我如何 shutil.move 我的文件，post 处理，在 python 中基于文件名？
How do I shutil.move my file, post processing, in python based on filename?
我的代码-
import pandas as pd
import datetime as dt
import os
import shutil
path = "C:/Users/rocky/Desktop/autotranscribe/python/Matching"
destination_path = ('C:/Users/rocky/Desktop/autotranscribe/python/Matching/Processed')
for file in os.listdir("C:/Users/rocky/Desktop/autotranscribe/python/Matching"):
if file.startswith("TVC")and "(updated headers)" not in file:
dfs = pd.read_excel(file, sheet_name=None)
output = dict()
for ws, df in dfs.items():
if ws in ["Opt-Ins", "New Voting Members", "Temporary Members"]:
continue
if ws in ["Voting Members", "Removed Members"]:
temp = df
dt = pd.to_datetime(os.path.getctime(os.path.join(path,file)),unit="s").replace(nanosecond=0)
temp['Status'] = "Active" if ws == "Voting Members" else "Cancelled"
output[ws] = temp
writer = pd.ExcelWriter(f'{file.replace(".xlsx","")} (updated headers).xlsx')
for ws, df in output.items():
df.to_excel(writer, index=None, sheet_name=ws)
writer.save()
writer.close()
shutil.move(path, destination_path )
我只想在处理完我的所有代码并生成输出文件后，将这里正在处理的文件 if file.startswith("TVC")and "(updated headers)" not in file: 移动到另一个文件夹目录..我在哪里申请 shutil.move ？我把它放在我的内部循环之外，但文件没有按预期填充到我的 dest 文件夹中。我需要一个 if 语句吗？如果脚本成功运行并生成输出 xls，则将原始文件移动到目标文件夹？
有几个问题。如果您想根据在 for 循环中获得的名称移动文件，则需要在 for 循环中进行移动。
一个更大的问题是 os.listdir 只是 returns 个文件名。如果要打开或访问该文件，则需要将路径添加回去。
你的temp = df东西没有意义。只需更改 df.
import pandas as pd
import datetime as dt
import os
import shutil
path = "C:/Users/rocky/Desktop/autotranscribe/python/Matching"
destination_path = path + '/Processed'
for file in os.listdir(path)
if file.startswith("TVC") and "(updated headers)" not in file:
fullpath = path + '/' + file
dfs = pd.read_excel(fullpath, sheet_name=None)
output = dict()
for ws, df in dfs.items():
if ws in ["Voting Members", "Removed Members"]:
dt = pd.to_datetime(os.path.getctime(os.path.join(path,file)),unit="s").replace(nanosecond=0)
df['Status'] = "Active" if ws == "Voting Members" else "Cancelled"
output[ws] = df
writer = pd.ExcelWriter(fullpath.replace(".xlsx","(updated headers).xlsx")
for ws, df in output.items():
df.to_excel(writer, index=None, sheet_name=ws)
writer.save()
writer.close()
shutil.move(fullpath, destination_path )
考虑到您问题中的代码试图做什么，您可能需要考虑构建功能 and/or 稍微修改文件创建策略。
这里有两种可能的策略。
#1：创建新文件，然后移动它。
#2：在目标目录中就地创建新文件。
无论哪种情况，还可以考虑以下相关问题：
- 目标目录不存在怎么办？您可以允许 python 标准库调用的默认行为（引发异常），或者您可以创建目录。
- 如果目标文件已经存在怎么办？您可以允许默认标准库行为（引发异常），或覆盖它（静默或发出警告），或在将新文件放入目标目录之前重命名现有文件。
例如，下面的代码使用策略 #1（创建和移动文件），根据需要创建目标目录，并用警告覆盖任何现有文件。 （出于测试目的，我更改了源路径和目标路径的名称。）
import pandas as pd
#import datetime as dt
import os
import shutil
#path = "C:/Users/rocky/Desktop/autotranscribe/python/Matching"
#destination_path = ('C:/Users/rocky/Desktop/autotranscribe/python/Matching/Processed')
path = "."
