使用 python 从 excel 文件导入数据到 SQL 服务器

Question

我发现其他一些问题与我得到的错误类似，但无法根据答案找出解决方法。我试图在 python 的帮助下将 excel 文件导入 SQL 服务器。这是我写的代码：

import pandas as pd
import numpy as np
import pandas.io.sql
import pyodbc
import xlrd

server = "won't disclose private info"
db = 'private info'
conn = pyodbc.connect('DRIVER={SQL Server};SERVER=' + Server + ';DATABASE=' + 
db + ';Trusted_Connection=yes')

cursor = conn.cursor()
book = xlrd.open_workbook("Daily Flash.xlsx")
sheet = book.sheet_by_name("Sheet1")

query1 = """CREATE TABLE [LEAF].[MK] ([LEAF][Lease_Number] varchar(255), 
[LEAF][Start_Date] varchar(255), [LEAF][Report_Status] varchar(255), [LEAF] 
[Status_Date] varchar(255), [LEAF][Current_Status] varchar(255), [LEAF] 
[Sales_Rep] varchar(255), [LEAF][Customer_Name] varchar(255),[LEAF] 
[Total_Finance] varchar(255),
[LEAF][Rate_Class] varchar(255) ,[LEAF][Supplier_Name] varchar(255) ,[LEAF] 
[DecisionStatus] varchar(255))"""


query = """INSERT INTO [LEAF].[MK] (Lease_Number, Start_Date, Report_Status, 
Status_Date, Current_Status, Sales_Rep, Customer_Name,Total_Finance,
Rate_Class,Supplier_Name,DecisionStatus) VALUES (%s, %s, %s, %s, %s, %s, %s, 
%s, %s, %s, %s)"""

for r in range(1, sheet.nrows):
    Lease_Number  = sheet.cell(r,0).value
    Start_Date    = sheet.cell(r,1).value
    Report_Status = sheet.cell(r,2).value
    Status_Date   = sheet.cell(r,3).value
    Current_Status= sheet.cell(r,4).value
    Sales_Rep     = sheet.cell(r,5).value
    Customer_Name = sheet.cell(r,6).value
    Total_Financed= sheet.cell(r,7).value
    Rate_Class    = sheet.cell(r,8).value
    Supplier_Name = sheet.cell(r,9).value
    DecisionStatus= sheet.cell(r,10).value


    values = (Lease_Number, Start_Date, Report_Status, Status_Date, 
    Current_Status, Sales_Rep, Customer_Name, Total_Financed, Rate_Class, 
    Supplier_Name, DecisionStatus)

    cursor.execute(query1)

    cursor.execute(query, values)


database.commit()


database.close()


database.commit()

我收到的错误信息是：

ProgrammingError                          Traceback (most recent call last)
<ipython-input-24-c525ebf0af73> in <module>()
 16 
 17     # Execute sql Query
 ---> 18     cursor.execute(query, values)
 19 
 20 # Commit the transaction

 ProgrammingError: ('The SQL contains 0 parameter markers, but 11 parameters 
 were supplied', 'HY000')

有人可以向我解释一下这个问题以及我该如何解决吗？谢谢！

更新：

根据下面的评论，我已收到该错误消息。我还修改了我的查询，因为我试图向其中插入值的 table 以前没有创建过，所以我更新了我的代码以尝试创建它。

但是，现在我收到错误消息：

ProgrammingError: ('42000', '[42000] [Microsoft][ODBC SQL Server Driver][SQL 
Server]The specified schema name "dbo" either does not exist or you do not 
have permission to use it. (2760) (SQLExecDirectW)')

我尝试通过编写 CREATE [HELLO][MK] 而不是仅仅 CREATE MK 来稍微改变它，但这告诉我 MK 已经在数据库中......接下来我应该采取什么步骤？

Answer 1

根据我们聊天中的对话，这里有一些要点：

执行您的 CREATE TABLE 查询后，确保在运行任何后续 INSERT 查询之前立即提交它。
当 table 已经存在于数据库中时，使用错误捕获。您问如果要将更多数据导入 table，脚本是否仍然运行。答案是否定的，因为 Python 会在 cursor.execute(query1).
如果您想验证您的插入操作是否成功，您可以做一个简单的记录计数检查。

