jupyter/文件操作.ipynb

数字文件名转换为文本文件名

数字文件名转换为文本文件名

In [ ]:

import os,sys,shutil
import openpyxl
import math

fi_xls = os.getcwd()+'/file/北海石化监测花名册2022 .xlsx'
fi_name = {}
fi_path = os.getcwd()+'/file/221103'
old = []
new = []
dict1 = {}

wb = openpyxl.load_workbook(fi_xls)
sheet = wb.active
depart = []
for n in range(2,sheet.max_row+1):
    if sheet.cell(n,3).value is not None: 
        m_name = sheet.cell(n,6).value.strip()
        m_depart = sheet.cell(n,3).value.strip()           
        depart.append(m_depart)    
        dict1[int(sheet.cell(n,4).value)] = [m_name,m_depart]
    #print()
# 创建部门办公室    
m_path = os.getcwd()+'/file/221103/new'
for pn in depart:
    if not os.path.exists(m_path + '/' + pn):
        os.mkdir(m_path + '/' + pn)
#print(dict1)


fl=os.listdir(fi_path)
for fn in fl:
    if os.path.isfile(fi_path + '/' + fn):
        ofn = int(fn.split('.')[0])
        old.append(ofn)
    #print(fn)
old.sort()
    #print(str(nfn)+'.pdf')

for n in old:
    
    o_name = f'{fi_path}/{n}.pdf'
    n_name = f'{fi_path}/new/{dict1[n][1]}/{str(n).rjust(5,"0")}-{dict1[n][0]}.pdf'
    if not os.path.exists(n_name):
        shutil.copyfile(o_name,n_name)
        print(n_name)
#print(old)

#print(dict1)

目录文件按照文件名排序

In [ ]:

import os,sys


fi_xls = 'test1.xlsx'
fi_name = {}
#fi_path = 'drive/My Drive/Colab Notebooks'+'/data'
fi_path = os.getcwd()+'/data'
old = []
new = []

fl=os.listdir(fi_path)
fl.sort()
n = 0
for i in fl:
    oldname=fl[n]
    name, suffix = os.path.splitext(oldname)
    if name in old:
        new_name = fi_path+ os.sep + fi_name[name]+suffix
        old_name = fi_path+ os.sep + fl[n]
        os.rename(old_name,new_name)
    n+= 1
fl

将pdf文件转为图片

In [ ]:

from pdf2image import convert_from_path, convert_from_bytes
import os,sys
import tempfile
from pdf2image.exceptions import (
    PDFInfoNotInstalledError,
    PDFPageCountError,
    PDFSyntaxError
)
#images = convert_from_path('1.pdf',dpi=200,fmt='jpg', output_folder='./sample_data')
with tempfile.TemporaryDirectory() as path:
    images_from_path = convert_from_path('./data/普通高等学校本科专业目录.pdf', dpi=300,fmt='jpg', output_folder='./data/pic')
print(path)

图像文件夹打包

In [ ]:

import zipfile
from pdf2image import convert_from_path, convert_from_bytes
import os,sys
import tempfile
import shutil
import time

from pdf2image.exceptions import (
    PDFInfoNotInstalledError,
    PDFPageCountError,
    PDFSyntaxError
)
def compress_file(zipfilename, dirname):      # zipfilename是压缩包名字，dirname是要打包的目录
    if os.path.isfile(dirname):
        with zipfile.ZipFile(zipfilename, 'w') as z:
            z.write(dirname)
    else:
        with zipfile.ZipFile(zipfilename, 'w') as z:
            for root, dirs, files in os.walk(dirname):
                for single_file in files:
                    if single_file != zipfilename:
                        filepath = os.path.join(root, single_file)
                        z.write(filepath)

def addfile(zipfilename, dirname):
    if os.path.isfile(dirname):
        with zipfile.ZipFile(zipfilename, 'a') as z:
            z.write(dirname)
    else:
        with zipfile.ZipFile(zipfilename, 'a') as z:
            for root, dirs, files in os.walk(dirname):
                for single_file in files:
                    if single_file != zipfilename:
                        filepath = os.path.join(root, single_file)
                        z.write(filepath)