destination_path = ('./Processed')
for file in os.listdir(path):
if file.startswith("TVC")and "(updated headers)" not in file:
dfs = pd.read_excel(file, sheet_name=None)
output = dict()
for ws, df in dfs.items():
if ws in ["Opt-Ins", "New Voting Members", "Temporary Members"]:
continue
if ws in ["Voting Members", "Removed Members"]:
temp = df
#dt = pd.to_datetime(os.path.getctime(os.path.join(path,file)),unit="s").replace(nanosecond=0)
temp['Status'] = "Active" if ws == "Voting Members" else "Cancelled"
output[ws] = temp
destination_file = f'{file.replace(".xlsx","")} (updated headers).xlsx'
destination_file_with_path = f'{destination_path}/{file.replace(".xlsx","")} (updated headers).xlsx'
# Create and move file, create the destination directory if needed, and overwrite any existing file with a warning:
writer = pd.ExcelWriter(destination_file)
for ws, df in output.items():
df.to_excel(writer, index=None, sheet_name=ws)
writer.save()
writer.close()
if not os.path.exists(destination_path):
os.makedirs(destination_path)
if os.path.exists(destination_file_with_path):
print(f'{destination_file_with_path} already exists, overwriting')
os.remove(destination_file_with_path)
shutil.move(destination_file, destination_path)
或者，如果您想使用策略 #2（在其目标目录中创建文件）如果需要再次创建目标目录并覆盖任何现有文件并发出警告，您可以这样做（注意 shutil 是这种方法不需要):
import pandas as pd
#import datetime as dt
import os
#import shutil
#path = "C:/Users/rocky/Desktop/autotranscribe/python/Matching"
#destination_path = ('C:/Users/rocky/Desktop/autotranscribe/python/Matching/Processed')
path = "."
destination_path = ('./Processed')
for file in os.listdir(path):
if file.startswith("TVC")and "(updated headers)" not in file:
dfs = pd.read_excel(file, sheet_name=None)
output = dict()
for ws, df in dfs.items():
if ws in ["Opt-Ins", "New Voting Members", "Temporary Members"]:
continue
if ws in ["Voting Members", "Removed Members"]:
temp = df
#dt = pd.to_datetime(os.path.getctime(os.path.join(path,file)),unit="s").replace(nanosecond=0)
temp['Status'] = "Active" if ws == "Voting Members" else "Cancelled"
output[ws] = temp
destination_file = f'{file.replace(".xlsx","")} (updated headers).xlsx'
destination_file_with_path = f'{destination_path}/{file.replace(".xlsx","")} (updated headers).xlsx'
# Create the destination directory if needed, create the new file in the destination directory, and overwrite any existing file with a warning:
if not os.path.exists(destination_path):
os.makedirs(destination_path)
if os.path.exists(destination_file_with_path):
print(f'{destination_file_with_path} already exists, overwriting')
os.remove(destination_file_with_path)
writer = pd.ExcelWriter(destination_file_with_path)
for ws, df in output.items():
df.to_excel(writer, index=None, sheet_name=ws)
writer.save()
writer.close()
我的代码-
import pandas as pd
import datetime as dt
import os
import shutil
path = "C:/Users/rocky/Desktop/autotranscribe/python/Matching"
destination_path = ('C:/Users/rocky/Desktop/autotranscribe/python/Matching/Processed')
for file in os.listdir("C:/Users/rocky/Desktop/autotranscribe/python/Matching"):
if file.startswith("TVC")and "(updated headers)" not in file:
dfs = pd.read_excel(file, sheet_name=None)
output = dict()
for ws, df in dfs.items():
if ws in ["Opt-Ins", "New Voting Members", "Temporary Members"]:
continue
if ws in ["Voting Members", "Removed Members"]:
temp = df
dt = pd.to_datetime(os.path.getctime(os.path.join(path,file)),unit="s").replace(nanosecond=0)
temp['Status'] = "Active" if ws == "Voting Members" else "Cancelled"
output[ws] = temp
writer = pd.ExcelWriter(f'{file.replace(".xlsx","")} (updated headers).xlsx')
for ws, df in output.items():
df.to_excel(writer, index=None, sheet_name=ws)
writer.save()
writer.close()
shutil.move(path, destination_path )
我只想在处理完我的所有代码并生成输出文件后，将这里正在处理的文件 if file.startswith("TVC")and "(updated headers)" not in file: 移动到另一个文件夹目录..我在哪里申请 shutil.move ？我把它放在我的内部循环之外，但文件没有按预期填充到我的 dest 文件夹中。我需要一个 if 语句吗？如果脚本成功运行并生成输出 xls，则将原始文件移动到目标文件夹？
有几个问题。如果您想根据在 for 循环中获得的名称移动文件，则需要在 for 循环中进行移动。
一个更大的问题是 os.listdir 只是 returns 个文件名。如果要打开或访问该文件，则需要将路径添加回去。
你的temp = df东西没有意义。只需更改 df.
