Skip to content

Z
zzsn_spider
提交 a20d13d3 作者: 薛凌堃
操作

10/10

上级 a2f6dae1
正在显示 包含 282 行增加 和 45 行删除
base/BaseCore.py
......@@ -5,22 +5,18 @@ 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
# import sys
# sys.path.append('D://zzsn_spider//base//fdfs_client')
......@@ -28,6 +24,15 @@ from DBUtils.PooledDB import PooledDB
from fdfs_client.client import get_tracker_conf, Fdfs_client
tracker_conf = get_tracker_conf('D:\\kkwork\\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:
......@@ -659,12 +664,10 @@ class BaseCore:
create_time = retData['create_time']
order_by = num
selects = self.secrchATT(item_id,year,type_id)
# sel_sql = '''select id,item_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()
if selects:
self.getLogger().info(f'com_name:{com_name}已存在')
id = selects[0]
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) values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'''
......@@ -695,6 +698,80 @@ class BaseCore:
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]}"
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=====')
else:
self.getLogger().info(f'=====文件存在obs========{file_path}')
def uptoOBS(self,pdf_url, name_pdf,type_id, social_code,pathType,taskType,start_time):
headers = {}
retData = {'state': False, 'type_id': type_id, 'item_id': social_code, 'group_name': 'group1', '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:
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
for i in range(0, 3):
try:
name = name_pdf + '.pdf'
now_time = time.strftime("%Y-%m")
result = obsClient.putContent('zzsn', f'{pathType}{now_time}/' + name, content=response.content)
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()
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:
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'] = unquote(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
......
base/RedisPPData.py
......@@ -475,7 +475,14 @@ def kegaishifan():
#双百企业
def shuangbaiqiye():
pass
cnx, cursor = connectSql()
query = "SELECT CompanyName FROM Hundred"
cursor.execute(query)
result = cursor.fetchall()
cnx.commit()
com_namelist = [item[0] for item in result]
for item in com_namelist:
r.rpush('hundred:baseinfo', item)
#专精特新
def zhuangjingtexind():
......@@ -484,7 +491,8 @@ def zhuangjingtexind():
if __name__ == "__main__":
start = time.time()
# danxiangguanjun()
kegaishifan()
# kegaishifan()
shuangbaiqiye()
# NoticeEnterprise()
# AnnualEnterpriseIPO()
# AnnualEnterprise()
......
comData/newlist/champion/BaseCore.py
......@@ -541,7 +541,10 @@ class BaseCore:
self.cursor.execute(query)
token_list = self.cursor.fetchall()
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
# 删除失效的token
......
comData/newlist/hundred/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
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/newlist/technological/BaseCore.py
......@@ -541,7 +541,10 @@ class BaseCore:
self.cursor.execute(query)
token_list = self.cursor.fetchall()
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
# 删除失效的token
......
comData/policylaw/BaseCore.py
......@@ -11,24 +11,28 @@ import logbook.more
import pandas as pd
import requests
import zhconv
import pymysql
import redis
from docx import Document
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
# import sys
# sys.path.append('D://zzsn_spider//base//fdfs_client')
from fdfs_client.client import get_tracker_conf, Fdfs_client
tracker_conf = get_tracker_conf('E:\\kkwork\\zzsn_spider\\comData\\policylaw\\client.conf')
tracker_conf = get_tracker_conf('D:\\kkwork\\zzsn_spider\\comData\\policylaw\\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:
......@@ -437,9 +441,9 @@ class BaseCore:
#解析word文件页数
def doc_page(self,file_path):
doc = Document(file_path)
return len(doc.sections)
# def doc_page(self,file_path):
# doc = Document(file_path)
# return len(doc.sections)
def pdf_content(self,resp_content):
# 解析pdf文件内容
content = ''
......@@ -507,9 +511,9 @@ class BaseCore:
# retData['page_size'] = page_size
return retData
def secrchATT(self,item_id,file_name,type_id):
sel_sql = '''select id from clb_sys_attachment where item_id = %s and name = %s and type_id=%s '''
self.cursor_.execute(sel_sql, (item_id, file_name, type_id))
def secrchATT(self,item_id,file_name,type_id,order_by):
sel_sql = '''select id from clb_sys_attachment where item_id = %s and name = %s and type_id=%s and order_by=%s '''
self.cursor_.execute(sel_sql, (item_id, file_name, type_id,order_by))
selects = self.cursor_.fetchone()
return selects
......@@ -527,26 +531,81 @@ class BaseCore:
page_size = retData['page_size']
create_time = retData['create_time']
order_by = num
selects = self.secrchATT(item_id,file_name,type_id)
if selects:
self.getLogger().info(f'com_name:{com_name}已存在')
id = selects[0]
return id,full_path
else:
Upsql = '''insert into clb_sys_attachment(name,type_id,item_id,group_name,path,full_path,category,file_size,order_by,status,create_by,create_time) values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'''
values = (
file_name, type_id, item_id, group_name, path, full_path, category, file_size, order_by,
status, create_by,
create_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,file_name,type_id)
id = selects[0]
return id,full_path
Upsql = '''insert into clb_sys_attachment(name,type_id,item_id,group_name,path,full_path,category,file_size,order_by,status,create_by,create_time) values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'''
values = (
file_name, type_id, item_id, group_name, path, full_path, category, file_size, order_by,
status, create_by,
create_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,file_name,type_id,order_by)
id = selects[0]
return id,full_path
# 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]}"
def uptoOBS(self,file_href,item_id,pathType,file_name):
headers = {}
category = os.path.splitext(file_href)[1]
retData = {'state': False, 'type_id': 7, 'item_id': item_id, 'group_name': 'group1', 'path': '',
'full_path': '',
'category': category, 'file_size': '', 'status': 1, 'create_by': 'XueLingKun',
'create_time': '', 'page_size': '', 'content': ''}
headers['User-Agent'] = self.getRandomUserAgent()
for i in range(0, 3):
try:
response = requests.get(file_href, headers=headers, verify=False, timeout=20)
file_size = int(response.headers.get('Content-Length'))
break
except:
time.sleep(3)
continue
page_size = 0
for i in range(0, 3):
try:
# name = file_name
if category in file_name:
pass
else:
file_name = file_name + '.' + category
result = obsClient.putContent('zzsn', f'{pathType}' + file_name, content=response.content)
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:
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'] = unquote(result['body']['objectUrl'])
retData['file_size'] = self.convert_size(file_size)
retData['create_time'] = time_now
except Exception as e:
print(f'error:{e}')
return retData
return retData
......
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