#images = convert_from_path('1.pdf',dpi=200,fmt='jpg', output_folder='./sample_data')
def make_path(p):
    if os.path.exists(p):       # 判断文件夹是否存在
        shutil.rmtree(p)        # 删除文件夹
    os.mkdir(p)    
pdf_file = '2.pdf'
output_folder='./pic1'
zip_file = 'ribenweiqishihua.zip'
make_path(output_folder)
print (time.strftime("%a %b %d %H:%M:%S %Y", time.localtime()))
with tempfile.TemporaryDirectory() as path:
    images_from_path = convert_from_path(pdf_file, dpi=300,fmt='jpg', output_folder=output_folder)
compress_file(zip_file, output_folder)      # 执行函数
print (time.strftime("%a %b %d %H:%M:%S %Y", time.localtime()))

文本文件操作

基本读取

In [ ]:

import re
file_name = 'data/2012.txt'
with open(file_name,'r') as fl,open('new_2012_1.txt','w') as fl1:
    for l in fl:
        l = re.sub('[\r\n\f ]{1,}', '', l)
        if l.split():
            print(l)
            fl1.write(l)

读取csv文件

In [ ]:

import csv
import re

filename = 'data/130.csv'
with open(filename,'r',newline='') as csv_file:
    fl = csv.reader(csv_file,delimiter=',')
    header = next(fl)    
    for line in fl:
        #line = re.sub('[\r\n\f ]{1,}', '', line)
        print(line)

读取分隔符分割文件，导入MongoDB

In [ ]:

import pymongo
import re
myclient = pymongo.MongoClient('mongodb://localhost:27017/')
mydb = myclient["gaokao"]
mycol = mydb["city"]
m_mongo = {}
m_xx = []
fl_name = 'china-city-list.txt'
n = 0
with open(fl_name,'r') as fl:
    for l in fl:
        n += 1
        if n >6:
            m_mongo = {}
            m_xx = re.sub('[ ]{1,}', '', l).split('|')
            #print(m_xx[1],m_xx[3],m_xx[8],m_xx[10])
            m_mongo['name'] = m_xx[3]
            m_mongo['code'] = m_xx[1]
            m_mongo['sheng'] = m_xx[8]
            m_mongo['shi'] = m_xx[10]
            m_mongo['jing'] = m_xx[11]
            m_mongo['wei'] = m_xx[12]
            mycol.insert_one(m_mongo) 
            #print(m_mongo)
print('ok!')

Excel文件修改

In [ ]:

import openpyxl
import json

filename = 'data/122.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
dict2 = {}
for k, v in dict1.items():
    for item in v:
        bh = item['avatar_id']
        dict2[bh] = item
print(dict2)        
    
wb = openpyxl.load_workbook('data/济南炼化职工分组表.xlsx')
sheet = wb.active
person = {}
for n in range(2, sheet.max_row+1):
    if sheet.cell(n, 14).value is not None and sheet.cell(n, 14).value in dict2.keys():
        code = sheet.cell(n, 14).value
        sheet[f'F{n}']=dict2[code]['birth']
wb.save('data/济南炼化职工分组表1.xlsx') 
print('ok!')    

YALM文件操作

YALM文件读取转存JSON文件

In [11]:

import yaml
import json

filename = 'data/全维健康中医体质检测问卷.yaml'
with open(filename, 'r', encoding='utf-8') as f:
    result = yaml.load(f.read(), Loader=yaml.FullLoader)
i = 1
#print(result)
filename = 'data/全维健康中医体质检测问卷.json'
with open(filename, 'w') as fl:
    json.dump(result, fl, ensure_ascii=False)
print('ok')

ok

按照年龄分组生成心理问卷

In [ ]:

import json
import os,sys,shutil
import openpyxl

list1 = [
    [1,'完全不正确','有点正确','多数正确','完全正确'],
    [2,'从不','极少','偶尔','经常','频繁','非常频繁','每天'],
    [3,'不符合','有时符合','常常符合','总是符合'],
    [4,'从不','很少','有时','经常','总是'],
    [5,'非常不满意','不满意','一般','满意','非常满意'],
    [6,'没有或很少时间（少于1天）','一部分时间（1-2天）','相当多时间（3-4天）','绝大部分时间（5-7天）'],
    [7,'从来没有这种感觉','很少有这种感觉','有时有这种感觉','经常有这种感觉'],
    [8,'完全不同意','不同意','同意','完全同意'],    
    [10,'晚多了','晚一点','差不多','早一点','早多了']
]
dict1 = {}
for item in list1:
    #dict1.setdefault(item[0],[])
    list2 =[]
    for i in range(1,len(item)):
        list2.append(item[i])
    dict1[item[0]] = list2
dict_choiced = {}
print(dict1)
wj = {}
wj["login"] = "phone"
wj["locale"] = "zh-cn"
wj["title"] = '社区心理测评问卷'
list2 =[]
dict2 = {
     "type": "radiogroup",
      "name": "Gender",
      "title": {
        "zh-cn": "您的性别"
      },
      "isRequired": True,
      "choices": [
        {
          "value": "m",
          "text": "男性"
        },
        {
          "value": "f",
          "text": "女性"
        }
      ]    
}
list2.append(dict2)
dict2 = {}
dict3 = {}
dict2 = {
     "type": "radiogroup",
      "name": "Age",
      "title": {
        "zh-cn": "您的年龄"
      },
      "isRequired": True,
      "choices": [
        {
          "value": "Y",
          "text": "8-17岁"
        },
        {
          "value": "M",
          "text": "15-59岁"
        },
        {
          "value": "O",
          "text": "60岁及以上"
        }
      ]    
}
list2.append(dict2)