import pandas as pd
import datetime as dt
import os
import shutil
path = "C:/Users/rocky/Desktop/autotranscribe/python/Matching"
destination_path = path + '/Processed'
for file in os.listdir(path)
if file.startswith("TVC") and "(updated headers)" not in file:
fullpath = path + '/' + file
dfs = pd.read_excel(fullpath, sheet_name=None)
output = dict()
for ws, df in dfs.items():
if ws in ["Voting Members", "Removed Members"]:
dt = pd.to_datetime(os.path.getctime(os.path.join(path,file)),unit="s").replace(nanosecond=0)
df['Status'] = "Active" if ws == "Voting Members" else "Cancelled"
output[ws] = df
writer = pd.ExcelWriter(fullpath.replace(".xlsx","(updated headers).xlsx")
for ws, df in output.items():
df.to_excel(writer, index=None, sheet_name=ws)
writer.save()
writer.close()
shutil.move(fullpath, destination_path )
考虑到您问题中的代码试图做什么，您可能需要考虑构建功能 and/or 稍微修改文件创建策略。
这里有两种可能的策略。
#1：创建新文件，然后移动它。
#2：在目标目录中就地创建新文件。
无论哪种情况，还可以考虑以下相关问题：
- 目标目录不存在怎么办？您可以允许 python 标准库调用的默认行为（引发异常），或者您可以创建目录。
- 如果目标文件已经存在怎么办？您可以允许默认标准库行为（引发异常），或覆盖它（静默或发出警告），或在将新文件放入目标目录之前重命名现有文件。
例如，下面的代码使用策略 #1（创建和移动文件），根据需要创建目标目录，并用警告覆盖任何现有文件。 （出于测试目的，我更改了源路径和目标路径的名称。）
import pandas as pd
#import datetime as dt
import os
import shutil
#path = "C:/Users/rocky/Desktop/autotranscribe/python/Matching"
#destination_path = ('C:/Users/rocky/Desktop/autotranscribe/python/Matching/Processed')
path = "."
destination_path = ('./Processed')
for file in os.listdir(path):
if file.startswith("TVC")and "(updated headers)" not in file:
dfs = pd.read_excel(file, sheet_name=None)
output = dict()
for ws, df in dfs.items():
if ws in ["Opt-Ins", "New Voting Members", "Temporary Members"]:
continue
if ws in ["Voting Members", "Removed Members"]:
temp = df
#dt = pd.to_datetime(os.path.getctime(os.path.join(path,file)),unit="s").replace(nanosecond=0)
temp['Status'] = "Active" if ws == "Voting Members" else "Cancelled"
output[ws] = temp
destination_file = f'{file.replace(".xlsx","")} (updated headers).xlsx'
destination_file_with_path = f'{destination_path}/{file.replace(".xlsx","")} (updated headers).xlsx'
# Create and move file, create the destination directory if needed, and overwrite any existing file with a warning:
writer = pd.ExcelWriter(destination_file)
for ws, df in output.items():
df.to_excel(writer, index=None, sheet_name=ws)
writer.save()
writer.close()
if not os.path.exists(destination_path):
os.makedirs(destination_path)
if os.path.exists(destination_file_with_path):
print(f'{destination_file_with_path} already exists, overwriting')
os.remove(destination_file_with_path)
shutil.move(destination_file, destination_path)
或者，如果您想使用策略 #2（在其目标目录中创建文件）如果需要再次创建目标目录并覆盖任何现有文件并发出警告，您可以这样做（注意 shutil 是这种方法不需要):
import pandas as pd
#import datetime as dt
import os
#import shutil
#path = "C:/Users/rocky/Desktop/autotranscribe/python/Matching"
#destination_path = ('C:/Users/rocky/Desktop/autotranscribe/python/Matching/Processed')
path = "."
destination_path = ('./Processed')
for file in os.listdir(path):
if file.startswith("TVC")and "(updated headers)" not in file:
dfs = pd.read_excel(file, sheet_name=None)
output = dict()
for ws, df in dfs.items():
if ws in ["Opt-Ins", "New Voting Members", "Temporary Members"]:
continue
if ws in ["Voting Members", "Removed Members"]:
temp = df
#dt = pd.to_datetime(os.path.getctime(os.path.join(path,file)),unit="s").replace(nanosecond=0)
temp['Status'] = "Active" if ws == "Voting Members" else "Cancelled"
output[ws] = temp
destination_file = f'{file.replace(".xlsx","")} (updated headers).xlsx'
destination_file_with_path = f'{destination_path}/{file.replace(".xlsx","")} (updated headers).xlsx'
# Create the destination directory if needed, create the new file in the destination directory, and overwrite any existing file with a warning:
if not os.path.exists(destination_path):
os.makedirs(destination_path)
if os.path.exists(destination_file_with_path):
print(f'{destination_file_with_path} already exists, overwriting')
os.remove(destination_file_with_path)
writer = pd.ExcelWriter(destination_file_with_path)
for ws, df in output.items():
df.to_excel(writer, index=None, sheet_name=ws)
writer.save()
writer.close()