编辑昨天，当我让@mkheifetz 测试我的代码时，他发现了一个小错误，其中验证检查会 return False，原因是因为数据库已经有现有记录，所以当仅与当前数据进行比较时导入，验证将失败。因此，作为解决bug的方案，我再次修改了代码。

下面是我将如何修改您的代码：

import pandas as pd
import numpy as np
import seaborn as sns
import scipy.stats as stats
import matplotlib.pyplot as plt

import pandas.io.sql
import pyodbc

import xlrd
server = 'XXXXX'
db = 'XXXXXdb'

# create Connection and Cursor objects
conn = pyodbc.connect('DRIVER={SQL Server};SERVER=' + server + ';DATABASE=' + db + ';Trusted_Connection=yes')
cursor = conn.cursor()

# read data
data = pd.read_excel('Flash Daily Apps through 070918.xls')

# rename columns
data = data.rename(columns={'Lease Number': 'Lease_Number',
                            'Start Date': 'Start_Date',
                            'Report Status': 'Report_Status',
                            'Status Date': 'Status_Date',
                            'Current Status': 'Current_Status',
                            'Sales Rep': 'Sales_Rep',
                            'Customer Name': 'Customer_Name',
                            'Total Financed': 'Total_Financed',
                            'Rate Class': 'Rate_Class',
                            'Supplier Name': 'Supplier_Name'})

# export
data.to_excel('Daily Flash.xlsx', index=False)

# Open the workbook and define the worksheet
book = xlrd.open_workbook("Daily Flash.xlsx")
sheet = book.sheet_by_name("Sheet1")

query1 = """
CREATE TABLE [LEAF].[ZZZ] (
    Lease_Number varchar(255),
    Start_Date varchar(255),
    Report_Status varchar(255),
    Status_Date varchar(255),
    Current_Status varchar(255),
    Sales_Rep varchar(255),
    Customer_Name varchar(255),
    Total_Finance varchar(255),
    Rate_Class varchar(255),
    Supplier_Name varchar(255),
    DecisionStatus varchar(255)
)"""

query = """
INSERT INTO [LEAF].[ZZZ] (
    Lease_Number,
    Start_Date,
    Report_Status,
    Status_Date,
    Current_Status,
    Sales_Rep,
    Customer_Name,
    Total_Finance,
    Rate_Class,
    Supplier_Name,
    DecisionStatus
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)"""

# execute create table
try:
    cursor.execute(query1)
    conn.commit()
except pyodbc.ProgrammingError:
    pass

# grab existing row count in the database for validation later
cursor.execute("SELECT count(*) FROM LEAF.ZZZ")
before_import = cursor.fetchone()

for r in range(1, sheet.nrows):
    Lease_Number = sheet.cell(r,0).value
    Start_Date = sheet.cell(r,1).value
    Report_Status = sheet.cell(r,2).value
    Status_Date = sheet.cell(r,3).value
    Current_Status= sheet.cell(r,4).value
    Sales_Rep = sheet.cell(r,5).value
    Customer_Name = sheet.cell(r,6).value
    Total_Financed= sheet.cell(r,7).value
    Rate_Class = sheet.cell(r,8).value
    Supplier_Name = sheet.cell(r,9).value
    DecisionStatus= sheet.cell(r,10).value

    # Assign values from each row
    values = (Lease_Number, Start_Date, Report_Status, Status_Date, Current_Status,
              Sales_Rep, Customer_Name, Total_Financed, Rate_Class, Supplier_Name,
              DecisionStatus)

    # Execute sql Query
    cursor.execute(query, values)

# Commit the transaction
conn.commit()

# If you want to check if all rows are imported
cursor.execute("SELECT count(*) FROM LEAF.ZZZ")
result = cursor.fetchone()

print((result[0] - before_import[0]) == len(data.index))  # should be True

# Close the database connection
conn.close()

使用 python 从 excel 文件导入数据到 SQL 服务器

Importing data from an excel file using python into SQL Server

python

xlrd

pyodbc

python-3.x