wb = openpyxl.load_workbook('data/心理问卷.xlsx')
sheet = wb.active
data1 =list(sheet.values)
del data1[0]
for item in data1:
    
    dict2 = {}        
    dict2['type'] = item[4]     
    dict2['name'] = 'q'+str(item[0])+item[3]
    dict2['visibleIf'] = '{Age}="'+item[3]+'"'
    dict3 = {}
    dict3["zh-cn"] = item[1]
    dict2['title'] =dict3    
    dict2['isRequired'] = True
    if item[4] == 'rating':
        dict2['rateMin'] = 0
        dict2['rateMax'] = 7
        dict2['minRateDescription'] = { 'zh-cn':'没有'}
        dict2['maxRateDescription'] = { 'zh-cn':'非常同意'}
    else:
        if int(item[2]) in dict_choiced.keys():
            dict2['choicesFromQuestion'] = dict_choiced[int(item[2])]
        else:
            list3 = []
            i = 1
            for xm in dict1[int(item[2])]:
                dict3 = {}
                dict3 = {'value': i,'text' : xm}
                list3.append(dict3)
                i+=1
            dict2['choices'] = list3
            dict_choiced[int(item[2])] = dict2['name']
    list2.append(dict2)
dict3 = {}
dict3["elements"] = list2
wj["pages"] =[]

wj["pages"].append(dict3)
#filename = 'data/心理问卷1.json'
#with open(filename, 'w') as fl:
#    json.dump(wj, fl, ensure_ascii=False)
#print('ok')
with open('心理问卷.yml', 'w', encoding='utf-8') as f:
    yaml.dump(data=wj, stream=f, allow_unicode=True)

In [ ]:

import yaml

邮件管理

使用网易邮箱群发邮件

In [ ]:

from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart
from email.mime.application import MIMEApplication
from email.header import Header
import smtplib
import requests
import time
import re
import json


      

fl_name = 'data/低碳院报告.json'

with open(fl_name,'r') as fl:
     m_xx = json.load(fl)
for k, v in m_xx.items():
    m_bh = str(k).rjust(5,"0")
    fl_name = f'file/220724/new/{m_bh}-{v[0]}.pdf'
    fl = f'{m_bh}-{v[0]}.pdf'
    m_rec = v[2]+'@ceic.com'
    
    from_addr = 'kmingedu@163.com' #发件邮箱
    password = 'GKWUZXMVYKSSUSSL' #邮箱密码
    smtp_server = 'smtp.163.com' #SMTP服务器，以新浪为例
    server = smtplib.SMTP(smtp_server,25) #第二个参数为默认端口为25，有些邮件有特殊端口
    msg = MIMEMultipart()
    msg['Subject'] = Header("低碳清洁能源研究院体质监测报告",'utf-8')
    msg['From'] = Header('北京坤铭体质监测评估中心')
    msg['To'] = Header(m_rec)

    from_addr = 'kmingedu@163.com' #发件邮箱
    password = 'GKWUZXMVYKSSUSSL' #邮箱密码
    to_addr = m_rec #收件邮箱
    att1 =MIMEApplication(open(fl_name, 'rb').read())
    #att1["Content-Type"] = 'application/octet-stream'
    # 这里的filename可以任意写，写什么名字，邮件中显示什么名字
    att1.add_header('Content-Disposition','attachment',filename=fl)
    msg.attach(att1)
    try:
        server.login(from_addr,password) #登录邮箱
        server.sendmail(from_addr,to_addr,msg.as_string())  #将msg转化成string发出
        server.quit
        time.sleep(5)
        print(f'{fl}邮件发送成功！')
    except smtplib.SMTPException:
        print ("Error: 无法发送邮件")
    

