TakeTime,url,CreateTime,ProcessIp,PID,Exception) VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s)"
values = [xydm, taskType, state, takeTime, url, createTime, ip, pid, e]
# try:
# self.cursor.execute(sql, values)
# except Exception as e:
# print(e)
# self.cnx.commit()
cnn = self.pool_caiji.connection()
cursor = cnn.cursor()
cursor.execute(sql,values)
cnn.commit()
cursor.close()
cnn.close()
except:
log = self.getLogger()
log.info('======保存日志失败=====')
#获取企查查token
def GetToken(self):
#获取企查查token
query = "select token from QCC_token "
# token = '67ec7402166df1da84ae83c4b95cefc0' # 需要隔两个小时左右抓包修改
self.cursor.execute(query)
token_list = self.cursor.fetchall()
self.cnx.commit()
try:
token = token_list[random.randint(0, len(token_list)-1)][0]
except:
token = ''
return token
# 删除失效的token
def delete_token(self,token):
deletesql = f"delete from QCC_token where token='{token}' "
self.cursor.execute(deletesql)
self.cnx.commit()
#获取天眼查token
def GetTYCToken(self):
query = 'select token from TYC_token'
self.cursor.execute(query)
token = self.cursor.fetchone()[0]
self.cnx.commit()
return token
#检测语言
def detect_language(self, text):
# 使用langid.py判断文本的语言
result = langid.classify(text)
if result == '':
return 'cn'
if result[0] == '':
return 'cn'
return result[0]
#追加接入excel
def writerToExcel(self,detailList,filename):
# filename='baidu搜索.xlsx'
# 读取已存在的xlsx文件
existing_data = pd.read_excel(filename,engine='openpyxl',dtype=str)
# 创建新的数据
new_data = pd.DataFrame(data=detailList)
# 将新数据添加到现有数据的末尾
combined_data = existing_data.append(new_data, ignore_index=True)
# 将结果写入到xlsx文件
combined_data.to_excel(filename, index=False)
# return combined_data
#对失败或者断掉的企业 重新放入redis
def rePutIntoR(self,key,item):
self.r.rpush(key, item)
#增加计数器的值并返回增加后的值
def incrSet(self,key):
# 增加计数器的值并返回增加后的值
new_value = self.r.incr(key)
print("增加后的值：", new_value)
return new_value
#获取key剩余的过期时间
def getttl(self,key):
# 获取key的剩余过期时间
ttl = self.r.ttl(key)
print("剩余过期时间：", ttl)
# 判断key是否已过期
if ttl < 0:
# key已过期，将key的值重置为0
self.r.set(key, 0)
self.r.expire(key, 3600)
time.sleep(2)
comData/newlist/china100/baseinfo_start.bat 0 → 100644
title dujiaoshoubaseinfo
call activate
call conda activate zzsn@3.8.0
python baseinfo_dujiaoshou.py
pause
\ No newline at end of file
comData/dfcfwGpdm/NQenterprise/NQbase_info.py → comData/newlist/china100/china100.py
...@@ -7,16 +7,17 @@ import requests ...@@ -7,16 +7,17 @@ import requests
import json import json
from kafka import KafkaProducer from kafka import KafkaProducer
from base.BaseCore import BaseCore from BaseCore import BaseCore
from getQccId import find_id_by_name from getQccId import find_id_by_name
baseCore = BaseCore() baseCore = BaseCore()
cnx_ = baseCore.cnx cnx_ = baseCore.cnx
cursor_ = baseCore.cursor cursor_ = baseCore.cursor
log = baseCore.getLogger() log = baseCore.getLogger()
import urllib3
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
# 通过企查查id获取企业基本信息 # 通过企查查id获取企业基本信息
def info_by_id(com_id,com_name,gpdm): def info_by_id(com_id,com_name):
aa_dict_list = [] aa_dict_list = []
t = str(int(time.time()) * 1000) t = str(int(time.time()) * 1000)
...@@ -31,7 +32,7 @@ def info_by_id(com_id,com_name,gpdm): ...@@ -31,7 +32,7 @@ def info_by_id(com_id,com_name,gpdm):
result_dict = resp_dict['result']['Company'] result_dict = resp_dict['result']['Company']
except: except:
log.info(com_name + ":获取失败===========重新放入redis") log.info(com_name + ":获取失败===========重新放入redis")
baseCore.rePutIntoR('EnterpriseIpo:nq_gpdm',gpdm) baseCore.rePutIntoR('china100:baseinfo',com_name)
return aa_dict_list return aa_dict_list
company_name = result_dict['Name'] company_name = result_dict['Name']
...@@ -306,12 +307,12 @@ def info_by_id(com_id,com_name,gpdm): ...@@ -306,12 +307,12 @@ def info_by_id(com_id,com_name,gpdm):
} }
aa_dict_list.append(aa_dict) aa_dict_list.append(aa_dict)
print(company_name + "：爬取完成") log.info(company_name + "：爬取完成")
return aa_dict_list return aa_dict_list
if __name__ == '__main__': if __name__ == '__main__':
taskType = '基本信息/企查查' taskType = '基本信息/企查查/中国100强'
headers = { headers = {
'Host': 'xcx.qcc.com', 'Host': 'xcx.qcc.com',
'Connection': 'keep-alive', 'Connection': 'keep-alive',
...@@ -323,65 +324,97 @@ if __name__ == '__main__': ...@@ -323,65 +324,97 @@ if __name__ == '__main__':
'Referer': 'https://servicewechat.com/wx395200814fcd7599/166/page-frame.html', 'Referer': 'https://servicewechat.com/wx395200814fcd7599/166/page-frame.html',
'Accept-Encoding': 'gzip, deflate, br,' 'Accept-Encoding': 'gzip, deflate, br,'
} }
list_weicha = []
name_list = []
#从redis里拿数据 #从redis里拿数据
while True: while True:
# TODO:需要隔两个小时左右抓包修改,token从数据库中获得 # TODO:需要隔两个小时左右抓包修改,token从数据库中获得
token = 'b4eb43143abdcf395f1335f322ca29e5' token = baseCore.GetToken()
list_weicha = [] dataList = []
list_all_info = [] if token:
name_list = [] pass
else:
log.info('==========已无token==========')
time.sleep(30)
continue
# list_all_info = []
start_time = time.time() start_time = time.time()
# 获取企业信息 # 获取企业信息
# com_code = baseCore.redicPullData('EnterpriseIpo:nq_gpdm') social_code = baseCore.redicPullData('china100:baseinfo')
com_code = '873349'
if '.NQ' in com_code:
com_code1 = com_code
else:
com_code1 = com_code + '.NQ'
company_id = find_id_by_name(start_time,token,com_code) # com_name = '卓新市万达铸业有限公司'
if social_code == '' or social_code is None:
if not company_id:
log.info(com_code + "：企业ID获取失败===重新放入redis")
list_weicha.append(com_code + "：企业ID获取失败")
baseCore.rePutIntoR('EnterpriseIpo:nq_gpdm',com_code)
log.info('-----已重新放入redis-----')
time.sleep(20) time.sleep(20)
continue continue
if '搜索不到' in social_code:
continue
else: else:
log.info(f'====={com_code}===={company_id}=====获取企业id成功=====') pass
# todo:企查查id写入gpdm表中 dic_info = baseCore.getInfomation(social_code)
updateSql = f"update gpdm set QCCID = '{company_id}' where gpdm = '{com_code}'" log.info(f'----当前企业{social_code}--开始处理---')
cursor_.execute(updateSql)
cnx_.commit() com_name = dic_info[1]
#企查查id
company_id = dic_info[3]
#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 == None or company_id == False:
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('china100:baseinfo', 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")
list_weicha.append(com_name + "：企业ID获取失败")
baseCore.rePutIntoR('china100:baseinfo',com_name)
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'====={com_name}===={company_id}=====获取企业id成功=====')
# todo:写入数据库
updateqccid = f"update China100 set qccid = '{company_id}' where CompanyName = '{com_name}'"
cursor_.execute(updateqccid)
cnx_.commit()
try: try:
post_data_list = info_by_id(company_id, '',com_code1) post_data_list = info_by_id(company_id, com_name)
except: except:
log.info(f'====={com_code}=====获取基本信息失败，重新放入redis=====') log.info(f'====={social_code}=====获取基本信息失败，重新放入redis=====')
baseCore.rePutIntoR('EnterpriseIpo:nq_gpdm', com_code) baseCore.rePutIntoR('china100:baseinfo', com_name)
baseCore.delete_token(token)
log.info('=====已重新放入redis,失效token已删除======')
continue continue
if post_data_list: if post_data_list:
pass pass
else: else:
log.info(f'======{com_code}====企查查token失效====') # log.info(f'======{social_code}====企查查token失效====')
time.sleep(20) time.sleep(20)
continue continue
for post_data in post_data_list: for post_data in post_data_list:
list_all_info.append(post_data) # list_all_info.append(post_data)
if post_data is None: if post_data is None:
print(com_code + "：企业信息获取失败") print(com_name + "：企业信息获取失败")
list_weicha.append(com_code + "：企业信息获取失败") list_weicha.append(com_name + "：企业信息获取失败")
continue continue
get_name = post_data['name'] get_name = post_data['name']
get_socialcode = post_data['socialCreditCode'] get_socialcode = post_data['socialCreditCode']
#todo:将信用代码更新到表中
updatesocialcode = f"update China100 set SocialCode = '{get_socialcode}' where CompanyName = '{com_name}'"
cursor_.execute(updatesocialcode)
cnx_.commit()
name_compile = { name_compile = {
'yuan_name':com_code, 'yuan_name':com_name,
'get_name':get_name 'get_name':get_name
} }
name_list.append(name_compile) name_list.append(name_compile)
# dataList.append(post_data)
log.info(f'采集{com_code}成功=======耗时{baseCore.getTimeCost(start_time,time.time())}') baseCore.writerToExcel(name_list,'中国100强企业.xlsx')
log.info(f'采集{com_name}成功=======耗时{baseCore.getTimeCost(start_time,time.time())}')
try: try:
producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'], api_version=(2, 0, 2)) producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'], api_version=(2, 0, 2))
kafka_result = producer.send("regionInfo", json.dumps(post_data, ensure_ascii=False).encode('utf8')) kafka_result = producer.send("regionInfo", json.dumps(post_data, ensure_ascii=False).encode('utf8'))
...@@ -392,13 +425,9 @@ if __name__ == '__main__': ...@@ -392,13 +425,9 @@ if __name__ == '__main__':
takeTime = baseCore.getTimeCost(start_time, time.time()) takeTime = baseCore.getTimeCost(start_time, time.time())
baseCore.recordLog(get_socialcode, taskType, state, takeTime, '', exception) baseCore.recordLog(get_socialcode, taskType, state, takeTime, '', exception)
log.info(f"{get_name}--{get_socialcode}--kafka传输失败") log.info(f"{get_name}--{get_socialcode}--kafka传输失败")
# 信息采集完成后将该企业的采集次数更新
# break
nowtime = baseCore.getNowTime(1).replace('-','_')[:10]
companyName = pd.DataFrame(name_list)
companyName.to_excel(f'./data/企业名称对比_{nowtime}.xlsx',index=False)
false_com = pd.DataFrame(list_weicha)
false_com.to_excel(f'./data/采集失败企业名单_{nowtime}.xlsx',index=False)
......
comData/dfcfwGpdm/NQenterprise/getQccId.py → comData/newlist/china100/getQccId.py
...@@ -5,21 +5,43 @@ import time ...@@ -5,21 +5,43 @@ import time
from urllib.parse import quote from urllib.parse import quote
import requests import requests
import urllib3 import urllib3
from base.BaseCore import BaseCore from BaseCore import BaseCore
baseCore = BaseCore() baseCore = BaseCore()
log = baseCore.getLogger() log = baseCore.getLogger()
# 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,'
# }
headers = { headers = {
'Host': 'xcx.qcc.com', 'Host': 'xcx.qcc.com',
'Connection': 'keep-alive', 'Connection': 'keep-alive',
'Qcc-Platform': 'mp-weixin', 'x-request-device-type': 'Android',
'Qcc-Timestamp': '', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 MicroMessenger/7.0.20.1781(0x6700143B) NetType/WIFI MiniProgramEnv/Windows WindowsWechat/WMPF XWEB/8391',
'Content-Type': 'application/json',
'Qcc-Version': '1.0.0', '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', 'authMini': 'Bearer f51dae1a2fcb109fa9ec58bd4a85e5c5',
'content-type': 'application/json', 'xweb_xhr': '1',
'Referer': 'https://servicewechat.com/wx395200814fcd7599/166/page-frame.html', 'xcx-version': '2023.09.27',
'Accept-Encoding': 'gzip, deflate, br,' 'Qcc-Platform': 'mp-weixin',
} 'Qcc-CurrentPage': '/company-subpackages/business/index',
'Qcc-Timestamp': '1696661787803',
'Qcc-RefPage': '/company-subpackages/detail/index',
'Accept': '*/*',
'Sec-Fetch-Site': 'cross-site',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Dest': 'empty',
'Referer': 'https://servicewechat.com/wx395200814fcd7599/307/page-frame.html',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'zh-CN,zh'
}
# 通过企业名称或信用代码获取企查查id # 通过企业名称或信用代码获取企查查id
def find_id_by_name(start,token,name): def find_id_by_name(start,token,name):
urllib3.disable_warnings() urllib3.disable_warnings()
...@@ -32,8 +54,8 @@ def find_id_by_name(start,token,name): ...@@ -32,8 +54,8 @@ def find_id_by_name(start,token,name):
try: try:
resp_dict = requests.get(url=url, headers=headers, verify=False).json() resp_dict = requests.get(url=url, headers=headers, verify=False).json()
break break
except: except Exception as e:
print('重试') print(f'{e}-------------重试')
time.sleep(5) time.sleep(5)
continue continue
time.sleep(2) time.sleep(2)
...@@ -46,19 +68,23 @@ def find_id_by_name(start,token,name): ...@@ -46,19 +68,23 @@ def find_id_by_name(start,token,name):
KeyNo = False 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())}') 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 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: try:
if resp_dict['result']['Result']: if resp_dict['result']['Result']:
result_dict = resp_dict['result']['Result'][0] result_dict = resp_dict['result']['Result'][0]
KeyNo = result_dict['KeyNo'] KeyNo = result_dict['KeyNo']
Name = result_dict['Name'].replace('<em>', '').replace('</em>', '').strip() Name = result_dict['Name'].replace('<em>', '').replace('</em>', '').strip()
if Name == '': if Name == '':
KeyNo = '' KeyNo = 'null'
else: else:
KeyNo = '' KeyNo = 'null'
except: except:
KeyNo = False KeyNo = False
log.info(f'====token失效====时间{baseCore.getTimeCost(start,time.time())}') log.info(f'====token失效====时间{baseCore.getTimeCost(start,time.time())}')
return KeyNo return KeyNo
print("{}，企业代码为:{}".format(qcc_key, KeyNo)) log.info("{}，企业代码为:{}".format(qcc_key, KeyNo))
return KeyNo return KeyNo
\ No newline at end of file
comData/newlist/global100/BaseCore.py 0 → 100644
# 核心工具包
import os
import random
import socket
import sys
import time
import fitz
import logbook
import logbook.more
import pandas as pd
import requests
import zhconv
import pymysql
import redis
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from openpyxl import Workbook
import langid
#创建连接池
import pymysql
from pymysql import connections
from DBUtils.PooledDB import PooledDB
# 注意 程序退出前 调用BaseCore.close() 关闭相关资源
class BaseCore:
# 序列号
__seq = 0
# 代理池 数据库连接
# __cnx_proxy =None
# __cursor_proxy = None
cnx = None
cursor = None
cnx_ = None
cursor_ = None
r = None
# agent 池
__USER_AGENT_LIST = [
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.29 Safari/525.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/531.4 (KHTML, like Gecko) Chrome/3.0.194.0 Safari/531.4',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.11 Safari/534.16',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.50 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.7 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727; Lunascape 5.0 alpha2)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.222.7 Safari/532.2',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; ru-RU) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.11 Safari/534.16',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.10 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Maxthon;',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.1 (KHTML, like Gecko) Chrome/2.0.169.0 Safari/530.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; ja-JP; rv:1.7) Gecko/20040614 Firefox/0.9',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.810.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.0 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.3.4000 Chrome/30.0.1599.101 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.6 (KHTML, like Gecko) Chrome/7.0.500.0 Safari/534.6',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; TencentTraveler)',
'Mozilla/5.0 (Windows NT 6.0; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.4 (KHTML, like Gecko) Chrome/6.0.481.0 Safari/534.4',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.370.0 Safari/533.4',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US; rv:1.7.5) Gecko/20041107 Firefox/1.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.4.154.31 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB; rv:1.9.1.17) Gecko/20110123 (like Firefox/3.x) SeaMonkey/2.0.12',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB) AppleWebKit/534.1 (KHTML, like Gecko) Chrome/6.0.428.0 Safari/534.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; de-DE) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/7.0.540.0 Safari/534.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; de-DE) Chrome/4.0.223.3 Safari/532.2',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/12.0.702.0 Safari/534.24',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.42 Safari/525.19',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.3 (KHTML, like Gecko) Chrome/4.0.227.0 Safari/532.3',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.8 (KHTML, like Gecko) Chrome/16.0.912.63 Safari/535.8',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.460.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.463.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/528.9 (KHTML, like Gecko) Chrome/2.0.157.0 Safari/528.9',
'Mozilla/5.0 (Windows NT 5.2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.794.0 Safari/535.1',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.694.0 Safari/534.24',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5',
'Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:15.0) Gecko/20120427 Firefox/15.0a1',
'Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.7.5) Gecko/20041107 Firefox/1.0',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Maxthon; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.223.4 Safari/532.2',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.65 Safari/535.11',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.21 (KHTML, like Gecko) Chrome/11.0.682.0 Safari/534.21',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/530.0 (KHTML, like Gecko) Chrome/2.0.182.0 Safari/531.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.9 (KHTML, like Gecko) Chrome/7.0.531.0 Safari/534.9',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; WOW64; Trident/6.0)',
'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.811.0 Safari/535.1',
'ozilla/5.0 (Windows; U; Windows NT 5.0; de-DE; rv:1.7.5) Gecko/20041108 Firefox/1.0',
'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
'Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.375.127 Safari/533.4',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E) QQBrowser/6.9.11079.201',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; zh-cn) Opera 8.50',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/7.0.0 Safari/700.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.4 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.53 Safari/525.19',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.6 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.1 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.7.5) Gecko/20041107 Firefox/0.9.2 StumbleUpon/1.994',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-GB; rv:1.9.0.11) Gecko/2009060215 Firefox/3.0.11 (.NET CLR 3.5.30729)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.7.5) Gecko/20041110 Firefox/1.0',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1467.0 Safari/537.36',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; en) Opera 8.0',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1 QQBrowser/6.9.11079.201',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2',