使用网易邮箱群发测试链接

In [ ]:

from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart
from email.mime.application import MIMEApplication
from email.header import Header
import smtplib
import requests
import time
import re
import json
import jwt

key = "Xixi1234"
encoded = jwt.encode({"email": "eygsoft@gmail.com"}, key, algorithm='HS256')
#print(encoded)


      
list1 = [
    {'name':'lillianwong','E_mail':'lillianwong73@gmail.com'},
    {'name':'杨玉冰','E_mail':'lkyyb@126.com'}]


for item in list1:
    m_mail = item['E_mail']
    m_name = item['name']
    encoded = jwt.encode({"email": m_mail}, key, algorithm='HS256')
    lianjie = f'https://www.forraid.com/survey/token/{encoded}/tcm0'
    mail_msg = f"""
<p>欢迎参加北京坤铭体质监测评估中心中医体质检测</p>
<p><a href="{lianjie}">点击参加测试</a></p>
"""
    from_addr = 'kmingedu@163.com' #发件邮箱
    password = 'GKWUZXMVYKSSUSSL' #邮箱密码
    smtp_server = 'smtp.163.com' #SMTP服务器，以新浪为例
    server = smtplib.SMTP(smtp_server,25) #第二个参数为默认端口为25，有些邮件有特殊端口
    msg = MIMEText(mail_msg, 'html', 'utf-8')
    msg['Subject'] = Header("中医体质检测测试链接",'utf-8')
    msg['From'] = Header('北京坤铭体质监测评估中心')
    msg['To'] = Header(m_mail)

    
    to_addr = m_mail #收件邮箱
    try:
        server.login(from_addr,password) #登录邮箱
        server.sendmail(from_addr,to_addr,msg.as_string())  #将msg转化成string发出
        server.quit
        time.sleep(5)
        print('邮件发送成功！')
    except smtplib.SMTPException:
        print ("Error: 无法发送邮件")
    

In [ ]:

try:
        server.login(from_addr,password) #登录邮箱
        server.sendmail(from_addr,to_addr,msg.as_string())  #将msg转化成string发出
        server.quit
        time.sleep(5)
        print(f'{fl}邮件发送成功！')
    except smtplib.SMTPException:
        print ("Error: 无法发送邮件")
    

Twilio使用

In [ ]:

import os
from twilio.rest import Client


# Your Account Sid and Auth Token from twilio.com/console
# and set the environment variables. See http://twil.io/secure
account_sid = 'AC1aac8c18078bf371992fda0f924860c8'
auth_token = '956199d0f1b724d00ef8bb934fcaefe9'
client = Client(account_sid, auth_token)

message = client.messages \
                .create(
                     body="I'm back.",
                     from_='+12056066931',
                     to='+8613793180751'
                 )

print(message.sid)

In [ ]:

import time

localtime = time.localtime(time.time())
#type(localtime)
print ("本地时间为 :", localtime)
jyr = '12345'
if time.strftime("%w", time.localtime()) in jyr:
    print('ok')
else:
    print('今日不是交易日！')

In [ ]:

from email.mime.text import MIMEText
from email.header import Header
import smtplib
import requests
import time
import re

def sendmail(message):
    msg = MIMEText(message,'plain','utf-8')
    msg['Subject'] = Header("外汇价格已经到达预期价位！",'utf-8')
    msg['From'] = Header('512song@sina.com')
    msg['To'] = Header('songyi@yeah.net','utf-8')

    from_addr = '512song@sina.com' #发件邮箱
    password = '409fe5d8471da663' #邮箱密码
    to_addr = 'songyi@yeah.net' #收件邮箱
    smtp_server = 'smtp.sina.com' #SMTP服务器，以新浪为例
    server = smtplib.SMTP(smtp_server,25) #第二个参数为默认端口为25，有些邮件有特殊端口
    server.login(from_addr,password) #登录邮箱
    server.sendmail(from_addr,to_addr,msg.as_string())  #将msg转化成string发出
    server.quit()    
    
       

pattern = re.compile(r'\"(.*)\"')
url = 'http://hq.sinajs.cn/list=USDCAD'
strhtml = requests.get(url)
data = strhtml.text
if pattern.findall(data):
    for data1 in pattern.findall(data):
        data2 = data1.split(',')
#print(data2)
with open('price.txt','r') as fl:
    for line in fl:
        p_high = line.split(',')[0]
        p_low = line.split(',')[1]
m_message = '当前美元加元买入价：{}'.format(data2[1])
while time.strftime("%w", time.localtime()) in '12345':
    
    print(p_high,p_low)
    time.sleep(10)
    strhtml = requests.get(url)
    data = strhtml.text
    if pattern.findall(data):
        for data1 in pattern.findall(data):
            data2 = data1.split(',')
        if float(data2[1]) > float(p_high):
            m_message = '当前美元加元买入价：{}'.format(data2[1])
            sendmail(m_message)
            p_high = str(float(p_high) + 0.04) 
        if float(data2[1]) > float(p_high):
            m_message = '当前美元加元卖出价：{}'.format(data2[2])
            p_low = str(float(p_low) - 0.04)
            sendmail(m_message)
    time.sleep(900)
            

AWS应用

AWS获取sns信息

In [ ]:

import boto3

# Create an SNS client
sns = boto3.client('sns')

# Call SNS to list topics
response = sns.list_topics()

# Get a list of all topic ARNs from the response
topics = [topic['TopicArn'] for topic in response['Topics']]

# Print out the topic list
print("Topic List: %s" % topics)

AWS操作DynamoDB

In [ ]:

import boto3

# Get the service resource.
dynamodb = boto3.resource('dynamodb')

# Create the DynamoDB table.
table = dynamodb.create_table(
    TableName='waihui',
    
    AttributeDefinitions=[        
        {
            'AttributeName': 'code',
            'AttributeType': 'S'
        }
        
        
    ],
    KeySchema=[
        {
            'AttributeName': 'code',
            'KeyType': 'HASH'
        }
        
    ],
    ProvisionedThroughput={
        'ReadCapacityUnits': 5,
        'WriteCapacityUnits': 5
    }
    
)

# Wait until the table exists.
table.meta.client.get_waiter('table_exists').wait(TableName='waihui')

# Print out some data about the table.
print(table.item_count)

In [ ]:

import boto3
import decimal
# Get the service resource.
dynamodb = boto3.resource('dynamodb')

table = dynamodb.Table('waihui')

table.put_item(
   Item={
        'code': 'USDCAD',
        'high': Decimal('1.3200'),
        'low': Decimal('1.3000'),
    }
)

In [ ]:

import boto3
# Get the service resource.
dynamodb = boto3.resource('dynamodb')

table = dynamodb.Table('waihui')

response = table.get_item(
   Key={
        'code': 'USDCAD'        
    }
)
item = response['Item']
print(item)

In [ ]:

import boto3
# Get the service resource.
dynamodb = boto3.resource('dynamodb')

table = dynamodb.Table('waihui')

table.delete_item(
   Key={
        'code': 'USDCAD'        
    }
)

In [ ]:

import boto3
import decimal
# Get the service resource.
dynamodb = boto3.resource('dynamodb')

table = dynamodb.Table('waihui')
table.update_item(
    Key={
        'code': 'USDCAD'
    },
    UpdateExpression='SET low = :val1',
    ExpressionAttributeValues={
        ':val1': decimal.Decimal('1.2900')
    }
)

In [ ]:

import boto3

# Create SQS client
sqs = boto3.client('sqs')

queue_url = 'https://sqs.us-east-1.amazonaws.com/915521803346/MySqs1'

# Receive message from SQS queue
response = sqs.receive_message(
    QueueUrl=queue_url,
    AttributeNames=[
        'SentTimestamp'
    ],
    MaxNumberOfMessages=1,
    MessageAttributeNames=[
        'All'
    ],
    VisibilityTimeout=0,
    WaitTimeSeconds=0
)

message = response['Messages'][0]
receipt_handle = message['ReceiptHandle']

# Delete received message from queue
sqs.delete_message(
    QueueUrl=queue_url,
    ReceiptHandle=receipt_handle
)
print('Received and deleted message: %s' % message)

MongoDB系统GridFS文件管理

文件上传

In [ ]:

import pymongo
from gridfs import GridFS
from bson.objectid import ObjectId
import os

myclient = pymongo.MongoClient('mongodb://localhost:27017/')
mydb = myclient["gaokao"]
mycol = mydb["college"]

UploadCache = "uploadcache"
dbURL = "mongodb://localhost:27017"