'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:2.0b4pre) Gecko/20100815 Minefield/4.0b4pre',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.6 Safari/530.5',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; .NET CLR 1.0.3705)',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.21 Safari/532.0',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.792.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.1 (KHTML, like Gecko) Chrome/2.0.168.0 Safari/530.1',
'Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20040913 Firefox/0.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.8 (KHTML, like Gecko) Chrome/2.0.177.1 Safari/530.8',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/533.17.8 (KHTML, like Gecko) Version/5.0.1 Safari/533.17.8',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.40 Safari/530.5',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.24 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/528.10 (KHTML, like Gecko) Chrome/2.0.157.2 Safari/528.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.223.2 Safari/532.2',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.75 Safari/535.7',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; T312461)',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.461.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.0; rv:1.7.3) Gecko/20041001 Firefox/0.10.1',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; de-DE) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.202.2 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.2; Win64; x64; rv:16.0) Gecko/16.0 Firefox/16.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/531.3 (KHTML, like Gecko) Chrome/3.0.193.2 Safari/531.3',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; .NET CLR 1',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.864.0 Safari/535.2',
'Mozilla/5.0 (Windows NT 5.2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.813.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.6 Safari/532.0',
'Mozilla/5.0 (Windows NT 5.1; rv:2.1.1) Gecko/20110415 Firefox/4.0.2pre Fennec/4.0.1',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.801.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.212.0 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.697.0 Safari/534.24',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/7.0.548.0 Safari/534.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.17 (KHTML, like Gecko) Chrome/11.0.652.0 Safari/534.17',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.62 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/8.0.552.224 Safari/534.10 ChromePlus/1.5.2.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.219.0 Safari/532.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.7 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/533.2 (KHTML, like Gecko) Chrome/5.0.342.2 Safari/533.2',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.219.4 Safari/532.1',
'Mozilla/5.0 (Windows NT 6.0; rv:2.1.1) Gecko/20110415 Firefox/4.0.2pre Fennec/4.0.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.2.153.0 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; sv-SE; rv:1.7.5) Gecko/20041108 Firefox/1.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.462.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; de-DE; rv:1.7.5) Gecko/20041122 Firefox/1.0',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; uZardWeb/1.0; Server_JP)',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; HCI0449; .NET CLR 1.0.3705)',
'Mozilla/4.0 (compatible; MSIE 5.0; Windows 98; DigExt); Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1);',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.23 Safari/530.5',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.208.0 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.0; rv:14.0) Gecko/20100101 Firefox/14.0.1',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.7 (KHTML, like Gecko) Chrome/2.0.176.0 Safari/530.7',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.21 (KHTML, like Gecko) Chrome/11.0.678.0 Safari/534.21',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.21 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322)',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; InfoPath.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.55 Safari/525.19',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0a1) Gecko/20110623 Firefox/7.0a1 Fennec/7.0a1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.30 (KHTML, like Gecko) Chrome/12.0.724.100 Safari/534.30',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.472.33 Safari/534.3 SE 2.X MetaSr 1.0',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; WOW64; SV1; uZardWeb/1.0; Server_HK)',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0.1) Gecko/20100101 Firefox/7.0.1',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)',
'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E)',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.0) yi; AppleWebKit/345667.12221 (KHTML, like Gecko) Chrome/23.0.1271.26 Safari/453667.1221',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.2 (KHTML, like Gecko) Chrome/3.0.191.3 Safari/531.2',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.39 Safari/530.5',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.1 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.38 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.27 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8b) Gecko/20050118 Firefox/1.0+',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; ja-JP; rv:1.7) Gecko/20040707 Firefox/0.9.2',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.202.0 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.4 (KHTML, like Gecko) Chrome/2.0.171.0 Safari/530.4',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648)',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; nl-NL; rv:1.7.5) Gecko/20041202 Firefox/1.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.204.0 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.222.6 Safari/532.2',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/528.8 (KHTML, like Gecko) Chrome/1.0.156.0 Safari/528.8',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/6.0)',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; SV1; .NET CLR 1.0.3705; .NET CLR 2.0.50727; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.517.43 Safari/534.7',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.15 Safari/534.13',
'Mozilla/5.0 (ipad Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.6 (KHTML, like Gecko) Chrome/7.0.498.0 Safari/534.6',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.43 Safari/530.5',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.208.0 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.66 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.19 (KHTML, like Gecko) Chrome/11.0.661.0 Safari/534.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-CA) AppleWebKit/534.13 (KHTML like Gecko) Chrome/9.0.597.98 Safari/534.13',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.2 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.201.1 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.201.1 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.213.1 Safari/532.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/530.6 (KHTML, like Gecko) Chrome/2.0.174.0 Safari/530.6',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.3.154.6 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.599.0 Safari/534.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.8 (KHTML, like Gecko) Chrome/7.0.521.0 Safari/534.8',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.1b2pre) Gecko/20081015 Fennec/1.0a1',
'Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5'
]
#Android agent池
__USER_PHONE_AGENT_LIST = ['Mozilla/5.0 (Linux; Android 7.1.1; OPPO R9sk) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.111 Mobile Safari/537.36']
def __init__(self):
# self.__cnx_proxy = pymysql.connect(host='114.115.159.144', user='caiji', password='zzsn9988', db='clb_project',
# charset='utf8mb4')
# self.__cursor_proxy = self.__cnx_proxy.cursor()
self.cnx = pymysql.connect(host='114.115.159.144', user='caiji', password='zzsn9988', db='caiji',
charset='utf8mb4')
self.cursor = self.cnx.cursor()
#11数据库
self.cnx_ = pymysql.connect(host='114.116.44.11', user='caiji', password='f7s0&7qqtK', db='clb_project',
charset='utf8mb4')
self.cursor_ = self.cnx_.cursor()
# 连接到Redis
self.r = redis.Redis(host="114.115.236.206", port=6379, password='clbzzsn', db=6)
self.pool_caiji = PooledDB(
creator=pymysql,
maxconnections=5,
mincached=2,
maxcached=5,
blocking=True,
host='114.115.159.144',
port=3306,
user='caiji',
password='zzsn9988',
database='caiji',
charset='utf8mb4'
)
def close(self):
try:
self.cursor.close()
self.cnx.close()
except :
pass
# 计算耗时
def getTimeCost(self,start, end):
seconds = int(end - start)
m, s = divmod(seconds, 60)
h, m = divmod(m, 60)
if (h > 0):
return "%d小时%d分钟%d秒" % (h, m, s)
elif (m > 0):
return "%d分钟%d秒" % (m, s)
elif (seconds > 0):
return "%d秒" % (s)
else:
ms = int((end - start) * 1000)
return "%d毫秒" % (ms)
# 当前时间格式化
# 1 : 2001-01-01 12:00:00 %Y-%m-%d %H:%M:%S
# 2 : 010101120000 %y%m%d%H%M%S
# 时间戳 3:1690179526555 精确到秒
def getNowTime(self, type):
now_time = ""
if type == 1:
now_time = time.strftime("%Y-%m-%d %H:%M:%S")
if type == 2:
now_time = time.strftime("%y%m%d%H%M%S")
if type == 3:
now_time = int(time.time() * 1000)
return now_time
# 获取流水号
def getNextSeq(self):
self.__seq += 1
if self.__seq > 1000:
self.__seq = 0
return self.getNowTime(2) + str(self.__seq).zfill(3)
# 获取信用代码
def getNextXydm(self):
self.__seq += 1
if self.__seq > 1000:
self.__seq = 0
return "ZZSN" + self.getNowTime(2) + str(self.__seq).zfill(3)
# 日志格式
def logFormate(self,record, handler):
formate = "[{date}] [{level}] [{filename}] [{func_name}] [{lineno}] {msg}".format(
date=record.time, # 日志时间
level=record.level_name, # 日志等级
filename=os.path.split(record.filename)[-1], # 文件名
func_name=record.func_name, # 函数名
lineno=record.lineno, # 行号
msg=record.message # 日志内容
)
return formate
# 获取logger
def getLogger(self,fileLogFlag=True, stdOutFlag=True):
dirname, filename = os.path.split(os.path.abspath(sys.argv[0]))
dirname = os.path.join(dirname, "logs")
filename = filename.replace(".py", "") + ".log"
if not os.path.exists(dirname):
os.mkdir(dirname)
logbook.set_datetime_format('local')
logger = logbook.Logger(filename)
logger.handlers = []
if fileLogFlag: # 日志输出到文件
logFile = logbook.TimedRotatingFileHandler(os.path.join(dirname, filename), date_format='%Y-%m-%d',
bubble=True, encoding='utf-8')
logFile.formatter = self.logFormate
logger.handlers.append(logFile)
if stdOutFlag: # 日志打印到屏幕
logStd = logbook.more.ColorizedStderrHandler(bubble=True)
logStd.formatter = self.logFormate
logger.handlers.append(logStd)
return logger
# 获取随机的userAgent
def getRandomUserAgent(self):
return random.choice(self.__USER_AGENT_LIST)
# 获取代理
def get_proxy(self):
sql = "select proxy from clb_proxy"
self.cursor.execute(sql)
proxy_lists = self.cursor.fetchall()
ip_list = []
for proxy_ in proxy_lists:
ip_list.append(str(proxy_).replace("('", '').replace("',)", ''))
proxy_list = []
for str_ip in ip_list:
str_ip_list = str_ip.split('-')
proxyMeta = "http://%(host)s:%(port)s" % {
"host": str_ip_list[0],
"port": str_ip_list[1],
}
proxy = {
"HTTP": proxyMeta,
"HTTPS": proxyMeta
}
proxy_list.append(proxy)
return proxy_list[random.randint(0, 3)]
#字符串截取
def getSubStr(self,str,beginStr,endStr):
if beginStr=='':
pass
else:
begin=str.rfind(beginStr)
if begin==-1:
begin=0
str=str[begin:]
if endStr=='':
pass
else:
end=str.rfind(endStr)
if end==-1:
pass
else:
str = str[0:end+1]
return str
# 繁体字转简体字
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(self,str_num):
panduan = False
for str_1 in str_num:
ppp = str_1.isdigit()
if ppp:
panduan = ppp
return panduan
# # 从Redis的List中获取并移除一个元素
# def redicPullData(self,type,key):
# #1 表示国内 2 表示国外
# if type == 1:
# gn_item = self.r.lpop(key)
# return gn_item.decode() if gn_item else None
# if type == 2:
# gw_item = self.r.lpop(key)
# return gw_item.decode() if gw_item else None
# 从Redis的List中获取并移除一个元素
def redicPullData(self,key):
item = self.r.lpop(key)
return item.decode() if item else None
# 获得脚本进程PID
def getPID(self):
PID = os.getpid()
return PID
# 获取本机IP
def getIP(self):
IP = socket.gethostbyname(socket.gethostname())
return IP
def mkPath(self,path):
folder = os.path.exists(path)
if not folder: # 判断是否存在文件夹如果不存在则创建为文件夹
os.makedirs(path) # makedirs 创建文件时如果路径不存在会创建这个路径
else:
pass
# 生成google模拟浏览器 必须传入值为googledriver位置信息
# headless用于决定是否为无头浏览器,初始默认为无头浏览器
# 正常浏览器可用于开始对页面解析使用或一些网站无头时无法正常采集
# 无头浏览器用于后续对信息采集时不会有浏览器一直弹出，
def buildDriver(self, path, headless=True):
service = Service(path)
chrome_options = webdriver.ChromeOptions()
if headless:
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
chrome_options.add_experimental_option(
"excludeSwitches", ["enable-automation"])
chrome_options.add_experimental_option('useAutomationExtension', False)
chrome_options.add_argument('lang=zh-CN,zh,zh-TW,en-US,en')
chrome_options.add_argument('user-agent=' + self.getRandomUserAgent())
# 'user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36')
driver = webdriver.Chrome(options=chrome_options, service=service)
# with open(r'F:\zzsn\zzsn_spider\base\stealth.min.js') as f:
# js = f.read()
#
# driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
# "source": js
# })
return driver
# 根据社会信用代码获取企业信息
def getInfomation(self, social_code):
data = []
try:
sql = f"SELECT * FROM Global100 WHERE SocialCode = '{social_code}'"
# self.cursor.execute(sql)
# data = self.cursor.fetchone()
conn = self.pool_caiji.connection()
cursor = conn.cursor()
cursor.execute(sql)
data = cursor.fetchone()
conn.commit()
data = list(data)
cursor.close()
conn.close()
except:
log = self.getLogger()
log.info('=========数据库操作失败========')
return data
# 更新企业采集次数
def updateRun(self, social_code, runType, count):
try:
sql_update = f"UPDATE EnterpriseInfo SET {runType} = {count} WHERE SocialCode = '{social_code}'"
# self.cursor.execute(sql_update)
# self.cnx.commit()
conn = self.pool_caiji.connection()
cursor = conn.cursor()
cursor.execute(sql_update)
conn.commit()
cursor.close()
conn.close()
except:
log = self.getLogger()
log.info('======更新数据库失败======')
# 保存日志入库
def recordLog(self, xydm, taskType, state, takeTime, url, e):
try:
createTime = self.getNowTime(1)
ip = self.getIP()
pid = self.getPID()
sql = "INSERT INTO LogTable(SocialCode,TaskType,state,TakeTime,url,CreateTime,ProcessIp,PID,Exception) VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s)"
values = [xydm, taskType, state, takeTime, url, createTime, ip, pid, e]
# try:
# self.cursor.execute(sql, values)
# except Exception as e:
# print(e)
# self.cnx.commit()
cnn = self.pool_caiji.connection()
cursor = cnn.cursor()
cursor.execute(sql,values)
cnn.commit()
cursor.close()
cnn.close()
except:
log = self.getLogger()
log.info('======保存日志失败=====')
#获取企查查token
def GetToken(self):
#获取企查查token
query = "select token from QCC_token "
# token = '67ec7402166df1da84ae83c4b95cefc0' # 需要隔两个小时左右抓包修改
self.cursor.execute(query)
token_list = self.cursor.fetchall()
self.cnx.commit()
try:
token = token_list[random.randint(0, len(token_list)-1)][0]
except:
token = ''
return token
# 删除失效的token
def delete_token(self,token):
deletesql = f"delete from QCC_token where token='{token}' "
self.cursor.execute(deletesql)
self.cnx.commit()
#获取天眼查token
def GetTYCToken(self):
query = 'select token from TYC_token'
self.cursor.execute(query)
token = self.cursor.fetchone()[0]
self.cnx.commit()
return token
#检测语言
def detect_language(self, text):
# 使用langid.py判断文本的语言
result = langid.classify(text)
if result == '':
return 'cn'
if result[0] == '':
return 'cn'
return result[0]
#追加接入excel
def writerToExcel(self,detailList,filename):
# filename='baidu搜索.xlsx'
# 读取已存在的xlsx文件
existing_data = pd.read_excel(filename,engine='openpyxl',dtype=str)
# 创建新的数据
new_data = pd.DataFrame(data=detailList)
# 将新数据添加到现有数据的末尾
combined_data = existing_data.append(new_data, ignore_index=True)
# 将结果写入到xlsx文件
combined_data.to_excel(filename, index=False)
# return combined_data
#对失败或者断掉的企业 重新放入redis
def rePutIntoR(self,key,item):
self.r.rpush(key, item)
#增加计数器的值并返回增加后的值
def incrSet(self,key):
# 增加计数器的值并返回增加后的值
new_value = self.r.incr(key)
print("增加后的值：", new_value)
return new_value
#获取key剩余的过期时间
def getttl(self,key):
# 获取key的剩余过期时间
ttl = self.r.ttl(key)
print("剩余过期时间：", ttl)
# 判断key是否已过期
if ttl < 0:
# key已过期，将key的值重置为0
self.r.set(key, 0)
self.r.expire(key, 3600)
time.sleep(2)
comData/newlist/global100/baseinfo_start.bat 0 → 100644
title dujiaoshoubaseinfo
call activate
call conda activate zzsn@3.8.0
python baseinfo_dujiaoshou.py
pause
\ No newline at end of file
comData/newlist/global100/getQccId.py 0 → 100644
# -*- coding: utf-8 -*-
import time
from urllib.parse import quote
import requests
import urllib3
from BaseCore import BaseCore
baseCore = BaseCore()
log = baseCore.getLogger()
# 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,'
# }
headers = {
'Host': 'xcx.qcc.com',
'Connection': 'keep-alive',
'x-request-device-type': 'Android',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 MicroMessenger/7.0.20.1781(0x6700143B) NetType/WIFI MiniProgramEnv/Windows WindowsWechat/WMPF XWEB/8391',
'Content-Type': 'application/json',
'Qcc-Version': '1.0.0',
'authMini': 'Bearer f51dae1a2fcb109fa9ec58bd4a85e5c5',
'xweb_xhr': '1',
'xcx-version': '2023.09.27',
'Qcc-Platform': 'mp-weixin',
'Qcc-CurrentPage': '/company-subpackages/business/index',
'Qcc-Timestamp': '1696661787803',
'Qcc-RefPage': '/company-subpackages/detail/index',
'Accept': '*/*',
'Sec-Fetch-Site': 'cross-site',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Dest': 'empty',
'Referer': 'https://servicewechat.com/wx395200814fcd7599/307/page-frame.html',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'zh-CN,zh'
}
# 通过企业名称或信用代码获取企查查id
def find_id_by_name(start,token,name):
urllib3.disable_warnings()
qcc_key = name
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 Exception as e:
print(f'{e}-------------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
log.info("{}，企业代码为:{}".format(qcc_key, KeyNo))
return KeyNo
\ No newline at end of file
comData/dfcfwGpdm/NQenterprise/NQgetid.py → comData/newlist/global100/global100.py
...@@ -7,16 +7,17 @@ import requests ...@@ -7,16 +7,17 @@ import requests
import json import json
from kafka import KafkaProducer from kafka import KafkaProducer
from base.BaseCore import BaseCore from BaseCore import BaseCore
from getQccId import find_id_by_name from getQccId import find_id_by_name
baseCore = BaseCore() baseCore = BaseCore()
cnx_ = baseCore.cnx cnx_ = baseCore.cnx
cursor_ = baseCore.cursor cursor_ = baseCore.cursor
log = baseCore.getLogger() log = baseCore.getLogger()
import urllib3
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
# 通过企查查id获取企业基本信息 # 通过企查查id获取企业基本信息
def info_by_id(com_id,com_name,gpdm): def info_by_id(com_id,com_name):
aa_dict_list = [] aa_dict_list = []
t = str(int(time.time()) * 1000) t = str(int(time.time()) * 1000)
...@@ -31,7 +32,7 @@ def info_by_id(com_id,com_name,gpdm): ...@@ -31,7 +32,7 @@ def info_by_id(com_id,com_name,gpdm):
result_dict = resp_dict['result']['Company'] result_dict = resp_dict['result']['Company']
except: except:
log.info(com_name + ":获取失败===========重新放入redis") log.info(com_name + ":获取失败===========重新放入redis")
baseCore.rePutIntoR('EnterpriseIpo:nq_gpdm',gpdm) baseCore.rePutIntoR('global100:baseinfo',com_name)
return aa_dict_list return aa_dict_list
company_name = result_dict['Name'] company_name = result_dict['Name']
...@@ -306,12 +307,12 @@ def info_by_id(com_id,com_name,gpdm): ...@@ -306,12 +307,12 @@ def info_by_id(com_id,com_name,gpdm):
} }
aa_dict_list.append(aa_dict) aa_dict_list.append(aa_dict)
print(company_name + "：爬取完成") log.info(company_name + "：爬取完成")
return aa_dict_list return aa_dict_list
if __name__ == '__main__': if __name__ == '__main__':
taskType = '基本信息/企查查' taskType = '基本信息/企查查/中国100强'
headers = { headers = {
'Host': 'xcx.qcc.com', 'Host': 'xcx.qcc.com',
'Connection': 'keep-alive', 'Connection': 'keep-alive',
...@@ -323,81 +324,110 @@ if __name__ == '__main__': ...@@ -323,81 +324,110 @@ if __name__ == '__main__':
'Referer': 'https://servicewechat.com/wx395200814fcd7599/166/page-frame.html', 'Referer': 'https://servicewechat.com/wx395200814fcd7599/166/page-frame.html',
'Accept-Encoding': 'gzip, deflate, br,' 'Accept-Encoding': 'gzip, deflate, br,'
} }
list_weicha = []
name_list = []
#从redis里拿数据 #从redis里拿数据
while True: while True:
# TODO:需要隔两个小时左右抓包修改,token从数据库中获得 # TODO:需要隔两个小时左右抓包修改,token从数据库中获得
token = '83a9a9be4e9ecf3a8f8a20364227dc5d' token = baseCore.GetToken()
list_weicha = [] dataList = []
list_all_info = [] if token:
name_list = [] pass
else:
log.info('==========已无token==========')
time.sleep(30)
continue
# list_all_info = []
start_time = time.time() start_time = time.time()
# 获取企业信息 # 获取企业信息
com_code = baseCore.redicPullData('EnterpriseIpoqccid:nq_gpdm') social_code = baseCore.redicPullData('global100:baseinfo')
if '.NQ' in com_code:
com_code1 = com_code
else:
com_code1 = com_code + '.NQ'
company_id = find_id_by_name(start_time,token,com_code1)
if not company_id: # com_name = '卓新市万达铸业有限公司'
log.info(com_code + "：企业ID获取失败===重新放入redis") if social_code == '' or social_code is None:
list_weicha.append(com_code + "：企业ID获取失败")
baseCore.rePutIntoR('EnterpriseIpoqccid:nq_gpdm',com_code)
log.info('-----已重新放入redis-----')
time.sleep(20) time.sleep(20)
continue 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---')
com_name = dic_info[1]
#企查查id
company_id = dic_info[3]
#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 == None or company_id == False:
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('global100:baseinfo', 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")
list_weicha.append(com_name + "：企业ID获取失败")
baseCore.rePutIntoR('global100:baseinfo',com_name)
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'====={com_name}===={company_id}=====获取企业id成功=====')
# todo:写入数据库
updateqccid = f"update Global100 set qccid = '{company_id}' where CompanyName = '{com_name}'"
cursor_.execute(updateqccid)
cnx_.commit()
try:
post_data_list = info_by_id(company_id, com_name)
except:
log.info(f'====={social_code}=====获取基本信息失败，重新放入redis=====')
baseCore.rePutIntoR('global100:baseinfo', com_name)
baseCore.delete_token(token)
log.info('=====已重新放入redis,失效token已删除======')
continue
if post_data_list:
pass
else: else:
log.info(f'====={com_code}===={company_id}=====获取企业id成功=====') # log.info(f'======{social_code}====企查查token失效====')
# todo:企查查id写入gpdm表中 time.sleep(20)
updateSql = f"update gpdm set QCCID = '{company_id}' where gpdm = '{com_code}'" continue
cursor_.execute(updateSql) for post_data in post_data_list:
cnx_.commit() # list_all_info.append(post_data)
# try: if post_data is None:
# post_data_list = info_by_id(company_id, '',com_code) print(com_name + "：企业信息获取失败")
# except: list_weicha.append(com_name + "：企业信息获取失败")
# log.info(f'====={com_code}=====获取基本信息失败，重新放入redis=====') continue
# baseCore.rePutIntoR('BaseInfoEnterprise:gnqy_social_code', com_code) get_name = post_data['name']
# continue # get_socialcode = post_data['socialCreditCode']
# if post_data_list: #todo:将信用代码更新到表中
# pass # updatesocialcode = f"update Global100 set SocialCode = '{get_socialcode}' where CompanyName = '{com_name}'"
# else: # cursor_.execute(updatesocialcode)
# log.info(f'======{com_code}====企查查token失效====') # cnx_.commit()
# time.sleep(20) name_compile = {
# continue 'yuan_name':com_name,
# for post_data in post_data_list: 'get_name':get_name
# list_all_info.append(post_data) }
# if post_data is None: name_list.append(name_compile)
# print(com_code + "：企业信息获取失败") # dataList.append(post_data)
# list_weicha.append(com_code + "：企业信息获取失败") baseCore.writerToExcel(name_list,'跨国公司100大.xlsx')
# continue log.info(f'采集{com_name}成功=======耗时{baseCore.getTimeCost(start_time,time.time())}')
# get_name = post_data['name'] try:
# get_socialcode = post_data['socialCreditCode'] producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'], api_version=(2, 0, 2))
# name_compile = { kafka_result = producer.send("regionInfo", json.dumps(post_data, ensure_ascii=False).encode('utf8'))
# 'yuan_name':com_code, print(kafka_result.get(timeout=10))
# 'get_name':get_name except:
# } exception = 'kafka传输失败'
# name_list.append(name_compile) state = 0
# takeTime = baseCore.getTimeCost(start_time, time.time())
# log.info(f'采集{com_code}成功=======耗时{baseCore.getTimeCost(start_time,time.time())}') baseCore.recordLog(get_socialcode, taskType, state, takeTime, '', exception)
# try: log.info(f"{get_name}--{get_socialcode}--kafka传输失败")
# producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'], api_version=(2, 0, 2))
# kafka_result = producer.send("regionInfo", json.dumps(post_data, ensure_ascii=False).encode('utf8')) # break
# print(kafka_result.get(timeout=10))
# except:
# exception = 'kafka传输失败'
# state = 0
# takeTime = baseCore.getTimeCost(start_time, time.time())
# baseCore.recordLog(get_socialcode, taskType, state, takeTime, '', exception)
# log.info(f"{get_name}--{get_socialcode}--kafka传输失败")
# # 信息采集完成后将该企业的采集次数更新
# nowtime = baseCore.getNowTime(1).replace('-','_')[:10]
# companyName = pd.DataFrame(name_list)
# companyName.to_excel(f'./data/企业名称对比_{nowtime}.xlsx',index=False)
# false_com = pd.DataFrame(list_weicha)
# false_com.to_excel(f'./data/采集失败企业名单_{nowtime}.xlsx',index=False)
......
comData/noticeReport/delete_obsfile.py 0 → 100644
from obs import ObsClient
from base.BaseCore import BaseCore
baseCore = BaseCore()
cnx_=baseCore.cnx_
cursor_=baseCore.cursor_
# 创建ObsClient对象
obs_client = ObsClient(access_key_id='VEHN7D0TJ9316H8AHCAV', secret_access_key='heR353lvSWVPNU8pe2QxDtd8GDsO5L6PGH5eUoQY', server='https://obs.cn-north-1.myhuaweicloud.com')
def delete(object_keys):
# 指定要删除的文件名列表
bucket_name = 'zzsn'
# object_keys = ['QYNotice/8921b4b0-7853-11ee-bcc0-000c29312880.pdf']
# 批量删除文件
for object_key in object_keys:
resp = obs_client.deleteObject(bucket_name, object_key)
if resp.status >= 200 and resp.status < 300:
print(f"文件 {object_key} 删除成功！")
else:
print(f"文件 {object_key} 删除失败！ 错误码：{resp.errorCode}，错误信息：{resp.errorMessage}")
# 关闭ObsClient对象
obs_client.close()
if __name__=='__main__':
query = "SELECT object_key FROM clb_sys_attachment WHERE type_id=8 AND source = '证监会' AND create_time >= '2023-10-30 16:46:09' AND create_time <= '2023-11-01 09:11:12'"
cursor_.execute(query)
results = cursor_.fetchall()
object_keys = [item[0] for item in results]
delete(object_keys)
\ No newline at end of file
comData/noticeReport/证监会-公告.py
import json
import json import json
import re import re
import time import time
import uuid
from datetime import datetime
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from kafka import KafkaProducer from kafka import KafkaProducer
from retry import retry
from base import BaseCore from base import BaseCore
from obs import ObsClient from obs import ObsClient
import fitz import fitz
...@@ -24,6 +30,11 @@ obsClient = ObsClient( ...@@ -24,6 +30,11 @@ obsClient = ObsClient(
secret_access_key='heR353lvSWVPNU8pe2QxDtd8GDsO5L6PGH5eUoQY', # 你的华为云的sk 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 server='https://obs.cn-north-1.myhuaweicloud.com' # 你的桶的地址
) )
pathType = 'QYNotice/'
def getuuid():
get_timestamp_uuid = uuid.uuid1() # 根据 时间戳生成 uuid , 保证全球唯一
return get_timestamp_uuid
#获取文件大小 #获取文件大小
def convert_size(size_bytes): def convert_size(size_bytes):
...@@ -44,26 +55,28 @@ def uptoOBS(pdf_url,pdf_name,type_id,social_code): ...@@ -44,26 +55,28 @@ def uptoOBS(pdf_url,pdf_name,type_id,social_code):
headers['User-Agent'] = baseCore.getRandomUserAgent() headers['User-Agent'] = baseCore.getRandomUserAgent()
for i in range(0, 3): for i in range(0, 3):
try: try:
response = requests.get(pdf_url, headers=headers,verify=False, timeout=20) response = requests.get(pdf_url, headers=headers, verify=False, timeout=20)
file_size = int(response.headers.get('Content-Length')) file_size = int(response.headers.get('Content-Length'))
break break
except: except:
time.sleep(3) time.sleep(3)
continue continue
page_size = 0 page_size = 0
for i in range(0, 3): name = str(getuuid()) + '.pdf'
try: now_time = time.strftime("%Y-%m")
name = pdf_name try:
now_time = time.strftime("%Y-%m") result = getOBSres(pathType, name, response)
result = obsClient.putContent('zzsn', 'QYNotice/'+name, content=response.content) except:
with fitz.open(stream=response.content, filetype='pdf') as doc: log.error(f'OBS发送失败')
page_size = doc.page_count return retData
for page in doc.pages(): try:
retData['content'] += page.get_text() with fitz.open(stream=response.content, filetype='pdf') as doc:
break page_size = doc.page_count
except: for page in doc.pages():
time.sleep(3) retData['content'] += page.get_text()
continue except:
log.error(f'文件损坏')
return retData
if page_size < 1: if page_size < 1:
# pdf解析失败 # pdf解析失败
...@@ -73,8 +86,8 @@ def uptoOBS(pdf_url,pdf_name,type_id,social_code): ...@@ -73,8 +86,8 @@ def uptoOBS(pdf_url,pdf_name,type_id,social_code):
try: try:
time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
retData['state'] = True retData['state'] = True
retData['path'] = unquote(result['body']['objectUrl'].split('.com')[1]) retData['path'] = result['body']['objectUrl'].split('.com')[1]
retData['full_path'] = unquote(result['body']['objectUrl']) retData['full_path'] = result['body']['objectUrl']
retData['file_size'] = convert_size(file_size) retData['file_size'] = convert_size(file_size)
retData['create_time'] = time_now retData['create_time'] = time_now
retData['page_size'] = page_size retData['page_size'] = page_size
...@@ -86,15 +99,21 @@ def uptoOBS(pdf_url,pdf_name,type_id,social_code): ...@@ -86,15 +99,21 @@ def uptoOBS(pdf_url,pdf_name,type_id,social_code):
return retData return retData
def secrchATT(item_id, name, type_id,order_by): @retry(tries=3, delay=1)
sel_sql = '''select id from clb_sys_attachment where item_id = %s and name = %s and type_id=%s and order_by=%s ''' def getOBSres(pathType,name, response):
cursor_.execute(sel_sql, (item_id, name, type_id,order_by)) result = obsClient.putContent('zzsn', pathType + name, content=response.content)
select = cursor_.fetchall() # resp = obsClient.putFile('zzsn', pathType + name, file_path='要上传的那个文件的本地路径')
selects = select[-1] return result
def secrchATT(item_id, retData, type_id,order_by):
sel_sql = '''select id from clb_sys_attachment where item_id = %s and path = %s and type_id=%s and order_by=%s '''
cursor_.execute(sel_sql, (item_id, retData['path'], type_id,order_by))
selects = cursor_.fetchone()
return selects return selects
# 插入到att表 返回附件id # 插入到att表 返回附件id
def tableUpdate(retData, com_name, year, pdf_name, num): def tableUpdate(retData, com_name, year, pdf_name, num,pub_time,origin):
item_id = retData['item_id'] item_id = retData['item_id']
type_id = retData['type_id'] type_id = retData['type_id']
group_name = retData['group_name'] group_name = retData['group_name']
...@@ -115,18 +134,19 @@ def tableUpdate(retData, com_name, year, pdf_name, num): ...@@ -115,18 +134,19 @@ def tableUpdate(retData, com_name, year, pdf_name, num):
# return id # return id
# else: # else:
try: try:
Upsql = '''insert into clb_sys_attachment(year,name,type_id,item_id,group_name,path,full_path,category,file_size,order_by,status,create_by,create_time,page_size,object_key,bucket_name) values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)''' Upsql = '''insert into clb_sys_attachment(year,name,type_id,item_id,group_name,path,full_path,category,file_size,order_by,status,create_by,create_time,page_size,object_key,bucket_name,publish_time,source) values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'''
values = ( values = (
year, pdf_name, type_id, item_id, group_name, path, full_path, category, file_size, order_by, year, pdf_name, type_id, item_id, group_name, path, full_path, category, file_size, order_by,
status, create_by, status, create_by,
create_time, page_size,full_path.split('https://zzsn.obs.cn-north-1.myhuaweicloud.com/')[1],'zzsn') create_time, page_size, full_path.split('https://zzsn.obs.cn-north-1.myhuaweicloud.com/')[1], 'zzsn',
pub_time, origin)
cursor_.execute(Upsql, values) # 插入 cursor_.execute(Upsql, values) # 插入
cnx_.commit() # 提交 cnx_.commit() # 提交
except Exception as e: except Exception as e:
print(e) print(e)
log.info(f"更新完成:{item_id}===={pdf_name}") log.info(f"更新完成:{item_id}===={pdf_name}")
selects = secrchATT(item_id, pdf_name, type_id,order_by) selects = secrchATT(item_id, retData, type_id,order_by)
id = selects[0] id = selects[0]
return id return id
...@@ -300,7 +320,8 @@ def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_na ...@@ -300,7 +320,8 @@ def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_na
log.info(f'====pdf解析失败====') log.info(f'====pdf解析失败====')
return False return False
num = num + 1 num = num + 1
att_id = tableUpdate(retData,com_name,year,pdf_name,num) origin = '证监会'
att_id = tableUpdate(retData,com_name,year,pdf_name,num,pub_time,origin)
if att_id: if att_id:
pass pass
else: else:
...@@ -318,7 +339,7 @@ def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_na ...@@ -318,7 +339,7 @@ def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_na
'id': '', 'id': '',
'keyWords': '', 'keyWords': '',
'lang': 'zh', 'lang': 'zh',
'origin': '证监会', 'origin': origin,
'publishDate': pub_time, 'publishDate': pub_time,
'sid': '1684032033495392257', 'sid': '1684032033495392257',
'sourceAddress': pdf_url, # 原文链接 'sourceAddress': pdf_url, # 原文链接
...@@ -332,7 +353,7 @@ def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_na ...@@ -332,7 +353,7 @@ def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_na
# 将相应字段通过kafka传输保存 # 将相应字段通过kafka传输保存
try: try:
producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092']) producer = KafkaProducer(bootstrap_servers=['114.115.159.144:9092'])
kafka_result = producer.send("researchReportTopicaaaas", json.dumps(dic_news, ensure_ascii=False).encode('utf8')) kafka_result = producer.send("researchReportTopic", json.dumps(dic_news, ensure_ascii=False).encode('utf8'))
print(kafka_result.get(timeout=10)) print(kafka_result.get(timeout=10))
...@@ -360,6 +381,8 @@ def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_na ...@@ -360,6 +381,8 @@ def GetContent(pdf_url, pdf_name, social_code, year, pub_time, start_time,com_na
def SpiderByZJH(url, payload, dic_info, start_time,num): # dic_info 数据库中获取到的基本信息 def SpiderByZJH(url, payload, dic_info, start_time,num): # dic_info 数据库中获取到的基本信息
social_code = dic_info[2] social_code = dic_info[2]
short_name = dic_info[4] short_name = dic_info[4]
if short_name == 'None':
short_name = dic_info[1]
com_name = dic_info[1] com_name = dic_info[1]
soup = RequestUrl(url, payload, social_code, start_time) soup = RequestUrl(url, payload, social_code, start_time)
...@@ -392,7 +415,7 @@ def SpiderByZJH(url, payload, dic_info, start_time,num): # dic_info 数据库 ...@@ -392,7 +415,7 @@ def SpiderByZJH(url, payload, dic_info, start_time,num): # dic_info 数据库
pass pass
else: else:
Maxpage = 50 Maxpage = 50
for i in range(1,Maxpage): for i in range(1,Maxpage+1):
log.info(f'==========正在采集第{i}页=========') log.info(f'==========正在采集第{i}页=========')
if i == 1: if i == 1:
href = url href = url
...@@ -413,17 +436,22 @@ def SpiderByZJH(url, payload, dic_info, start_time,num): # dic_info 数据库 ...@@ -413,17 +436,22 @@ def SpiderByZJH(url, payload, dic_info, start_time,num): # dic_info 数据库
pdf_url = pdf_url_info['onclick'].strip('downloadPdf1(').split(',')[0].strip('\'') pdf_url = pdf_url_info['onclick'].strip('downloadPdf1(').split(',')[0].strip('\'')
name_pdf = pdf_url_info['onclick'].strip('downloadPdf1(').split('\',')[1].strip('\'') + '.pdf' name_pdf = pdf_url_info['onclick'].strip('downloadPdf1(').split('\',')[1].strip('\'') + '.pdf'
pub_time = pdf_url_info['onclick'].strip('downloadPdf1(').split('\',')[2].strip('\'') pub_time_ = pdf_url_info['onclick'].strip('downloadPdf1(').split('\',')[2].strip('\'')
#todo:判断发布日期是否是日期格式 #todo:判断发布日期是否是日期格式
pattern = r"^\d{4}-\d{2}-\d{2}$" # 正则表达式匹配YYYY-MM-DD格式的日期 pattern = r"^\d{4}-\d{2}-\d{2}$" # 正则表达式匹配YYYY-MM-DD格式的日期
date_time_pattern = r"\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}" date_time_pattern = r"\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}"
if re.match(pattern, pub_time): if re.match(pattern, pub_time_):
pass pass
else: else:
if re.match(date_time_pattern, pub_time): if re.match(date_time_pattern, pub_time_):
pass pass
else: else:
continue continue
# 将时间年月日字符串转换为datetime对象
date_object = datetime.strptime(pub_time_, "%Y-%m-%d")
# 将datetime对象转换为年月日时分秒字符串
pub_time = date_object.strftime("%Y-%m-%d %H:%M:%S")
year = pub_time[:4] year = pub_time[:4]
report_type = td_list[4].text.strip() report_type = td_list[4].text.strip()
...@@ -513,6 +541,8 @@ if __name__ == '__main__': ...@@ -513,6 +541,8 @@ if __name__ == '__main__':
# 股票代码0、2、3开头的为深圳交易所，6、9开头的为上海交易所，4、8开头的为北京交易所 # 股票代码0、2、3开头的为深圳交易所，6、9开头的为上海交易所，4、8开头的为北京交易所
code = dic_info[3] code = dic_info[3]
short_name = dic_info[4] short_name = dic_info[4]
if short_name == 'None':
short_name = dic_info[1]
com_name = dic_info[1] com_name = dic_info[1]
dic_parms = getUrl(code, url_parms, Catagory2_parms) dic_parms = getUrl(code, url_parms, Catagory2_parms)
dic_parms_ls = getUrl(code, url_parms_ls, Catagory2_parms_ls) dic_parms_ls = getUrl(code, url_parms_ls, Catagory2_parms_ls)
......
comData/policylaw/policy_copy.py 0 → 100644
This source diff could not be displayed because it is too large. You can view the blob instead.
comData/weixin_solo/get_tokenCookies.py
...@@ -56,7 +56,7 @@ if __name__=="__main__": ...@@ -56,7 +56,7 @@ if __name__=="__main__":
url = "https://mp.weixin.qq.com/" url = "https://mp.weixin.qq.com/"
browser.get(url) browser.get(url)
# 可改动 # 可改动
time.sleep(20) time.sleep(40)
s = requests.session() s = requests.session()
#获取到token和cookies #获取到token和cookies
......
comData/weixin_solo/wxList.py
...@@ -49,6 +49,7 @@ def getSourceInfo(infoSourceCode): ...@@ -49,6 +49,7 @@ def getSourceInfo(infoSourceCode):
sql = f"SELECT site_uri,id,site_name,info_source_code from info_source where info_source_code = '{infoSourceCode}' " sql = f"SELECT site_uri,id,site_name,info_source_code from info_source where info_source_code = '{infoSourceCode}' "
cursor.execute(sql) cursor.execute(sql)
row = cursor.fetchone() row = cursor.fetchone()
cnx.commit()
dic_url = { dic_url = {
'url_': row[0], 'url_': row[0],
'sid': row[1], 'sid': row[1],
...@@ -143,6 +144,7 @@ def updateCookieToken(token,cookies): ...@@ -143,6 +144,7 @@ def updateCookieToken(token,cookies):
def getToken(): def getToken():
cursor_.execute(f"select token,cookies from weixin_tokenCookies where fenghao_time < DATE_SUB(NOW(), INTERVAL 2 HOUR) order by update_time asc limit 1") cursor_.execute(f"select token,cookies from weixin_tokenCookies where fenghao_time < DATE_SUB(NOW(), INTERVAL 2 HOUR) order by update_time asc limit 1")
row = cursor_.fetchall() row = cursor_.fetchall()
cnx_.commit()
if row: if row:
pass pass
else: else:
...@@ -159,7 +161,7 @@ def getPageData(dic_url,page): ...@@ -159,7 +161,7 @@ def getPageData(dic_url,page):
info_source_code = dic_url['info_source_code'] info_source_code = dic_url['info_source_code']
biz = dic_url['biz'] biz = dic_url['biz']
fakeid = biz + '==' fakeid = biz + '=='
tokenAndCookie = getToken() tokenAndCookie = getToken()
if tokenAndCookie: if tokenAndCookie:
pass pass
else: else:
...@@ -258,7 +260,7 @@ def getFromSql(): ...@@ -258,7 +260,7 @@ def getFromSql():
cnx.commit() cnx.commit()
result_list = [item[0] for item in results] result_list = [item[0] for item in results]
#放入redis # 放入redis
for item in result_list: for item in result_list:
r.rpush('WeiXinGZH:infoSourceCode', item) r.rpush('WeiXinGZH:infoSourceCode', item)
if __name__=="__main__": if __name__=="__main__":
......
cpws/BaseCore.py 0 → 100644
# 核心工具包
import os
import random
import socket
import sys
import time
import logbook
import logbook.more
import pandas as pd
import requests
import zhconv
import redis
from retry import retry
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
import langid
# 创建连接池
import pymysql
from DBUtils.PooledDB import PooledDB
# import sys
# sys.path.append('D://zzsn_spider//base//fdfs_client')
import uuid
# from fdfs_client.client import get_tracker_conf, Fdfs_client
# tracker_conf = get_tracker_conf(r'C:\Users\WIN10\DataspellProjects\zzsn_spider\base\client.conf')
# client = Fdfs_client(tracker_conf)
from obs import ObsClient
import fitz
from urllib.parse import unquote
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
)
# 注意 程序退出前 调用BaseCore.close() 关闭相关资源
class BaseCore:
# 序列号
__seq = 0
# 代理池 数据库连接
# __cnx_proxy =None
# __cursor_proxy = None
cnx = None
cursor = None
cnx_ = None
cursor_ = None
r = None
# agent 池
__USER_AGENT_LIST = [
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.29 Safari/525.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/531.4 (KHTML, like Gecko) Chrome/3.0.194.0 Safari/531.4',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.11 Safari/534.16',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.50 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.7 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727; Lunascape 5.0 alpha2)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.222.7 Safari/532.2',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; ru-RU) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.11 Safari/534.16',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.10 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; Maxthon;',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.1 (KHTML, like Gecko) Chrome/2.0.169.0 Safari/530.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; ja-JP; rv:1.7) Gecko/20040614 Firefox/0.9',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.810.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.0 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.3.4000 Chrome/30.0.1599.101 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.6 (KHTML, like Gecko) Chrome/7.0.500.0 Safari/534.6',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; TencentTraveler)',
'Mozilla/5.0 (Windows NT 6.0; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.4 (KHTML, like Gecko) Chrome/6.0.481.0 Safari/534.4',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.370.0 Safari/533.4',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US; rv:1.7.5) Gecko/20041107 Firefox/1.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.4.154.31 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB; rv:1.9.1.17) Gecko/20110123 (like Firefox/3.x) SeaMonkey/2.0.12',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB) AppleWebKit/534.1 (KHTML, like Gecko) Chrome/6.0.428.0 Safari/534.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; de-DE) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/7.0.540.0 Safari/534.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; de-DE) Chrome/4.0.223.3 Safari/532.2',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/12.0.702.0 Safari/534.24',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.42 Safari/525.19',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.3 (KHTML, like Gecko) Chrome/4.0.227.0 Safari/532.3',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.8 (KHTML, like Gecko) Chrome/16.0.912.63 Safari/535.8',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.460.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.463.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/528.9 (KHTML, like Gecko) Chrome/2.0.157.0 Safari/528.9',
'Mozilla/5.0 (Windows NT 5.2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.794.0 Safari/535.1',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.694.0 Safari/534.24',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5',
'Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:15.0) Gecko/20120427 Firefox/15.0a1',
'Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.7.5) Gecko/20041107 Firefox/1.0',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Maxthon; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.223.4 Safari/532.2',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.65 Safari/535.11',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.21 (KHTML, like Gecko) Chrome/11.0.682.0 Safari/534.21',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/530.0 (KHTML, like Gecko) Chrome/2.0.182.0 Safari/531.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.9 (KHTML, like Gecko) Chrome/7.0.531.0 Safari/534.9',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; WOW64; Trident/6.0)',
'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.811.0 Safari/535.1',
'ozilla/5.0 (Windows; U; Windows NT 5.0; de-DE; rv:1.7.5) Gecko/20041108 Firefox/1.0',
'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
'Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/533.4 (KHTML, like Gecko) Chrome/5.0.375.127 Safari/533.4',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E) QQBrowser/6.9.11079.201',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; zh-cn) Opera 8.50',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/7.0.0 Safari/700.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.4 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.53 Safari/525.19',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.6 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.1 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.7.5) Gecko/20041107 Firefox/0.9.2 StumbleUpon/1.994',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-GB; rv:1.9.0.11) Gecko/2009060215 Firefox/3.0.11 (.NET CLR 3.5.30729)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.7.5) Gecko/20041110 Firefox/1.0',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1467.0 Safari/537.36',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; en) Opera 8.0',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1 QQBrowser/6.9.11079.201',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2',
'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:2.0b4pre) Gecko/20100815 Minefield/4.0b4pre',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.6 Safari/530.5',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; .NET CLR 1.0.3705)',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.21 Safari/532.0',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.792.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.1 (KHTML, like Gecko) Chrome/2.0.168.0 Safari/530.1',
'Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20040913 Firefox/0.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.8 (KHTML, like Gecko) Chrome/2.0.177.1 Safari/530.8',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/533.17.8 (KHTML, like Gecko) Version/5.0.1 Safari/533.17.8',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.40 Safari/530.5',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.24 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/528.10 (KHTML, like Gecko) Chrome/2.0.157.2 Safari/528.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.223.2 Safari/532.2',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.75 Safari/535.7',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; T312461)',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.461.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.0; rv:1.7.3) Gecko/20041001 Firefox/0.10.1',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; de-DE) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.202.2 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.2; Win64; x64; rv:16.0) Gecko/16.0 Firefox/16.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/531.3 (KHTML, like Gecko) Chrome/3.0.193.2 Safari/531.3',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; .NET CLR 1',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.864.0 Safari/535.2',
'Mozilla/5.0 (Windows NT 5.2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.813.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.6 Safari/532.0',
'Mozilla/5.0 (Windows NT 5.1; rv:2.1.1) Gecko/20110415 Firefox/4.0.2pre Fennec/4.0.1',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.801.0 Safari/535.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.212.0 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Chrome/0.2.149.27 Safari/525.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.697.0 Safari/534.24',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/7.0.548.0 Safari/534.10',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.17 (KHTML, like Gecko) Chrome/11.0.652.0 Safari/534.17',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.62 Safari/537.36',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.10 (KHTML, like Gecko) Chrome/8.0.552.224 Safari/534.10 ChromePlus/1.5.2.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.219.0 Safari/532.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.7 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/533.2 (KHTML, like Gecko) Chrome/5.0.342.2 Safari/533.2',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.219.4 Safari/532.1',
'Mozilla/5.0 (Windows NT 6.0; rv:2.1.1) Gecko/20110415 Firefox/4.0.2pre Fennec/4.0.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.2.153.0 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; sv-SE; rv:1.7.5) Gecko/20041108 Firefox/1.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.462.0 Safari/534.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; de-DE; rv:1.7.5) Gecko/20041122 Firefox/1.0',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; uZardWeb/1.0; Server_JP)',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; HCI0449; .NET CLR 1.0.3705)',
'Mozilla/4.0 (compatible; MSIE 5.0; Windows 98; DigExt); Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1);',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.23 Safari/530.5',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.208.0 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.0; rv:14.0) Gecko/20100101 Firefox/14.0.1',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.7 (KHTML, like Gecko) Chrome/2.0.176.0 Safari/530.7',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.21 (KHTML, like Gecko) Chrome/11.0.678.0 Safari/534.21',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.21 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322)',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; InfoPath.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/1.0.154.55 Safari/525.19',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0a1) Gecko/20110623 Firefox/7.0a1 Fennec/7.0a1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.30 (KHTML, like Gecko) Chrome/12.0.724.100 Safari/534.30',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.472.33 Safari/534.3 SE 2.X MetaSr 1.0',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; WOW64; SV1; uZardWeb/1.0; Server_HK)',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0.1) Gecko/20100101 Firefox/7.0.1',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)',
'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; .NET4.0E)',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.0) yi; AppleWebKit/345667.12221 (KHTML, like Gecko) Chrome/23.0.1271.26 Safari/453667.1221',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.2 (KHTML, like Gecko) Chrome/3.0.191.3 Safari/531.2',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.39 Safari/530.5',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.1 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.38 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/3.0.195.27 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8b) Gecko/20050118 Firefox/1.0+',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; ja-JP; rv:1.7) Gecko/20040707 Firefox/0.9.2',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.202.0 Safari/532.0',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/530.4 (KHTML, like Gecko) Chrome/2.0.171.0 Safari/530.4',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648)',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; nl-NL; rv:1.7.5) Gecko/20041202 Firefox/1.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.204.0 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.2 (KHTML, like Gecko) Chrome/4.0.222.6 Safari/532.2',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/528.8 (KHTML, like Gecko) Chrome/1.0.156.0 Safari/528.8',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; Trident/6.0)',
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; SV1; .NET CLR 1.0.3705; .NET CLR 2.0.50727; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.517.43 Safari/534.7',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.15 Safari/534.13',
'Mozilla/5.0 (ipad Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.6 (KHTML, like Gecko) Chrome/7.0.498.0 Safari/534.6',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/530.5 (KHTML, like Gecko) Chrome/2.0.172.43 Safari/530.5',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.208.0 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.66 Safari/535.11',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.19 (KHTML, like Gecko) Chrome/11.0.661.0 Safari/534.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-CA) AppleWebKit/534.13 (KHTML like Gecko) Chrome/9.0.597.98 Safari/534.13',
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.211.2 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.201.1 Safari/532.0',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/532.0 (KHTML, like Gecko) Chrome/4.0.201.1 Safari/532.0',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.1 (KHTML, like Gecko) Chrome/4.0.213.1 Safari/532.1',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/530.6 (KHTML, like Gecko) Chrome/2.0.174.0 Safari/530.6',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.3.154.6 Safari/525.19',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.599.0 Safari/534.13',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.8 (KHTML, like Gecko) Chrome/7.0.521.0 Safari/534.8',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.1b2pre) Gecko/20081015 Fennec/1.0a1',
'Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5'
]
# Android agent池
__USER_PHONE_AGENT_LIST = [
'Mozilla/5.0 (Linux; Android 7.1.1; OPPO R9sk) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.111 Mobile Safari/537.36']
def __init__(self):
# self.__cnx_proxy = pymysql.connect(host='114.115.159.144', user='caiji', password='zzsn9988', db='clb_project',
# charset='utf8mb4')
# self.__cursor_proxy = self.__cnx_proxy.cursor()
self.cnx = pymysql.connect(host='114.115.159.144', user='caiji', password='zzsn9988', db='caiji',
charset='utf8mb4')
self.cursor = self.cnx.cursor()
# 11数据库
self.cnx_ = pymysql.connect(host='114.116.44.11', user='caiji', password='f7s0&7qqtK', db='clb_project',
charset='utf8mb4')
self.cursor_ = self.cnx_.cursor()
# 连接到Redis
self.r = redis.Redis(host="114.115.236.206", port=6379, password='clbzzsn', db=6)
self.pool_caiji = PooledDB(
creator=pymysql,
maxconnections=5,
mincached=2,
maxcached=5,
blocking=True,
host='114.115.159.144',
port=3306,
user='caiji',
password='zzsn9988',
database='caiji',
charset='utf8mb4'
)
def close(self):
try:
self.cursor.close()
self.cnx.close()
except:
pass
# 计算耗时
def getTimeCost(self, start, end):
seconds = int(end - start)
m, s = divmod(seconds, 60)
h, m = divmod(m, 60)
if (h > 0):
return "%d小时%d分钟%d秒" % (h, m, s)
elif (m > 0):
return "%d分钟%d秒" % (m, s)
elif (seconds > 0):
return "%d秒" % (s)
else:
ms = int((end - start) * 1000)
return "%d毫秒" % (ms)
# 当前时间格式化
# 1 : 2001-01-01 12:00:00 %Y-%m-%d %H:%M:%S
# 2 : 010101120000 %y%m%d%H%M%S
# 时间戳 3:1690179526555 精确到秒
def getNowTime(self, type):
now_time = ""
if type == 1:
now_time = time.strftime("%Y-%m-%d %H:%M:%S")
if type == 2:
now_time = time.strftime("%y%m%d%H%M%S")
if type == 3:
now_time = int(time.time() * 1000)
return now_time
# 获取流水号
def getNextSeq(self):
self.__seq += 1
if self.__seq > 1000:
self.__seq = 0
return self.getNowTime(2) + str(self.__seq).zfill(3)
# 获取信用代码
def getNextXydm(self):
self.__seq += 1
if self.__seq > 1000:
self.__seq = 0
return "ZZSN" + self.getNowTime(2) + str(self.__seq).zfill(3)
# 日志格式
def logFormate(self, record, handler):
formate = "[{date}] [{level}] [{filename}] [{func_name}] [{lineno}] {msg}".format(
date=record.time, # 日志时间
level=record.level_name, # 日志等级
filename=os.path.split(record.filename)[-1], # 文件名
func_name=record.func_name, # 函数名
lineno=record.lineno, # 行号
msg=record.message # 日志内容
)
return formate
# 获取logger
def getLogger(self, fileLogFlag=True, stdOutFlag=True):
pid = self.getPID()
dirname, filename = os.path.split(os.path.abspath(sys.argv[0]))
dirname = os.path.join(dirname, "logs")
filename = filename.replace(".py", "") + f"{pid}.log"
if not os.path.exists(dirname):
os.mkdir(dirname)
logbook.set_datetime_format('local')
logger = logbook.Logger(filename)
logger.handlers = []
if fileLogFlag: # 日志输出到文件
logFile = logbook.TimedRotatingFileHandler(os.path.join(dirname, filename), date_format='%Y-%m-%d',
bubble=True, encoding='utf-8')
logFile.formatter = self.logFormate
logger.handlers.append(logFile)
if stdOutFlag: # 日志打印到屏幕
logStd = logbook.more.ColorizedStderrHandler(bubble=True)
logStd.formatter = self.logFormate
logger.handlers.append(logStd)
return logger
# 获取随机的userAgent
def getRandomUserAgent(self):
return random.choice(self.__USER_AGENT_LIST)
# 获取代理
def get_proxy(self):
sql = "select proxy from clb_proxy"
self.cursor.execute(sql)
proxy_lists = self.cursor.fetchall()
ip_list = []
for proxy_ in proxy_lists:
ip_list.append(str(proxy_).replace("('", '').replace("',)", ''))
proxy_list = []
for str_ip in ip_list:
str_ip_list = str_ip.split('-')
proxyMeta = "http://%(host)s:%(port)s" % {
"host": str_ip_list[0],
"port": str_ip_list[1],
}
proxy = {
"HTTP": proxyMeta,
"HTTPS": proxyMeta
}
proxy_list.append(proxy)
return proxy_list[random.randint(0, 3)]
# 字符串截取
def getSubStr(self, str, beginStr, endStr):
if beginStr == '':
pass
else:
begin = str.rfind(beginStr)
if begin == -1:
begin = 0
str = str[begin:]
if endStr == '':
pass
else:
end = str.rfind(endStr)
if end == -1:
pass
else:
str = str[0:end + 1]
return str
# 繁体字转简体字
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(self, str_num):
panduan = False
for str_1 in str_num:
ppp = str_1.isdigit()
if ppp:
panduan = ppp
return panduan
# # 从Redis的List中获取并移除一个元素
# def redicPullData(self,type,key):
# #1 表示国内 2 表示国外
# if type == 1:
# gn_item = self.r.lpop(key)
# return gn_item.decode() if gn_item else None
# if type == 2:
# gw_item = self.r.lpop(key)
# return gw_item.decode() if gw_item else None
# 从Redis的List中获取并移除一个元素
def redicPullData(self, key):
item = self.r.lpop(key)
return item.decode() if item else None
# 获得脚本进程PID
def getPID(self):
PID = os.getpid()
return PID
# 获取本机IP
def getIP(self):
IP = socket.gethostbyname(socket.gethostname())
return IP
def mkPath(self, path):
folder = os.path.exists(path)
if not folder: # 判断是否存在文件夹如果不存在则创建为文件夹
os.makedirs(path) # makedirs 创建文件时如果路径不存在会创建这个路径
else:
pass
# 生成google模拟浏览器 必须传入值为googledriver位置信息
# headless用于决定是否为无头浏览器,初始默认为无头浏览器
# 正常浏览器可用于开始对页面解析使用或一些网站无头时无法正常采集
# 无头浏览器用于后续对信息采集时不会有浏览器一直弹出，
def buildDriver(self, path, headless=True):
service = Service(path)
chrome_options = webdriver.ChromeOptions()
if headless:
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
chrome_options.add_experimental_option(
"excludeSwitches", ["enable-automation"])
chrome_options.add_experimental_option('useAutomationExtension', False)
chrome_options.add_argument('lang=zh-CN,zh,zh-TW,en-US,en')
chrome_options.add_argument('user-agent=' + self.getRandomUserAgent())
# 'user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36')
driver = webdriver.Chrome(options=chrome_options, service=service)
# with open(r'F:\zzsn\zzsn_spider\base\stealth.min.js') as f:
# js = f.read()
#
# driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
# "source": js
# })
return driver
# 根据社会信用代码获取企业信息
def getInfomation(self, social_code):
data = []
try:
sql = f"SELECT * FROM EnterpriseInfo WHERE SocialCode = '{social_code}'"
# self.cursor.execute(sql)
# data = self.cursor.fetchone()
conn = self.pool_caiji.connection()
cursor = conn.cursor()
cursor.execute(sql)
data = cursor.fetchone()
conn.commit()
data = list(data)
cursor.close()
conn.close()
except:
log = self.getLogger()
log.info('=========数据库操作失败========')
return data
# 更新企业采集次数
def updateRun(self, social_code, runType, count):
try:
sql_update = f"UPDATE EnterpriseInfo SET {runType} = {count} WHERE SocialCode = '{social_code}'"
# self.cursor.execute(sql_update)
# self.cnx.commit()
conn = self.pool_caiji.connection()
cursor = conn.cursor()
cursor.execute(sql_update)
conn.commit()
cursor.close()
conn.close()
except:
log = self.getLogger()
log.info('======更新数据库失败======')
# 保存日志入库
def recordLog(self, xydm, taskType, state, takeTime, url, e):
try:
createTime = self.getNowTime(1)
ip = self.getIP()
pid = self.getPID()
sql = "INSERT INTO LogTable(SocialCode,TaskType,state,TakeTime,url,CreateTime,ProcessIp,PID,Exception) VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s)"
values = [xydm, taskType, state, takeTime, url, createTime, ip, pid, e]
# try:
# self.cursor.execute(sql, values)
# except Exception as e:
# print(e)
# self.cnx.commit()
cnn = self.pool_caiji.connection()
cursor = cnn.cursor()
cursor.execute(sql, values)
cnn.commit()
cursor.close()
cnn.close()
except:
log = self.getLogger()
log.info('======保存日志失败=====')
# 获取企查查token
def GetToken(self):
# 获取企查查token
query = "select token from QCC_token "
# token = '67ec7402166df1da84ae83c4b95cefc0' # 需要隔两个小时左右抓包修改
self.cursor.execute(query)
token_list = self.cursor.fetchall()
self.cnx.commit()
token = token_list[random.randint(0, len(token_list) - 1)][0]
return token
# 获取天眼查token
def GetTYCToken(self):
query = 'select token from TYC_token'
self.cursor.execute(query)
token = self.cursor.fetchone()[0]
self.cnx.commit()
return token
# 检测语言
def detect_language(self, text):
# 使用langid.py判断文本的语言
result = langid.classify(text)
if result == '':
return 'cn'
if result[0] == '':
return 'cn'
return result[0]
# 追加接入excel
def writerToExcel(self, detailList, filename):
# filename='baidu搜索.xlsx'
# 读取已存在的xlsx文件
existing_data = pd.read_excel(filename, engine='openpyxl', dtype=str)
# 创建新的数据
new_data = pd.DataFrame(data=detailList)
# 将新数据添加到现有数据的末尾
combined_data = existing_data.append(new_data, ignore_index=True)
# 将结果写入到xlsx文件
combined_data.to_excel(filename, index=False)
# return combined_data
# 对失败或者断掉的企业 重新放入redis
def rePutIntoR(self, key, item):
self.r.rpush(key, item)
# 增加计数器的值并返回增加后的值
def incrSet(self, key):
# 增加计数器的值并返回增加后的值
new_value = self.r.incr(key)
print("增加后的值：", new_value)
return new_value
# 获取key剩余的过期时间
def getttl(self, key):
# 获取key的剩余过期时间
ttl = self.r.ttl(key)
print("剩余过期时间：", ttl)
# 判断key是否已过期
if ttl < 0:
# key已过期，将key的值重置为0
self.r.set(key, 0)
self.r.expire(key, 3600)
time.sleep(2)
# 上传至文件服务器,并解析pdf的内容和页数
# def upLoadToServe(self, pdf_url, type_id, social_code):
# headers = {}
# retData = {'state': False, 'type_id': type_id, 'item_id': social_code, 'group_name': '', 'path': '',
# 'full_path': '',
# 'category': 'pdf', 'file_size': '', 'status': 1, 'create_by': 'XueLingKun',
# 'create_time': '', 'page_size': '', 'content': ''}
# headers['User-Agent'] = self.getRandomUserAgent()
# for i in range(0, 3):
# try:
# resp_content = requests.get(pdf_url, headers=headers, verify=False, timeout=20).content
# break
# except:
# time.sleep(3)
# continue
# page_size = 0
#
# for i in range(0, 3):
# try:
# result = client.upload_by_buffer(resp_content, file_ext_name='pdf')
# with fitz.open(stream=resp_content, filetype='pdf') as doc:
# page_size = doc.page_count
# for page in doc.pages():
# retData['content'] += page.get_text()
# break
# except:
# time.sleep(3)
# continue
# if page_size < 1:
# # pdf解析失败
# print(f'======pdf解析失败=====')
# return retData
# else:
# time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
# retData['state'] = True
# retData['path'] = bytes.decode(result['Remote file_id']).replace('group1', '')
# retData['full_path'] = bytes.decode(result['Remote file_id'])
# retData['file_size'] = result['Uploaded size']
# retData['create_time'] = time_now
# retData['page_size'] = page_size
#
# return retData
def secrchATT(self, item_id, year, type_id):
sel_sql = '''select id from clb_sys_attachment where item_id = %s and year = %s and type_id=%s '''
self.cursor_.execute(sel_sql, (item_id, year, type_id))
selects = self.cursor_.fetchone()
return selects
# 插入到att表 返回附件id
def tableUpdate(self, retData, com_name, year, pdf_name, num, pub_time):
item_id = retData['item_id']
type_id = retData['type_id']
group_name = retData['group_name']
path = retData['path']
full_path = retData['full_path']
category = retData['category']
file_size = retData['file_size']
status = retData['status']
create_by = retData['create_by']
page_size = retData['page_size']
create_time = retData['create_time']
order_by = num
selects = self.secrchATT(item_id, year, type_id)
if selects:
self.getLogger().info(f'com_name:{com_name}--{year}已存在')
id = ''
return id
else:
Upsql = '''insert into clb_sys_attachment(year,name,type_id,item_id,group_name,path,full_path,category,file_size,order_by,status,create_by,create_time,page_size,object_key,bucket_name,publish_time) values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'''
values = (
year, pdf_name, type_id, item_id, group_name, path, full_path, category, file_size, order_by,
status, create_by,
create_time, page_size, full_path.split('https://zzsn.obs.cn-north-1.myhuaweicloud.com/')[1], 'zzsn',
pub_time)
self.cursor_.execute(Upsql, values) # 插入
self.cnx_.commit() # 提交
self.getLogger().info("更新完成:{}".format(Upsql))
selects = self.secrchATT(item_id, year, type_id)
id = selects[0]
return id
# 更新企业的CIK
def updateCIK(self, social_code, cik):
try:
sql = f"UPDATE EnterpriseInfo SET CIK = '{cik}' WHERE SocialCode = '{social_code}'"
cnn = self.pool_caiji.connection()
cursor = cnn.cursor()
cursor.execute(sql)
cnn.commit()
cursor.close()
cnn.close()
except:
log = self.getLogger()
log.info('======保存企业CIK失败=====')
# 上传至obs华为云服务器，并解析破地方的内容和页数
# 获取文件大小
def convert_size(self, size_bytes):
# 定义不同单位的转换值
units = ['bytes', 'KB', 'MB', 'GB', 'TB']
i = 0
while size_bytes >= 1024 and i < len(units) - 1:
size_bytes /= 1024
i += 1
return f"{size_bytes:.2f} {units[i]}"
# 查看obs文件是否已经上传
def obsexist(self, file_path):
# # 文件路径
# file_path = 'XQWAnnualReport/2023-10/浙江国祥股份有限公司首次公开发行股票并在主板上市暂缓发行公告.doc'
# 检查文件是否存在
response = obsClient.getObjectMetadata('zzsn', file_path)
if response.status >= 300:
self.getLogger().info('=====文件不存在obs=====')
return True
else:
self.getLogger().info(f'=====文件存在obs========{file_path}')
#uuid 根据时间戳生成 文件名 上传到obs
def getuuid(self):
get_timestamp_uuid = uuid.uuid1() # 根据 时间戳生成 uuid , 保证全球唯一
return get_timestamp_uuid
def uptoOBS(self, pdf_url, name_pdf, type_id, social_code, pathType, taskType, start_time,create_by):
headers = {}
retData = {'state': False, 'type_id': type_id, 'item_id': social_code, 'group_name': '', 'path': '',
'full_path': '',
'category': 'pdf', 'file_size': '', 'status': 1, 'create_by': create_by,
'create_time': '', 'page_size': '', 'content': ''}
headers['User-Agent'] = self.getRandomUserAgent()
for i in range(0, 3):
try:
response = requests.get(pdf_url, headers=headers, verify=False, timeout=20)
file_size = int(response.headers.get('Content-Length'))
break
except:
time.sleep(3)
continue
page_size = 0
name = str(self.getuuid()) + '.pdf'
now_time = time.strftime("%Y-%m")
try:
result = self.getOBSres(pathType, now_time, name, response)
except:
log = self.getLogger()
log.error(f'OBS发送失败')
return retData
with fitz.open(stream=response.content, filetype='pdf') as doc:
page_size = doc.page_count
for page in doc.pages():
retData['content'] += page.get_text()
if page_size < 1:
# pdf解析失败
# print(f'======pdf解析失败=====')
return retData
else:
try:
time_now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
retData['state'] = True
retData['path'] = result['body']['objectUrl'].split('.com')[1]
retData['full_path'] = result['body']['objectUrl']
retData['file_size'] = self.convert_size(file_size)
retData['create_time'] = time_now
retData['page_size'] = page_size
except Exception as e:
state = 0
takeTime = self.getTimeCost(start_time, time.time())
self.recordLog(social_code, taskType, state, takeTime, pdf_url, f'{e}')
return retData
return retData
@retry(tries=3, delay=1)
def getOBSres(self, pathType, now_time, name, response):
result = obsClient.putContent('zzsn', pathType + name, content=response.content)
# resp = obsClient.putFile('zzsn', pathType + name, file_path='要上传的那个文件的本地路径')
return result
cpws/裁判文书网列表正文.py
import base64 #coding=utf-8
#coding=utf-8
import base64 import base64
import datetime import datetime
import json import json
...@@ -78,8 +81,11 @@ url = 'https://wenshu.court.gov.cn/website/parse/rest.q4w' ...@@ -78,8 +81,11 @@ url = 'https://wenshu.court.gov.cn/website/parse/rest.q4w'
#获取登录Cookie #获取登录Cookie
def getCookie(): def getCookie():
# cursor_.execute(
# f"select user,cookie from cpwsw_user where fenghao_time < DATE_SUB(NOW(), INTERVAL 2 HOUR) order by update_time asc limit 1")
cursor_.execute( cursor_.execute(
f"select user,cookie from cpwsw_user where fenghao_time < DATE_SUB(NOW(), INTERVAL 2 HOUR) order by update_time asc limit 1") f"select user,cookie from cpwsw_user where user='18703752600' ")
row = cursor_.fetchall() row = cursor_.fetchall()
if row: if row:
pass pass
...@@ -117,7 +123,8 @@ def getDoc(info_id,userCookie): ...@@ -117,7 +123,8 @@ def getDoc(info_id,userCookie):
'cs':'0' 'cs':'0'
} }
ip = baseCore.get_proxy() ip = baseCore.get_proxy()
res_info = requests.post(url=url,headers=headers,data=data_info,proxies=ip, verify=False,timeout=10) # res_info = requests.post(url=url,headers=headers,data=data_info,proxies=ip, verify=False,timeout=10)
res_info = requests.post(url=url,headers=headers,data=data_info, verify=False,timeout=10)
#{'code': -12, 'description': None, 'secretKey': None, 'result': None, 'success': False} SESSION的值不对 #{'code': -12, 'description': None, 'secretKey': None, 'result': None, 'success': False} SESSION的值不对
#{'code': 9, 'description': '没有权限请求接口,cfg=com.lawyee.judge.dc.parse.dto.SearchDataDsoDTO@docInfoSearch', 'secretKey': None, 'result': None, 'success': False} #{'code': 9, 'description': '没有权限请求接口,cfg=com.lawyee.judge.dc.parse.dto.SearchDataDsoDTO@docInfoSearch', 'secretKey': None, 'result': None, 'success': False}
#'{"code":1,"description":"权限已失效","secretKey":null,"result":null,"success":true}' #'{"code":1,"description":"权限已失效","secretKey":null,"result":null,"success":true}'
...@@ -290,8 +297,10 @@ def getList(keyword,page): ...@@ -290,8 +297,10 @@ def getList(keyword,page):
'cs': '0' 'cs': '0'
} }
proxy=baseCore.get_proxy() proxy=baseCore.get_proxy()
res = requests.post(url=url, headers=headers, data=data,verify=False,timeout=10,proxies=proxy) # res = requests.post(url=url, headers=headers, data=data,verify=False,timeout=10,proxies=proxy)
res = requests.post(url=url, headers=headers, data=data,verify=False,timeout=10)
code = res.json()["code"] code = res.json()["code"]
print(res.json())
if code!=1: if code!=1:
#没有正常返回 #没有正常返回
#记录信息 删除登录信息 #记录信息 删除登录信息
...@@ -324,9 +333,10 @@ def test(): ...@@ -324,9 +333,10 @@ def test():
if __name__=="__main__": if __name__=="__main__":
while True: while True:
kwLstr='浙江银通典当有限责任公司|浙江省化工进出口有限公司|浙江省能源集团有限公司|浙江海港中奥能源有限责任公司|杭州香格里拉饭店有限公司|浙能集团新疆准东能源化工有限公司|温州衢化东南工贸有限公司|义乌产权交易所有限公司|温州机场集团有限公司|浙江浙能电力股份有限公司|浙江工程设计有限公司|浙江国信控股集团有限责任公司|浙江巨化集团进出口有限公司|上海盛东国际集装箱码头有限公司|衢州巨化房地产开发有限公司|浙江省空港融资租赁有限公司|浙江中旅商务会展有限公司|浙江海港集团财务有限公司|浙江浙能港口运营管理有限公司|浙江机场集团保安服务有限公司|新疆塔建三五九建工有限责任公司|浙江能源天然气集团有限公司|浙江华江科技股份有限公司|浙江浙能资产经营管理有限公司|浙江海港黄泽山油品储运有限公司|浙江浙旅投资有限责任公司|浙江海港海洋工程建设有限公司|浙江省能源集团财务有限责任公司|江西省赣浙能源有限公司|温州联合产权交易中心有限公司|浙江省通用航空产业发展有限公司|物产中大期货有限公司|浙江省富浙融资租赁有限公司|宁波机场集团有限公司|浙江省振兴乡村建设投资发展集团有限公司|浙江杭钢融资租赁有限公司|浙江国贸云商控股有限公司|浙江省农村实业发展有限公司|巨化控股有限公司|浙江省国际贸易集团有限公司|浙江机电职业技术学院|浙江头门港投资开发有限公司|伊犁新天煤化工有限责任公司|浙江省农村发展集团农产品有限公司|衢州巨化传媒有限公司|浙江机场投资有限责任公司|浙江中大元通融资租赁有限公司|巨化集团公司兴化实业有限公司|浙江新世纪期货有限公司|巨化集团有限公司|浙旅盛景资本投资有限公司|浙江省医疗健康集团有限公司|浙江歌瑞新材料有限公司|浙江省国贸集团资产经营有限公司|浙能资本控股有限公司|杭州萧山国际机场有限公司|浙江梅苑酒店管理有限公司|浙江国贸集团东方机电工程股份有限公司|上港集团平湖独山港码头有限公司|浙江巨化热电有限公司|浙江省粮食集团有限公司|宁波舟山港集团有限公司|浙江省纺织品进出口集团有限公司|浙江巨化物流有限公司|浙江建设技师学院|浙江杭州临空经济开发有限公司|浙江中大技术进出口集团有限公司|浙江省粮油食品进出口股份有限公司|浙江省石油股份有限公司|浙江空港培训服务咨询有限公司|浙江省机电集团有限公司|浙江省二轻集团有限责任公司|巨化集团上海融资租赁有限公司|浙江巨化股份有限公司|宁波航运交易所有限公司|浙江巨化投资有限公司|浙江省农村发展集团有限公司|浙江省国际贸易集团温州有限公司|浙江巨化化工矿业有限公司|浙江天虹物资贸易有限公司|浙江浙能兴源节能科技有限公司|浙江巨化装备工程集团有限公司|温州瑞平苍高速公路有限公司|上海巨化实业发展有限公司|浙能集团新疆准东煤业有限公司|浙江浙能煤运投资有限责任公司|浙江省新能源投资集团股份有限公司|浙江锦华新材料股份有限公司|浙旅湛景置业有限公司|浙江省交通投资集团财务有限责任公司|杭州钢铁集团有限公司|浙江巨化塑胶有限责任公司|浙江巨化信息技术有限公司|浙江新农都实业有限公司|浙江省万里教育集团|浙江长广（集团）有限责任公司|浙江海港资产管理有限公司|物产中大融资租赁集团有限公司|浙江浙能企业管理培训服务有限公司|浙江省海洋产业投资有限公司|浙江省交通投资集团有限公司|浙江轻工联非融资性担保有限公司|浙江省机场集团有限公司|浙江巨化汉正新材料有限公司|浙江海港内河港口发展有限公司|浙江外事旅游股份有限公司|浙江省浙商资产管理股份有限公司|浙江东方金融控股集团股份有限公司|浙江浙能技术研究院有限公司|浙江经济职业技术学院|浙江巨化清安检测科技有限公司|浙江省国有资本运营有限公司|浙江省土产畜产进出口集团有限公司|浙江巨化能源有限公司|浙江产权交易所有限公司|宁波海运集团有限公司|浙江省中国旅行社集团有限公司|杭州工商信托股份有限公司|浙江省衢州机场管理有限公司|浙江省旅游投资集团有限公司|巨化集团公司塑化厂|同煤浙能麻家梁煤业有限责任公司|浙江轻工联典当有限责任公司|浙江省海港投资运营集团有限公司|衢州衢化宾馆有限公司|舟山普陀山机场有限公司|深圳市巨化华南投资发展有限公司|浙江金华安邦护卫有限公司|浙江海港洋山投资开发有限公司|物产中大资本管理（浙江）有限公司|浙江南方工程咨询管理有限公司|黑龙江绿色农业发展集团有限公司|浙商财产保险股份有限公司|物产中大资产管理（浙江）有限公司|衢州氟硅技术研究院|招商局港口集团股份有限公司|浙江省台州机场管理有限公司|浙江省机电技师学院|巨化集团财务有限责任公司|浙江省电力建设有限公司|浙江省中医药健康产业集团有限公司|浙江巨化化工材料有限公司|浙江浙商金控有限公司|浙江富兴电力燃料有限公司|浙旅蝶来酒店集团有限公司|浙江英特集团股份有限公司|浙江省义乌机场管理有限公司|浙江省农都农产品有限公司|物产中大集团财务有限公司|宁波海运股份有限公司|浙江省建设投资集团股份有限公司|浙江菲达环保科技股份有限公司|浙江海正药业股份有限公司|物产中大集团股份有限公司|浙江运达风电股份有限公司|杭州钢铁股份有限公司|浙商中拓集团股份有限公司|勿忘农集团有限公司|浙江交通科技股份有限公司|巨化集团（香港）有限公司|香港泰纬国际贸易有限公司|浙江能源国际有限公司|常熟市国瑞科技股份有限公司|浙江镇洋发展股份有限公司|浙商银行股份有限公司|浙江物产环保能源股份有限公司|浙江诺和机电股份有限公司|浙江沪杭甬高速公路股份有限公司|宁波远洋运输股份有限公司|浙江大学控股集团有限公司|安邦护卫集团股份有限公司|浙江富建投资管理有限公司|浙江富浙科技有限公司|浙江富浙资产管理有限公司|浙江富浙资本管理有限公司|浙江富物资产管理有限公司|浙江省发展资产经营有限公司|浙江省环境科技有限公司|浙江省盐业集团有限公司|浙江省种业集团有限公司|浙江物产中大医药有限公司|浙江物产元通汽车集团有限公司|浙江物产实业控股（集团）有限公司|物产中大（浙江）产业投资有限公司|物产中大云商有限公司|物产中大元通实业集团有限公司|物产中大元通汽车有限公司|物产中大公用环境投资有限公司|物产中大化工集团有限公司|物产中大医疗健康投资有限公司|物产中大国际学院|物产中大数字科技有限公司|物产中大欧泰有限公司|物产中大物流投资集团有限公司|物产中大财智共享服务（浙江）有限公司|物产中大金属集团有限公司|物产中大金石集团有限公司|物产中大长乐林场有限公司|物产中大集团投资有限公司|南水北调（开化）水务有限公司|太仓中茵建设投资有限公司|安吉浙建投资有限公司|庆元县浙建项目管理有限公司|新昌县浙建投资管理有限公司|新疆阿拉尔上游水利水电工程有限责任公司|杭州财金未来社区股权投资合伙企业（有限合伙）|永嘉县浙建投资有限公司|浙建（兰溪）矿业有限公司|浙建项目管理（杭州）有限公司|浙江基建投资管理有限公司|浙江天台浙建环保科技有限公司|浙江建工建筑工程咨询有限公司|浙江建投创新科技有限公司|浙江建投发展房地产开发有限公司|浙江建投工程物资设备有限公司|浙江建投数字技术有限公司|浙江建投机械租赁有限公司|浙江建投环保工程有限公司|浙江建设商贸物流有限公司|浙江浙建云采贸易有限公司|浙江浙建实业发展有限公司|浙江浙建建筑设计有限公司|浙江浙建美丽乡村建设有限公司|浙江浙建钢结构有限公司|浙江省一建建设集团有限公司|浙江省二建建设集团有限公司|浙江省工业设备安装集团有限公司|浙江省建工集团有限责任公司|浙江省建投交通基础建设集团有限公司|浙江省建材集团有限公司|浙江省建设工程机械集团有限公司|浙江财金未来社区股权投资有限责任公司|衢州市衢江区浙建投资管理有限公司|长兴建图建设投资管理有限公司|长兴浙建投资有限公司|玉环市浙建城镇建设投资有限公司|绍兴市越城区浙建建设项目管理有限公司|绍兴市越城区浙建投资有限公司|苏州浙建地产发展有限公司|长兴浙建城镇建设有限公司|遂昌浙建投资有限公司|长兴浙永建设投资有限公司|阿拉尔浙建城市建设投资有限公司|浙江《机电工程》杂志社有限公司|浙江工匠培训有限公司|浙江康宁咨询服务有限公司|浙江新华体育器材制造有限公司|浙江机电华瑞航空投资有限公司|浙江机电集团投资有限公司|浙江新联民爆器材有限公司|浙江浙商金融服务有限公司|浙江省军工集团股份有限公司|浙江省工业矿产对外贸易有限责任公司|浙江省机电设计研究院有限公司|浙江蓝箭称重技术有限公司|浙江省机械设备进出口有限责任公司|浙江富浙投资有限公司|浙江海正集团有限公司|浙江五金矿产控股有限公司|浙江省医药保健品进出口有限责任公司|浙江省国兴进出口有限公司|浙江省国际贸易集团供应链有限公司|浙江省工艺品进出口有限公司|浙江经贸房地产公司|浙江英特药业有限责任公司|天台国大镕丰酒店管理有限公司|杭州千岛湖温馨岛娱乐旅游有限公司|杭州花港饭店|浙江《江南游报》社有限责任公司|浙江东菱酒店有限公司|杭州花港海航度假酒店有限公司|浙江国际大酒店有限公司|浙江旅游信息中心有限公司|浙江时代国际展览服务有限公司|浙江浙勤服务控股集团有限公司|浙江浙勤集团有限公司|浙江浙旅投数字科技有限公司|浙江省人才发展集团有限公司|浙江省古村落（传统村落）保护利用股权投资基金合伙企业（有限合伙）|浙江省国际投资服务中心有限公司|浙江省国际贸易展览有限公司|浙江省旅工贸有限责任公司|浙江雷迪森物业服务有限公司|浙江雷迪森酒店集团有限公司|舟山市普陀山银海饭店有限公司|雷迪森旅业集团有限公司|上海杭钢凯暄矿业投资有限公司|幸福之江资本运营有限公司|杭州杭钢合金钢铸造有限公司|杭州钢铁厂小型轧钢股份有限公司|浙江东菱商贸有限公司|浙江富春紫光环保股份有限公司|中杭监测技术研究院有限公司|杭州紫云能源综合利用开发有限公司|杭州紫元置业有限公司|浙江杭钢人力资源开发服务有限公司|浙江杭钢健康产业投资管理有限公司|浙江杭钢公管后勤服务有限公司|浙江杭钢动力有限公司|浙江杭钢商贸集团有限公司|浙江杭钢工贸有限公司|浙江杭钢数字科技有限公司|浙江杭钢智谷科技有限公司|浙江杭钢电炉炼钢有限公司|浙江杭钢职业教育集团有限公司|浙江杭钢高速线材有限公司|浙江省冶金研究院有限公司|浙江省工业设计研究院有限公司|浙江省环保集团有限公司|浙江省遂昌金矿有限公司|浙江紫汇资产管理有限公司|浙江紫臻物业管理服务有限公司|浙江钢联控股有限公司|温州杭钢水务有限公司|上海华山康健医疗有限公司|台州台信企业管理合伙企业（有限合伙）|浙江中天东方氟硅材料股份有限公司|浙江巨化环保科技有限公司|浙江巨柯私募基金管理有限公司|浙江巨荣石油化工销售有限公司|浙江晋巨化工有限公司|浙能巨化（浙江自贸区）股权投资基金合伙企业（有限合伙）|中核浙能能源有限公司|中海油绿能港浙江宁波能源有限公司|伊犁新矿煤业有限责任公司|内蒙古同煤鄂尔多斯矿业投资有限公司|国家管网集团浙江省天然气管网有限公司|浙江浙能产业研究院有限公司|浙江浙能物业发展有限公司|浙江浙能绿城体育文化发展有限公司|浙江省白马湖实验室有限公司|浙江职业足球俱乐部有限公司|嘉兴公路建设投资有限公司|嘉兴市嘉萧高速公路投资开发有限公司|德清县杭绕高速有限公司|杭州都市高速公路有限公司|浙商食品集团有限公司|浙江临金高速公路有限公司|浙江义东高速公路有限公司|浙江乐清湾高速公路有限公司|浙江交投交通建设管理有限公司|浙江交投太平交通基础设施股权投资基金（有限合伙）|浙江交投高速公路建设管理有限公司|浙江交投高速公路运营管理有限公司|浙江交通资源投资集团有限公司|浙江台州沈海高速公路有限公司|浙江台州甬台温高速公路有限公司|浙江宁波杭甬复线三期高速公路有限公司|浙江宁波甬台温高速公路有限公司|浙江数智交院科技股份有限公司|浙江景文高速公路有限公司|浙江杭宁高速公路有限责任公司|浙江杭宣高速公路有限公司|浙江杭新景高速公路有限公司|浙江杭海城际铁路有限公司|浙江杭温铁路有限公司|浙江杭甬复线宁波一期高速公路有限公司|浙江杭绍甬高速公路有限公司|浙江沪平盐铁路有限公司|浙江温州市域铁路一号线有限公司|浙江甬舟复线一期高速公路有限公司|浙江省交投控股集团有限公司|浙江省交通投资集团高速公路管理有限公司|浙江省商业集团有限公司|浙江省海运集团股份有限公司|浙江省经济建设投资有限公司|浙江省轨道交通建设管理集团有限公司|浙江省轨道交通运营管理集团有限公司|浙江省铁路发展控股集团有限责任公司|浙江省长三角投资有限公司|浙江舟山北向大通道有限公司|浙江衢丽铁路有限公司|浙江衢松铁路有限公司|浙江诸永高速公路有限公司|浙江路产城发展集团有限公司|浙江金华甬金衢上高速公路有限公司|浙江高信技术股份有限公司|浙江高速物流有限公司|温州市文泰高速公路有限公司|温州市瑞文高速公路有限公司|绍兴柯桥杭金衢联络线高速公路有限公司|金华市东永高速投资有限公司|东港投资发展集团有限公司|杭州农发原乡人农特产有限公司|杭州千岛湖鲟龙科技股份有限公司|浙江农发产业投资有限公司|浙江省现代农业研究会|芜湖信农硬科技投资合伙企业（有限合伙）|黑龙江亚欧牧业有限公司|浙江四港联动发展有限公司|浙江电子口岸有限公司|浙江空港商业经营管理有限责任公司|浙江空港数字科技有限公司|浙江空港资本控股有限公司|上海大宗商品仓单登记有限责任公司|宁波舟山港铁矿石储运有限公司|杭州港务集团有限公司|浙江中澳现代产业园有限公司|浙江义迪通供应链服务有限公司|浙江之迪控股有限公司|浙江海港国际联运有限公司|浙江海港大宗商品交易中心有限公司|浙江海港引航服务有限公司|浙江船舶交易市场有限公司|杭州富格企业管理合伙企业（有限合伙）|杭州松下马达有限公司|汇孚集团有限公司|浙江信联钢铁有限公司|浙江广杰投资管理有限公司|浙江建设融资租赁有限公司|浙江杰尚投资管理有限公司|浙江申达塑料机械有限公司|浙江申达机器制造股份有限公司|浙江省二轻供销总公司|浙江省二轻商业经营管理有限公司|浙江省二轻房地产开发有限公司|浙江省工美控股有限公司|浙江省工艺美术研究院有限公司|浙江省皮革塑料有限公司|浙江省艺创投资发展股份有限公司|浙江省艺创文旅发展有限公司|安邦护卫（浙江）公共安全智慧科技有限公司|浙江丽水安邦护卫有限公司|浙江台州安邦护卫有限公司|浙江嘉兴安邦护卫有限公司|浙江宁波安邦护卫有限公司|浙江安邦护卫安全服务有限公司|浙江安邦护卫科技服务有限公司|浙江杭州安邦护卫有限公司|浙江温州安邦护卫有限公司|浙江湖州安邦护卫有限公司|浙江绍兴安邦护卫有限公司|浙江舟山安邦护卫有限公司|浙江衢州安邦护卫有限公司|上海浙大科技发展有限公司|杭州启真未来创新股权投资合伙企业（有限合伙）|杭州浙大动物医院有限公司|杭州浙大文化创意发展有限公司|杭州紫金港未来创新投资合伙企业（有限合伙）|杭州网新信息控股有限公司|杭州西投启真脑机智能产业运营有限公司|浙江启真人才发展有限公司|浙江大学农业科技园有限公司|浙江大学创新技术研究院有限公司|浙江大学城乡规划设计研究院有限公司|浙江大学杭州国际科创中心发展有限公司|浙江大学科技园发展有限公司|浙江大学能源工程设计研究院有限公司|浙江浙大列车智能化工程技术研究中心有限公司|浙江浙大圆正科技创新服务有限公司|浙江浙大新宇物业集团有限公司|浙江浙大科创集团有限公司|浙江浙大西投脑机智能科技有限公司|浙江钱塘机器人及智能装备研究有限公司|丽水市廉合产权交易有限公司|北京中产智合咨询服务中心（有限合伙）|北京金马甲产权网络交易有限公司|台州市产权交易所有限公司|嘉兴市产权交易有限公司|湖州市联合产权交易有限公司|绍兴市产权交易有限公司|舟山市产权交易中心有限责任公司|衢州市产权交易中心有限公司|浙江省三建建设集团有限公司|' # kwLstr='巨化集团上海融资租赁有限公司|浙江巨化股份有限公司|宁波航运交易所有限公司|浙江巨化投资有限公司|浙江省农村发展集团有限公司|浙江省国际贸易集团温州有限公司|浙江巨化化工矿业有限公司|浙江天虹物资贸易有限公司|浙江浙能兴源节能科技有限公司|浙江巨化装备工程集团有限公司|温州瑞平苍高速公路有限公司|上海巨化实业发展有限公司|浙能集团新疆准东煤业有限公司|浙江浙能煤运投资有限责任公司|浙江省新能源投资集团股份有限公司|浙江锦华新材料股份有限公司|浙旅湛景置业有限公司|浙江省交通投资集团财务有限责任公司|杭州钢铁集团有限公司|浙江巨化塑胶有限责任公司|浙江巨化信息技术有限公司|浙江新农都实业有限公司|浙江省万里教育集团|浙江长广（集团）有限责任公司|浙江海港资产管理有限公司|物产中大融资租赁集团有限公司|浙江浙能企业管理培训服务有限公司|浙江省海洋产业投资有限公司|浙江省交通投资集团有限公司|浙江轻工联非融资性担保有限公司|浙江省机场集团有限公司|浙江巨化汉正新材料有限公司|浙江海港内河港口发展有限公司|浙江外事旅游股份有限公司|浙江省浙商资产管理股份有限公司|浙江东方金融控股集团股份有限公司|浙江浙能技术研究院有限公司|浙江经济职业技术学院|浙江巨化清安检测科技有限公司|浙江省国有资本运营有限公司|浙江省土产畜产进出口集团有限公司|浙江巨化能源有限公司|浙江产权交易所有限公司|宁波海运集团有限公司|浙江省中国旅行社集团有限公司|杭州工商信托股份有限公司|浙江省衢州机场管理有限公司|浙江省旅游投资集团有限公司|巨化集团公司塑化厂|同煤浙能麻家梁煤业有限责任公司|浙江轻工联典当有限责任公司|浙江省海港投资运营集团有限公司|衢州衢化宾馆有限公司|舟山普陀山机场有限公司|深圳市巨化华南投资发展有限公司|浙江金华安邦护卫有限公司|浙江海港洋山投资开发有限公司|物产中大资本管理（浙江）有限公司|浙江南方工程咨询管理有限公司|黑龙江绿色农业发展集团有限公司|浙商财产保险股份有限公司|物产中大资产管理（浙江）有限公司|衢州氟硅技术研究院|招商局港口集团股份有限公司|浙江省台州机场管理有限公司|浙江省机电技师学院|巨化集团财务有限责任公司|浙江省电力建设有限公司|浙江省中医药健康产业集团有限公司|浙江巨化化工材料有限公司|浙江浙商金控有限公司|浙江富兴电力燃料有限公司|浙旅蝶来酒店集团有限公司|浙江英特集团股份有限公司|浙江省义乌机场管理有限公司|浙江省农都农产品有限公司|物产中大集团财务有限公司|宁波海运股份有限公司|浙江省建设投资集团股份有限公司|浙江菲达环保科技股份有限公司|浙江海正药业股份有限公司|物产中大集团股份有限公司|浙江运达风电股份有限公司|杭州钢铁股份有限公司|浙商中拓集团股份有限公司|勿忘农集团有限公司|浙江交通科技股份有限公司|巨化集团（香港）有限公司|香港泰纬国际贸易有限公司|浙江能源国际有限公司|常熟市国瑞科技股份有限公司|浙江镇洋发展股份有限公司|浙商银行股份有限公司|浙江物产环保能源股份有限公司|浙江诺和机电股份有限公司|浙江沪杭甬高速公路股份有限公司|宁波远洋运输股份有限公司|浙江大学控股集团有限公司|安邦护卫集团股份有限公司|浙江富建投资管理有限公司|浙江富浙科技有限公司|浙江富浙资产管理有限公司|浙江富浙资本管理有限公司|浙江富物资产管理有限公司|浙江省发展资产经营有限公司|浙江省环境科技有限公司|浙江省盐业集团有限公司|浙江省种业集团有限公司|浙江物产中大医药有限公司|浙江物产元通汽车集团有限公司|浙江物产实业控股（集团）有限公司|物产中大（浙江）产业投资有限公司|物产中大云商有限公司|物产中大元通实业集团有限公司|物产中大元通汽车有限公司|物产中大公用环境投资有限公司|物产中大化工集团有限公司|物产中大医疗健康投资有限公司|物产中大国际学院|物产中大数字科技有限公司|物产中大欧泰有限公司|物产中大物流投资集团有限公司|物产中大财智共享服务（浙江）有限公司|物产中大金属集团有限公司|物产中大金石集团有限公司|物产中大长乐林场有限公司|物产中大集团投资有限公司|南水北调（开化）水务有限公司|太仓中茵建设投资有限公司|安吉浙建投资有限公司|庆元县浙建项目管理有限公司|新昌县浙建投资管理有限公司|新疆阿拉尔上游水利水电工程有限责任公司|杭州财金未来社区股权投资合伙企业（有限合伙）|永嘉县浙建投资有限公司|浙建（兰溪）矿业有限公司|浙建项目管理（杭州）有限公司|浙江基建投资管理有限公司|浙江天台浙建环保科技有限公司|浙江建工建筑工程咨询有限公司|浙江建投创新科技有限公司|浙江建投发展房地产开发有限公司|浙江建投工程物资设备有限公司|浙江建投数字技术有限公司|浙江建投机械租赁有限公司|浙江建投环保工程有限公司|浙江建设商贸物流有限公司|浙江浙建云采贸易有限公司|浙江浙建实业发展有限公司|浙江浙建建筑设计有限公司|浙江浙建美丽乡村建设有限公司|浙江浙建钢结构有限公司|浙江省一建建设集团有限公司|浙江省二建建设集团有限公司|浙江省工业设备安装集团有限公司|浙江省建工集团有限责任公司|浙江省建投交通基础建设集团有限公司|浙江省建材集团有限公司|浙江省建设工程机械集团有限公司|浙江财金未来社区股权投资有限责任公司|衢州市衢江区浙建投资管理有限公司|长兴建图建设投资管理有限公司|长兴浙建投资有限公司|玉环市浙建城镇建设投资有限公司|绍兴市越城区浙建建设项目管理有限公司|绍兴市越城区浙建投资有限公司|苏州浙建地产发展有限公司|长兴浙建城镇建设有限公司|遂昌浙建投资有限公司|长兴浙永建设投资有限公司|阿拉尔浙建城市建设投资有限公司|浙江《机电工程》杂志社有限公司|浙江工匠培训有限公司|浙江康宁咨询服务有限公司|浙江新华体育器材制造有限公司|浙江机电华瑞航空投资有限公司|浙江机电集团投资有限公司|浙江新联民爆器材有限公司|浙江浙商金融服务有限公司|浙江省军工集团股份有限公司|浙江省工业矿产对外贸易有限责任公司|浙江省机电设计研究院有限公司|浙江蓝箭称重技术有限公司|浙江省机械设备进出口有限责任公司|浙江富浙投资有限公司|浙江海正集团有限公司|浙江五金矿产控股有限公司|浙江省医药保健品进出口有限责任公司|浙江省国兴进出口有限公司|浙江省国际贸易集团供应链有限公司|浙江省工艺品进出口有限公司|浙江经贸房地产公司|浙江英特药业有限责任公司|天台国大镕丰酒店管理有限公司|杭州千岛湖温馨岛娱乐旅游有限公司|杭州花港饭店|浙江《江南游报》社有限责任公司|浙江东菱酒店有限公司|杭州花港海航度假酒店有限公司|浙江国际大酒店有限公司|浙江旅游信息中心有限公司|浙江时代国际展览服务有限公司|浙江浙勤服务控股集团有限公司|浙江浙勤集团有限公司|浙江浙旅投数字科技有限公司|浙江省人才发展集团有限公司|浙江省古村落（传统村落）保护利用股权投资基金合伙企业（有限合伙）|浙江省国际投资服务中心有限公司|浙江省国际贸易展览有限公司|浙江省旅工贸有限责任公司|浙江雷迪森物业服务有限公司|浙江雷迪森酒店集团有限公司|舟山市普陀山银海饭店有限公司|雷迪森旅业集团有限公司|上海杭钢凯暄矿业投资有限公司|幸福之江资本运营有限公司|杭州杭钢合金钢铸造有限公司|杭州钢铁厂小型轧钢股份有限公司|浙江东菱商贸有限公司|浙江富春紫光环保股份有限公司|中杭监测技术研究院有限公司|杭州紫云能源综合利用开发有限公司|杭州紫元置业有限公司|浙江杭钢人力资源开发服务有限公司|浙江杭钢健康产业投资管理有限公司|浙江杭钢公管后勤服务有限公司|浙江杭钢动力有限公司|浙江杭钢商贸集团有限公司|浙江杭钢工贸有限公司|浙江杭钢数字科技有限公司|浙江杭钢智谷科技有限公司|浙江杭钢电炉炼钢有限公司|浙江杭钢职业教育集团有限公司|浙江杭钢高速线材有限公司|浙江省冶金研究院有限公司|浙江省工业设计研究院有限公司|浙江省环保集团有限公司|浙江省遂昌金矿有限公司|浙江紫汇资产管理有限公司|浙江紫臻物业管理服务有限公司|浙江钢联控股有限公司|温州杭钢水务有限公司|上海华山康健医疗有限公司|台州台信企业管理合伙企业（有限合伙）|浙江中天东方氟硅材料股份有限公司|浙江巨化环保科技有限公司|浙江巨柯私募基金管理有限公司|浙江巨荣石油化工销售有限公司|浙江晋巨化工有限公司|浙能巨化（浙江自贸区）股权投资基金合伙企业（有限合伙）|中核浙能能源有限公司|中海油绿能港浙江宁波能源有限公司|伊犁新矿煤业有限责任公司|内蒙古同煤鄂尔多斯矿业投资有限公司|国家管网集团浙江省天然气管网有限公司|浙江浙能产业研究院有限公司|浙江浙能物业发展有限公司|浙江浙能绿城体育文化发展有限公司|浙江省白马湖实验室有限公司|浙江职业足球俱乐部有限公司|嘉兴公路建设投资有限公司|嘉兴市嘉萧高速公路投资开发有限公司|德清县杭绕高速有限公司|杭州都市高速公路有限公司|浙商食品集团有限公司|浙江临金高速公路有限公司|浙江义东高速公路有限公司|浙江乐清湾高速公路有限公司|浙江交投交通建设管理有限公司|浙江交投太平交通基础设施股权投资基金（有限合伙）|浙江交投高速公路建设管理有限公司|浙江交投高速公路运营管理有限公司|浙江交通资源投资集团有限公司|浙江台州沈海高速公路有限公司|浙江台州甬台温高速公路有限公司|浙江宁波杭甬复线三期高速公路有限公司|浙江宁波甬台温高速公路有限公司|浙江数智交院科技股份有限公司|浙江景文高速公路有限公司|浙江杭宁高速公路有限责任公司|浙江杭宣高速公路有限公司|浙江杭新景高速公路有限公司|浙江杭海城际铁路有限公司|浙江杭温铁路有限公司|浙江杭甬复线宁波一期高速公路有限公司|浙江杭绍甬高速公路有限公司|浙江沪平盐铁路有限公司|浙江温州市域铁路一号线有限公司|浙江甬舟复线一期高速公路有限公司|浙江省交投控股集团有限公司|浙江省交通投资集团高速公路管理有限公司|浙江省商业集团有限公司|浙江省海运集团股份有限公司|浙江省经济建设投资有限公司|浙江省轨道交通建设管理集团有限公司|浙江省轨道交通运营管理集团有限公司|浙江省铁路发展控股集团有限责任公司|浙江省长三角投资有限公司|浙江舟山北向大通道有限公司|浙江衢丽铁路有限公司|浙江衢松铁路有限公司|浙江诸永高速公路有限公司|浙江路产城发展集团有限公司|浙江金华甬金衢上高速公路有限公司|浙江高信技术股份有限公司|浙江高速物流有限公司|温州市文泰高速公路有限公司|温州市瑞文高速公路有限公司|绍兴柯桥杭金衢联络线高速公路有限公司|金华市东永高速投资有限公司|东港投资发展集团有限公司|杭州农发原乡人农特产有限公司|杭州千岛湖鲟龙科技股份有限公司|浙江农发产业投资有限公司|浙江省现代农业研究会|芜湖信农硬科技投资合伙企业（有限合伙）|黑龙江亚欧牧业有限公司|浙江四港联动发展有限公司|浙江电子口岸有限公司|浙江空港商业经营管理有限责任公司|浙江空港数字科技有限公司|浙江空港资本控股有限公司|上海大宗商品仓单登记有限责任公司|宁波舟山港铁矿石储运有限公司|杭州港务集团有限公司|浙江中澳现代产业园有限公司|浙江义迪通供应链服务有限公司|浙江之迪控股有限公司|浙江海港国际联运有限公司|浙江海港大宗商品交易中心有限公司|浙江海港引航服务有限公司|浙江船舶交易市场有限公司|杭州富格企业管理合伙企业（有限合伙）|杭州松下马达有限公司|汇孚集团有限公司|浙江信联钢铁有限公司|浙江广杰投资管理有限公司|浙江建设融资租赁有限公司|浙江杰尚投资管理有限公司|浙江申达塑料机械有限公司|浙江申达机器制造股份有限公司|浙江省二轻供销总公司|浙江省二轻商业经营管理有限公司|浙江省二轻房地产开发有限公司|浙江省工美控股有限公司|浙江省工艺美术研究院有限公司|浙江省皮革塑料有限公司|浙江省艺创投资发展股份有限公司|浙江省艺创文旅发展有限公司|安邦护卫（浙江）公共安全智慧科技有限公司|浙江丽水安邦护卫有限公司|浙江台州安邦护卫有限公司|浙江嘉兴安邦护卫有限公司|浙江宁波安邦护卫有限公司|浙江安邦护卫安全服务有限公司|浙江安邦护卫科技服务有限公司|浙江杭州安邦护卫有限公司|浙江温州安邦护卫有限公司|浙江湖州安邦护卫有限公司|浙江绍兴安邦护卫有限公司|浙江舟山安邦护卫有限公司|浙江衢州安邦护卫有限公司|上海浙大科技发展有限公司|杭州启真未来创新股权投资合伙企业（有限合伙）|杭州浙大动物医院有限公司|杭州浙大文化创意发展有限公司|杭州紫金港未来创新投资合伙企业（有限合伙）|杭州网新信息控股有限公司|杭州西投启真脑机智能产业运营有限公司|浙江启真人才发展有限公司|浙江大学农业科技园有限公司|浙江大学创新技术研究院有限公司|浙江大学城乡规划设计研究院有限公司|浙江大学杭州国际科创中心发展有限公司|浙江大学科技园发展有限公司|浙江大学能源工程设计研究院有限公司|浙江浙大列车智能化工程技术研究中心有限公司|浙江浙大圆正科技创新服务有限公司|浙江浙大新宇物业集团有限公司|浙江浙大科创集团有限公司|浙江浙大西投脑机智能科技有限公司|浙江钱塘机器人及智能装备研究有限公司|丽水市廉合产权交易有限公司|北京中产智合咨询服务中心（有限合伙）|北京金马甲产权网络交易有限公司|台州市产权交易所有限公司|嘉兴市产权交易有限公司|湖州市联合产权交易有限公司|绍兴市产权交易有限公司|舟山市产权交易中心有限责任公司|衢州市产权交易中心有限公司|浙江省三建建设集团有限公司|浙江银通典当有限责任公司|浙江省化工进出口有限公司|浙江省能源集团有限公司|浙江海港中奥能源有限责任公司|杭州香格里拉饭店有限公司|浙能集团新疆准东能源化工有限公司|温州衢化东南工贸有限公司|义乌产权交易所有限公司|温州机场集团有限公司|浙江浙能电力股份有限公司|浙江工程设计有限公司|浙江国信控股集团有限责任公司|浙江巨化集团进出口有限公司|上海盛东国际集装箱码头有限公司|衢州巨化房地产开发有限公司|浙江省空港融资租赁有限公司|浙江中旅商务会展有限公司|浙江海港集团财务有限公司|浙江浙能港口运营管理有限公司|浙江机场集团保安服务有限公司|新疆塔建三五九建工有限责任公司|浙江能源天然气集团有限公司|浙江华江科技股份有限公司|浙江浙能资产经营管理有限公司|浙江海港黄泽山油品储运有限公司|浙江浙旅投资有限责任公司|浙江海港海洋工程建设有限公司|浙江省能源集团财务有限责任公司|江西省赣浙能源有限公司|温州联合产权交易中心有限公司|浙江省通用航空产业发展有限公司|物产中大期货有限公司|浙江省富浙融资租赁有限公司|宁波机场集团有限公司|浙江省振兴乡村建设投资发展集团有限公司|浙江杭钢融资租赁有限公司|浙江国贸云商控股有限公司|浙江省农村实业发展有限公司|巨化控股有限公司|浙江省国际贸易集团有限公司|浙江机电职业技术学院|浙江头门港投资开发有限公司|伊犁新天煤化工有限责任公司|浙江省农村发展集团农产品有限公司|衢州巨化传媒有限公司|浙江机场投资有限责任公司|浙江中大元通融资租赁有限公司|巨化集团公司兴化实业有限公司|浙江新世纪期货有限公司|巨化集团有限公司|浙旅盛景资本投资有限公司|浙江省医疗健康集团有限公司|浙江歌瑞新材料有限公司|浙江省国贸集团资产经营有限公司|浙能资本控股有限公司|杭州萧山国际机场有限公司|浙江梅苑酒店管理有限公司|浙江国贸集团东方机电工程股份有限公司|上港集团平湖独山港码头有限公司|浙江巨化热电有限公司|浙江省粮食集团有限公司|宁波舟山港集团有限公司|浙江省纺织品进出口集团有限公司|浙江巨化物流有限公司|浙江建设技师学院|浙江杭州临空经济开发有限公司|浙江中大技术进出口集团有限公司|浙江省粮油食品进出口股份有限公司|浙江省石油股份有限公司|浙江空港培训服务咨询有限公司|浙江省机电集团有限公司|浙江省二轻集团有限责任公司'
kwLstr='巨化集团上海融资租赁有限公司|浙江巨化股份有限公司|宁波航运交易所有限公司|浙江巨化投资有限公司|浙江省农村发展集团有限公司|浙江省国际贸易集团温州有限公司|浙江巨化化工矿业有限公司|浙江天虹物资贸易有限公司|浙江浙能兴源节能科技有限公司|浙江巨化装备工程集团有限公司|温州瑞平苍高速公路有限公司|上海巨化实业发展有限公司|浙能集团新疆准东煤业有限公司|浙江浙能煤运投资有限责任公司|浙江省新能源投资集团股份有限公司|浙江锦华新材料股份有限公司|浙旅湛景置业有限公司|浙江省交通投资集团财务有限责任公司|杭州钢铁集团有限公司|浙江巨化塑胶有限责任公司|浙江巨化信息技术有限公司|浙江新农都实业有限公司|浙江省万里教育集团|浙江长广（集团）有限责任公司|浙江海港资产管理有限公司|物产中大融资租赁集团有限公司|浙江浙能企业管理培训服务有限公司|浙江省海洋产业投资有限公司|浙江省交通投资集团有限公司|浙江轻工联非融资性担保有限公司|浙江省机场集团有限公司|浙江巨化汉正新材料有限公司|浙江海港内河港口发展有限公司|浙江外事旅游股份有限公司|浙江省浙商资产管理股份有限公司|浙江东方金融控股集团股份有限公司|浙江浙能技术研究院有限公司|浙江经济职业技术学院|浙江巨化清安检测科技有限公司|浙江省国有资本运营有限公司|浙江省土产畜产进出口集团有限公司|浙江巨化能源有限公司|浙江产权交易所有限公司|宁波海运集团有限公司|浙江省中国旅行社集团有限公司|杭州工商信托股份有限公司|浙江省衢州机场管理有限公司|浙江省旅游投资集团有限公司|巨化集团公司塑化厂|同煤浙能麻家梁煤业有限责任公司|浙江轻工联典当有限责任公司|浙江省海港投资运营集团有限公司|衢州衢化宾馆有限公司|舟山普陀山机场有限公司|深圳市巨化华南投资发展有限公司|浙江金华安邦护卫有限公司|浙江海港洋山投资开发有限公司|物产中大资本管理（浙江）有限公司|浙江南方工程咨询管理有限公司|黑龙江绿色农业发展集团有限公司|浙商财产保险股份有限公司|物产中大资产管理（浙江）有限公司|衢州氟硅技术研究院|招商局港口集团股份有限公司|浙江省台州机场管理有限公司|浙江省机电技师学院|巨化集团财务有限责任公司|浙江省电力建设有限公司|浙江省中医药健康产业集团有限公司|浙江巨化化工材料有限公司|浙江浙商金控有限公司|浙江富兴电力燃料有限公司|浙旅蝶来酒店集团有限公司|浙江英特集团股份有限公司|浙江省义乌机场管理有限公司|浙江省农都农产品有限公司|物产中大集团财务有限公司|宁波海运股份有限公司|浙江省建设投资集团股份有限公司|浙江菲达环保科技股份有限公司|浙江海正药业股份有限公司|物产中大集团股份有限公司|浙江运达风电股份有限公司|杭州钢铁股份有限公司|浙商中拓集团股份有限公司|勿忘农集团有限公司|浙江交通科技股份有限公司|巨化集团（香港）有限公司|香港泰纬国际贸易有限公司|浙江能源国际有限公司|常熟市国瑞科技股份有限公司|浙江镇洋发展股份有限公司|浙商银行股份有限公司|浙江物产环保能源股份有限公司|浙江诺和机电股份有限公司|浙江沪杭甬高速公路股份有限公司|宁波远洋运输股份有限公司|浙江大学控股集团有限公司|安邦护卫集团股份有限公司|浙江富建投资管理有限公司|浙江富浙科技有限公司|浙江富浙资产管理有限公司|浙江富浙资本管理有限公司|浙江富物资产管理有限公司|浙江省发展资产经营有限公司|浙江省环境科技有限公司|浙江省盐业集团有限公司|浙江省种业集团有限公司|浙江物产中大医药有限公司|浙江物产元通汽车集团有限公司|浙江物产实业控股（集团）有限公司|物产中大（浙江）产业投资有限公司|物产中大云商有限公司|物产中大元通实业集团有限公司|物产中大元通汽车有限公司|物产中大公用环境投资有限公司|物产中大化工集团有限公司|物产中大医疗健康投资有限公司|物产中大国际学院|物产中大数字科技有限公司|物产中大欧泰有限公司|物产中大物流投资集团有限公司|物产中大财智共享服务（浙江）有限公司|物产中大金属集团有限公司|物产中大金石集团有限公司|物产中大长乐林场有限公司|物产中大集团投资有限公司|南水北调（开化）水务有限公司|太仓中茵建设投资有限公司|安吉浙建投资有限公司|庆元县浙建项目管理有限公司|新昌县浙建投资管理有限公司|新疆阿拉尔上游水利水电工程有限责任公司|杭州财金未来社区股权投资合伙企业（有限合伙）|永嘉县浙建投资有限公司|浙建（兰溪）矿业有限公司|浙建项目管理（杭州）有限公司|浙江基建投资管理有限公司|浙江天台浙建环保科技有限公司|浙江建工建筑工程咨询有限公司|浙江建投创新科技有限公司|浙江建投发展房地产开发有限公司|浙江建投工程物资设备有限公司|浙江建投数字技术有限公司|浙江建投机械租赁有限公司|浙江建投环保工程有限公司|浙江建设商贸物流有限公司|浙江浙建云采贸易有限公司|浙江浙建实业发展有限公司|浙江浙建建筑设计有限公司|浙江浙建美丽乡村建设有限公司|浙江浙建钢结构有限公司|浙江省一建建设集团有限公司|浙江省二建建设集团有限公司|浙江省工业设备安装集团有限公司|浙江省建工集团有限责任公司|浙江省建投交通基础建设集团有限公司|浙江省建材集团有限公司|浙江省建设工程机械集团有限公司|浙江财金未来社区股权投资有限责任公司|衢州市衢江区浙建投资管理有限公司|长兴建图建设投资管理有限公司|长兴浙建投资有限公司|玉环市浙建城镇建设投资有限公司|绍兴市越城区浙建建设项目管理有限公司|绍兴市越城区浙建投资有限公司|苏州浙建地产发展有限公司|长兴浙建城镇建设有限公司|遂昌浙建投资有限公司|长兴浙永建设投资有限公司|阿拉尔浙建城市建设投资有限公司|浙江《机电工程》杂志社有限公司|浙江工匠培训有限公司|浙江康宁咨询服务有限公司|浙江新华体育器材制造有限公司|浙江机电华瑞航空投资有限公司|浙江机电集团投资有限公司|浙江新联民爆器材有限公司|浙江浙商金融服务有限公司|浙江省军工集团股份有限公司|浙江省工业矿产对外贸易有限责任公司|浙江省机电设计研究院有限公司|浙江蓝箭称重技术有限公司|浙江省机械设备进出口有限责任公司|浙江富浙投资有限公司|浙江海正集团有限公司|浙江五金矿产控股有限公司|浙江省医药保健品进出口有限责任公司|浙江省国兴进出口有限公司|浙江省国际贸易集团供应链有限公司|浙江省工艺品进出口有限公司|浙江经贸房地产公司|浙江英特药业有限责任公司|天台国大镕丰酒店管理有限公司|杭州千岛湖温馨岛娱乐旅游有限公司|杭州花港饭店|浙江《江南游报》社有限责任公司|浙江东菱酒店有限公司|杭州花港海航度假酒店有限公司|浙江国际大酒店有限公司|浙江旅游信息中心有限公司|浙江时代国际展览服务有限公司|浙江浙勤服务控股集团有限公司|浙江浙勤集团有限公司|浙江浙旅投数字科技有限公司|浙江省人才发展集团有限公司|浙江省古村落（传统村落）保护利用股权投资基金合伙企业（有限合伙）|浙江省国际投资服务中心有限公司|浙江省国际贸易展览有限公司|浙江省旅工贸有限责任公司|浙江雷迪森物业服务有限公司|浙江雷迪森酒店集团有限公司|舟山市普陀山银海饭店有限公司|雷迪森旅业集团有限公司|上海杭钢凯暄矿业投资有限公司|幸福之江资本运营有限公司|杭州杭钢合金钢铸造有限公司|杭州钢铁厂小型轧钢股份有限公司|浙江东菱商贸有限公司|浙江富春紫光环保股份有限公司|中杭监测技术研究院有限公司|杭州紫云能源综合利用开发有限公司|杭州紫元置业有限公司|浙江杭钢人力资源开发服务有限公司|浙江杭钢健康产业投资管理有限公司|浙江杭钢公管后勤服务有限公司|浙江杭钢动力有限公司|浙江杭钢商贸集团有限公司|浙江杭钢工贸有限公司|浙江杭钢数字科技有限公司|浙江杭钢智谷科技有限公司|浙江杭钢电炉炼钢有限公司|浙江杭钢职业教育集团有限公司|浙江杭钢高速线材有限公司|浙江省冶金研究院有限公司|浙江省工业设计研究院有限公司|浙江省环保集团有限公司|浙江省遂昌金矿有限公司|浙江紫汇资产管理有限公司|浙江紫臻物业管理服务有限公司|浙江钢联控股有限公司|温州杭钢水务有限公司|上海华山康健医疗有限公司|台州台信企业管理合伙企业（有限合伙）|浙江中天东方氟硅材料股份有限公司|浙江巨化环保科技有限公司|浙江巨柯私募基金管理有限公司|浙江巨荣石油化工销售有限公司|浙江晋巨化工有限公司|浙能巨化（浙江自贸区）股权投资基金合伙企业（有限合伙）|中核浙能能源有限公司|中海油绿能港浙江宁波能源有限公司|伊犁新矿煤业有限责任公司|内蒙古同煤鄂尔多斯矿业投资有限公司|国家管网集团浙江省天然气管网有限公司|浙江浙能产业研究院有限公司|浙江浙能物业发展有限公司|浙江浙能绿城体育文化发展有限公司|浙江省白马湖实验室有限公司|浙江职业足球俱乐部有限公司|嘉兴公路建设投资有限公司|嘉兴市嘉萧高速公路投资开发有限公司|德清县杭绕高速有限公司|杭州都市高速公路有限公司|浙商食品集团有限公司|浙江临金高速公路有限公司|浙江义东高速公路有限公司|浙江乐清湾高速公路有限公司|浙江交投交通建设管理有限公司|浙江交投太平交通基础设施股权投资基金（有限合伙）|浙江交投高速公路建设管理有限公司|浙江交投高速公路运营管理有限公司|浙江交通资源投资集团有限公司|浙江台州沈海高速公路有限公司|浙江台州甬台温高速公路有限公司|浙江宁波杭甬复线三期高速公路有限公司|浙江宁波甬台温高速公路有限公司|浙江数智交院科技股份有限公司|浙江景文高速公路有限公司|浙江杭宁高速公路有限责任公司|浙江杭宣高速公路有限公司|浙江杭新景高速公路有限公司|浙江杭海城际铁路有限公司|浙江杭温铁路有限公司|浙江杭甬复线宁波一期高速公路有限公司|浙江杭绍甬高速公路有限公司|浙江沪平盐铁路有限公司|浙江温州市域铁路一号线有限公司|浙江甬舟复线一期高速公路有限公司|浙江省交投控股集团有限公司|浙江省交通投资集团高速公路管理有限公司|浙江省商业集团有限公司|浙江省海运集团股份有限公司|浙江省经济建设投资有限公司|浙江省轨道交通建设管理集团有限公司|浙江省轨道交通运营管理集团有限公司|浙江省铁路发展控股集团有限责任公司|浙江省长三角投资有限公司|浙江舟山北向大通道有限公司|浙江衢丽铁路有限公司|浙江衢松铁路有限公司|浙江诸永高速公路有限公司|浙江路产城发展集团有限公司|浙江金华甬金衢上高速公路有限公司|浙江高信技术股份有限公司|浙江高速物流有限公司|温州市文泰高速公路有限公司|温州市瑞文高速公路有限公司|绍兴柯桥杭金衢联络线高速公路有限公司|金华市东永高速投资有限公司|东港投资发展集团有限公司|杭州农发原乡人农特产有限公司|杭州千岛湖鲟龙科技股份有限公司|浙江农发产业投资有限公司|浙江省现代农业研究会|芜湖信农硬科技投资合伙企业（有限合伙）|黑龙江亚欧牧业有限公司|浙江四港联动发展有限公司|浙江电子口岸有限公司|浙江空港商业经营管理有限责任公司|浙江空港数字科技有限公司|浙江空港资本控股有限公司|上海大宗商品仓单登记有限责任公司|宁波舟山港铁矿石储运有限公司|杭州港务集团有限公司|浙江中澳现代产业园有限公司|浙江义迪通供应链服务有限公司|浙江之迪控股有限公司|浙江海港国际联运有限公司|浙江海港大宗商品交易中心有限公司|浙江海港引航服务有限公司|浙江船舶交易市场有限公司|杭州富格企业管理合伙企业（有限合伙）|杭州松下马达有限公司|汇孚集团有限公司|浙江信联钢铁有限公司|浙江广杰投资管理有限公司|浙江建设融资租赁有限公司|浙江杰尚投资管理有限公司|浙江申达塑料机械有限公司|浙江申达机器制造股份有限公司|浙江省二轻供销总公司|浙江省二轻商业经营管理有限公司|浙江省二轻房地产开发有限公司|浙江省工美控股有限公司|浙江省工艺美术研究院有限公司|浙江省皮革塑料有限公司|浙江省艺创投资发展股份有限公司|浙江省艺创文旅发展有限公司|安邦护卫（浙江）公共安全智慧科技有限公司|浙江丽水安邦护卫有限公司|浙江台州安邦护卫有限公司|浙江嘉兴安邦护卫有限公司|浙江宁波安邦护卫有限公司|浙江安邦护卫安全服务有限公司|浙江安邦护卫科技服务有限公司|浙江杭州安邦护卫有限公司|浙江温州安邦护卫有限公司|浙江湖州安邦护卫有限公司|浙江绍兴安邦护卫有限公司|浙江舟山安邦护卫有限公司|浙江衢州安邦护卫有限公司|上海浙大科技发展有限公司|杭州启真未来创新股权投资合伙企业（有限合伙）|杭州浙大动物医院有限公司|杭州浙大文化创意发展有限公司|杭州紫金港未来创新投资合伙企业（有限合伙）|杭州网新信息控股有限公司|杭州西投启真脑机智能产业运营有限公司|浙江启真人才发展有限公司|浙江大学农业科技园有限公司|浙江大学创新技术研究院有限公司|浙江大学城乡规划设计研究院有限公司|浙江大学杭州国际科创中心发展有限公司|浙江大学科技园发展有限公司|浙江大学能源工程设计研究院有限公司|浙江浙大列车智能化工程技术研究中心有限公司|浙江浙大圆正科技创新服务有限公司|浙江浙大新宇物业集团有限公司|浙江浙大科创集团有限公司|浙江浙大西投脑机智能科技有限公司|浙江钱塘机器人及智能装备研究有限公司|丽水市廉合产权交易有限公司|北京中产智合咨询服务中心（有限合伙）|北京金马甲产权网络交易有限公司|台州市产权交易所有限公司|嘉兴市产权交易有限公司|湖州市联合产权交易有限公司|绍兴市产权交易有限公司|舟山市产权交易中心有限责任公司|衢州市产权交易中心有限公司|浙江省三建建设集团有限公司|浙江银通典当有限责任公司|浙江省化工进出口有限公司|浙江省能源集团有限公司|浙江海港中奥能源有限责任公司|杭州香格里拉饭店有限公司|浙能集团新疆准东能源化工有限公司|温州衢化东南工贸有限公司|义乌产权交易所有限公司|温州机场集团有限公司|浙江浙能电力股份有限公司|浙江工程设计有限公司|浙江国信控股集团有限责任公司|浙江巨化集团进出口有限公司|上海盛东国际集装箱码头有限公司|衢州巨化房地产开发有限公司|浙江省空港融资租赁有限公司|浙江中旅商务会展有限公司|浙江海港集团财务有限公司|浙江浙能港口运营管理有限公司|浙江机场集团保安服务有限公司|新疆塔建三五九建工有限责任公司|浙江能源天然气集团有限公司|浙江华江科技股份有限公司|浙江浙能资产经营管理有限公司|浙江海港黄泽山油品储运有限公司|浙江浙旅投资有限责任公司|浙江海港海洋工程建设有限公司|浙江省能源集团财务有限责任公司|江西省赣浙能源有限公司|温州联合产权交易中心有限公司|浙江省通用航空产业发展有限公司|物产中大期货有限公司|浙江省富浙融资租赁有限公司|宁波机场集团有限公司|浙江省振兴乡村建设投资发展集团有限公司|浙江杭钢融资租赁有限公司|浙江国贸云商控股有限公司|浙江省农村实业发展有限公司|巨化控股有限公司|浙江省国际贸易集团有限公司|浙江机电职业技术学院|浙江头门港投资开发有限公司|伊犁新天煤化工有限责任公司|浙江省农村发展集团农产品有限公司|衢州巨化传媒有限公司|浙江机场投资有限责任公司|浙江中大元通融资租赁有限公司|巨化集团公司兴化实业有限公司|浙江新世纪期货有限公司|巨化集团有限公司|浙旅盛景资本投资有限公司|浙江省医疗健康集团有限公司|浙江歌瑞新材料有限公司|浙江省国贸集团资产经营有限公司|浙能资本控股有限公司|杭州萧山国际机场有限公司|浙江梅苑酒店管理有限公司|浙江国贸集团东方机电工程股份有限公司|上港集团平湖独山港码头有限公司|浙江巨化热电有限公司|浙江省粮食集团有限公司|宁波舟山港集团有限公司|浙江省纺织品进出口集团有限公司|浙江巨化物流有限公司|浙江建设技师学院|浙江杭州临空经济开发有限公司|浙江中大技术进出口集团有限公司|浙江省粮油食品进出口股份有限公司|浙江省石油股份有限公司|浙江空港培训服务咨询有限公司|浙江省机电集团有限公司|浙江省二轻集团有限责任公司'
kwL=kwLstr.split('|') kwL=kwLstr.split('|')
for keyword in kwL: for keyword in kwL[50:]:
log.info(f"采集的企业公司：{keyword}") log.info(f"采集的企业公司：{keyword}")
# keyword = baseCore.redicPullData('cpwsqy') # keyword = baseCore.redicPullData('cpwsqy')
if keyword == 'None' or keyword == None: if keyword == 'None' or keyword == None:
......
estool/Esmethod.py 0 → 100644
import json
"""
Elasticsearch 安装
pip install elasticsearch==7.8.1 版本的
使用时参考文章
https://blog.csdn.net/yangbisheng1121/article/details/128528112
https://blog.csdn.net/qiuweifan/article/details/128610083
"""
from elasticsearch import Elasticsearch
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'
'''
模糊
# 查询方法：模糊查询（会被分词）。
# 比如 我爱你中国，会查到只包含：“我爱你”， “中国”的内容
'''
def match(self,index_name,pnum):
body = {
'query':{
'match':{
'title' : '.pdf',
'origin' : '雪球网',
'type' : '1',
}
},
'from' : pnum,
'size' : 20,
}
filter_path=['hits.hits._source.title', # 字段1
'hits.hits._source.id'] # 字段2
result = self.es.search(index=index_name
,doc_type='_doc'
,filter_path = filter_path
,body=body)
print(result)
'''
包含查询
# 查询方法：模糊查询（不会被分词）。会查到包含：“我爱你中国”的内容
'''
def match_phrase(self,index_name):
body = {
'query':{
'match_phrase':{
'm_ext1' : 'XXXXXX' #keyword
}
}
}
filter_path=['hits.hits._source.title', # 字段1
'hits.hits._source.id',
'hits.hits._source.sourceAddress',
'hits.hits._source.publishDate'
] # 字段2
result = self.es.search(index=index_name
,doc_type='_doc'
,filter_path = filter_path
,body=body)
print(result)
'''
精准查询
'''
def term(self,index_name):
body = {
'query':{
'term':{
'm_slhm' : 'XXXXXX'
}
}
}
filter_path=['hits.hits._source.m_ext1', # 字段1
'hits.hits._source.m_ext2'] # 字段2
result = self.es.search(index=index_name
,doc_type='_doc'
,filter_path = filter_path
,body=body)
print(result)
'''
多个条件精准查询
'''
def terms(self,index_name):
body = {
'query':{
'terms':{
'm_slhm' : ['13XXXXXX ','13XXXXXX']
}
}
}
filter_path=['hits.hits._source.m_ext1', # 字段1
'hits.hits._source.m_slhm'] # 字段2
result = self.es.search(index=index_name
,doc_type='_doc'
,filter_path = filter_path
,body=body)
print(result)
'''
多条件 and 查询
'''
def multi_must(self,index_name):
body = {
'query': {
'bool': {
'must':[
{'term':{'m_slhm' : '13XXXXXXX'}},
{'terms':{'m_slhm' : ['13XXXXXX']}},
]
}
}
}
filter_path=['hits.hits._source.m_ext1', # 字段1
'hits.hits._source.m_slhm'] # 字段2
result = self.es.search(index=index_name
,doc_type='_doc'
,filter_path = filter_path
,body=body)
print(result)
'''
更新
'''
def update(self,index_name):
result = self.es.update(index=index_name
,id='20220901-XXXXX'
,body={'serialno': 'XXXXXX' })
print('更新结果:%s' % result)
'''
新增
'''
def add(self,index_name):
result = self.es.index(index=index_name
,id='20220901-XXXXXX'
,body={'serialno': 'XXXXXX' })
print('新增结果:%s' % result)
'''
删除
'''
def delete(self,index_name,id):
result = self.es.delete(index=index_name
,doc_type="_doc"
,id=id)
print('删除结果 %s' % result)
'''
多条件 or 查询
'''
def multi_should(self,index_name,pnum):
body = {
'query': {
'bool': {
'should':[
{'term':{'labels.relationId' : '91110108740053589U'}},
{'term':{'type' : 3}},
],
# 'must': [
# {'match': {'title': '.pdf'}}
# ]
}
},
'from' : pnum,
'size' : 600,
}
body = {
"query": {
"bool": {
"must": [
{
"nested": {
"path": "labels",
"query": {
"match": {
"labels.relationId": "91110108740053589U"
}
}
}
},
{
"term": {
"type.keyword": {
"value": "3"
}
}
}
]
}
},
"sort": [
{
"publishDate": {
"order": "desc"
}
}
],
"track_total_hits": True,
"size": 212
}
filter_path=['hits.hits._source.title', # 字段1
'hits.hits._source.id',
'hits.total.value',
] # 字段2
result = self.es.search(index=index_name
,doc_type='_doc'
,filter_path = filter_path
,body=body)
print(result)
return result
'''
更新
'''
def updateaunn(self,index_name,id,utitle):
body = {
'doc': {
'title': utitle
}
}
result = self.es.update(index=index_name
,id=id
,body=body)
print('更新结果:%s' % result)
def getFileds(self,index_name):
mapping = self.es.indices.get_mapping(index=index_name)
fields = mapping[index_name]['mappings']['properties'].keys()
print(fields)
if __name__ == '__main__':
esMethod=EsMethod()
# esMethod.getFileds(index_name=esMethod.index_name)
num=1
for pnum in range(0,num):
p=pnum*20
print(f'第{pnum}页数据')
result=esMethod.multi_should(index_name=esMethod.index_name,pnum=p)
msglist=result['hits']['hits']
# print(msglist)
for mms in msglist:
id=mms['_source']['id']
title=mms['_source']['title']
utitle=title.replace('.pdf','')
print(f'id:{id}---title:{title}--utitle:{utitle}')
# esMethod.updateaunn(esMethod.index_name,str(id),utitle)
esMethod.delete(esMethod.index_name,str(id))
print('跟新成功！！')
estool/esconn.py 0 → 100644
import json
from elasticsearch import Elasticsearch
# 创建Elasticsearch对象，并提供账号信息
es = Elasticsearch(
['http://114.116.19.92:9700'], http_auth=('elastic', 'zzsn9988') # 账号和密码
)
index_name = 'basedata'
# 搜索文档
search_query = {
"query": {
"match": {
"sourceAddress": "www"
}
}
}
# search_query=json.dumps(search_query)
res = es.search(index=index_name, body=search_query)
for hit in res['hits']['hits']:
print(hit['_source'])
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论