#上传文件
def upLoadFile(file_coll,file_name,data_link):
    client = pymongo.MongoClient('mongodb://localhost:27017/')

    db = client["gaokao"]

    filter_condition = {"filename": os.path.basename(file_name), "url": data_link}
    gridfs_col = GridFS(db, collection=file_coll)
    file_ = "0"
    query = {"filename":""}
    query["filename"] = file_name

    if gridfs_col.exists(query):
        print('已经存在该文件')
    else:

        with open(file_name, 'rb') as file_r:
            file_data = file_r.read()
            file_ = gridfs_col.put(data=file_data, **filter_condition)  # 上传到gridfs

            print(file_)


    return file_   
# 按文件名获取文档
def downLoadFile(self,file_coll,file_name,out_name,ver):
    client = pymongo.MongoClient(self.dbURL)

    db = client["store"]

    gridfs_col = GridFS(db, collection=file_coll)

    file_data = gridfs_col.get_version(filename=file_name, version=ver).read()

    with open(out_name, 'wb') as file_w:
        file_w.write(file_data)

# 按文件_Id获取文档       
def downLoadFilebyID(self,file_coll,_id,out_name):
    client = pymongo.MongoClient(self.dbURL)

    db = client["store"]

    gridfs_col = GridFS(db, collection=file_coll)

    O_Id = ObjectId(_id)

    gf = gridfs_col.get(file_id=O_Id)
    file_data = gf.read()
    with open(out_name, 'wb') as file_w:

        file_w.write(file_data)     


    return gf.filename    
m_dir = './data/tmp'
fls=os.listdir(m_dir)
n = 0
for fl in fls:
    #oldname=fl[n]
    name, suffix = os.path.splitext(fl)
    #if name in old:
    #    new_name = fi_path+ os.sep + fi_name[name]+suffix
    #    old_name = fi_path+ os.sep + fl[n]
     #   os.rename(old_name,new_name)
    #print(os.path.basename(fl))
    #print(fl,suffix[1:])
    full_path = m_dir+ '/' + fl
    upLoadFile("document",full_path,"")
#a = MongoGridFS("")
#a.upLoadFile("pdf","MongoGridFS.py","")
#a.downLoadFile("pdf","MongoGridFS.py","out2.p",2)
#ll = a.downLoadFilebyID("pdf","5d70a5b283a3c5104cd39346","out3.p")
#print (ll)

In [ ]:

import pymongo
from gridfs import GridFS
from bson.objectid import ObjectId
import os

myclient = pymongo.MongoClient('mongodb://localhost:27017/')
mydb = myclient["gaokao"]
mycol = mydb["college"]

UploadCache = "uploadcache"
dbURL = "mongodb://localhost:27017"

#上传文件
def upLoadFile(file_coll,file_name,data_link):
    client = pymongo.MongoClient('mongodb://localhost:27017/')

    db = client["gaokao"]

    filter_condition = {"filename": file_name, "url": data_link}
    gridfs_col = GridFS(db, collection=file_coll)
    file_ = "0"
    query = {"filename":""}
    query["filename"] = file_name

    if gridfs_col.exists(query):
        print('已经存在该文件')
    else:

        with open(file_name, 'rb') as file_r:
            file_data = file_r.read()
            file_ = gridfs_col.put(data=file_data, **filter_condition)  # 上传到gridfs

            print(file_)


    return file_   
# 按文件名获取文档
def downLoadFile(self,file_coll,file_name,out_name,ver):
    client = pymongo.MongoClient(self.dbURL)

    db = client["store"]

    gridfs_col = GridFS(db, collection=file_coll)

    file_data = gridfs_col.get_version(filename=file_name, version=ver).read()

    with open(out_name, 'wb') as file_w:
        file_w.write(file_data)

# 按文件_Id获取文档       
def downLoadFilebyID(file_coll,_id,out_name):
    client = pymongo.MongoClient('mongodb://localhost:27017/')

    db = client["gaokao"]

    gridfs_col = GridFS(db, collection=file_coll)

    O_Id = ObjectId(_id)

    gf = gridfs_col.get(file_id=O_Id)
    file_data = gf.read()
    with open(out_name, 'wb') as file_w:

        file_w.write(file_data)     


    return gf.filename    
ll = downLoadFilebyID("pdf","5fbf351b62452a56d7d16603","out3.pdf")
print (ll)
#a = MongoGridFS("")
#a.upLoadFile("pdf","MongoGridFS.py","")
#a.downLoadFile("pdf","MongoGridFS.py","out2.p",2)
#ll = a.downLoadFilebyID("pdf","5d70a5b283a3c5104cd39346","out3.pdf")
#print (ll)

In [ ]: