python - 在从一个文件夹传输到另一个 Python 期间修改多个文件
问题描述
现在我有一个程序将文件从 SOURCE 文件夹中的子目录移动到 DESTINATION 文件夹中的子目录。这些文件包含如下信息: 移动前的文件内容。
现在在从 SOURCE 到 DESTINATION 的移动过程中,我想修改 2 个位置的移动文件。
- 我想复制时间并将其粘贴为时间下的 TimeDif。类型保持 Y 并且值必须是当前时间 - Time 的值。
- 我想修改 Power * 10 的值。如果 Power =< 1000 的值,则类型保持 N,否则 Power 的类型 = Y
因此,在文件从 SOURCE 移动到 DESTINATION 后,它必须如下所示:
这是我现在用于移动文件的代码,所有移动都很顺利。当我想修改文件的内容时,我只是不知道从哪里开始:
import os, os.path
import time
#Make source, destination and archive paths.
source = r'c:\data\AS\Desktop\Source'
destination = r'c:\data\AS\Desktop\Destination'
archive = r'c:\data\AS\Desktop\Archive'
#Make directory paths and make sure to consider only directories under source.
for subdir in os.listdir(source):
subdir_path = os.path.join(source, subdir)
if not os.path.isdir(subdir_path):
continue
#Now we want to get the absolute paths of the files inside those directories
#and store them in a list.
all_file_paths = [os.path.join(subdir_path, file) for file in os.listdir(subdir_path)]
all_file_paths = [p for p in all_file_paths if os.path.isfile(p)]
#Exclude empty sub-directories
if len(all_file_paths) == 0:
continue
#Get only the newest files of those directories.
newest_file_paths = max(all_file_paths, key=os.path.getctime)
#Now we are selecting the files which will be moved
#and make a destination path for them.
for file_path in all_file_paths:
if file_path == newest_file_paths and os.path.getctime(newest_file_paths) < time.time() - 120:
dst_root = destination
else:
dst_root = archive
#Now its time to make the move.
dst_path = os.path.join(dst_root, subdir, os.path.basename(file_path))
os.rename(file_path, dst_path)
解决方案
如果文件很小,那么您可以简单地移动文件而不是移动文件:
- 从所有文件中读取信息
- 找到要替换的数据
- 用源目录中的新数据写入文件
- 删除旧文件
就像是
def move_file(file_path, dst_path):
with open(file_path, "r") as input_file, open(dst_path, "w") as output_file:
for line in input_file:
if <line meets criteria to modify>:
<modify_line>
print(line, file=output_file)
for <data> in <additional_data>:
print(<data>, file=output_file)
# remove the old file
os.remove(file_path)
然后代替原始代码中的 os.rename 调用 move_file 函数
#Now we are selecting the files which will be moved
#and make a destination path for them.
for file_path in all_file_paths:
if file_path == newest_file_paths and os.path.getctime(newest_file_paths) < time.time() - 120:
dst_root = destination
else:
dst_root = archive
#Now its time to make the move.
dst_path = os.path.join(dst_root, subdir, os.path.basename(file_path))
move_file(file_path, dst_path)
你可以像这样实现
import os
import time
from datetime import datetime
SOURCE = r'c:\data\AS\Desktop\Source'
DESTINATION = r'c:\data\AS\Desktop\Destination'
ARCHIVE = r'c:\data\AS\Desktop\Archive'
def get_time_difference(date, time_string):
"""
You may want to modify this logic to change the way the time difference is calculated.
"""
time_difference = datetime.now() - datetime.strptime(f"{date} {time_string}", "%d-%m-%Y %H:%M")
hours = time_difference.total_seconds() // 3600
minutes = (time_difference.total_seconds() % 3600) // 60
return f"{int(hours)}:{int(minutes)}"
def move_and_transform_file(file_path, dst_path, delimiter="\t"):
"""
Reads the data from the old file, writes it into the new file and then
deletes the old file.
"""
with open(file_path, "r") as input_file, open(dst_path, "w") as output_file:
data = {
"Date": None,
"Time": None,
"Power": None,
}
time_difference_seen = False
for line in input_file:
(line_id, item, line_type, value) = line.strip().split()
if item in data:
data[item] = value
if not time_difference_seen and data["Date"] is not None and data["Time"] is not None:
time_difference = get_time_difference(data["Date"], data["Time"])
time_difference_seen = True
print(delimiter.join([line_id, "TimeDif", line_type, time_difference]), file=output_file)
if item == "Power":
value = str(int(value) * 10)
print(delimiter.join((line_id, item, line_type, value)), file=output_file)
os.remove(file_path)
def process_files(all_file_paths, newest_file_path, subdir):
"""
For each file, decide where to send it, then perform the transformation.
"""
for file_path in all_file_paths:
if file_path == newest_file_path and os.path.getctime(newest_file_path) < time.time() - 120:
dst_root = DESTINATION
else:
dst_root = ARCHIVE
dst_path = os.path.join(dst_root, subdir, os.path.basename(file_path))
move_and_transform_file(file_path, dst_path)
def main():
"""
Gather the files from the directories and then process them.
"""
for subdir in os.listdir(SOURCE):
subdir_path = os.path.join(SOURCE, subdir)
if not os.path.isdir(subdir_path):
continue
all_file_paths = [
os.path.join(subdir_path, p)
for p in os.listdir(subdir_path)
if os.path.isfile(os.path.join(subdir_path, p))
]
if all_file_paths:
newest_path = max(all_file_paths, key=os.path.getctime)
process_files(all_file_paths, newest_path, subdir)
if __name__ == "__main__":
main()
推荐阅读
- arrays - 如何使用 Angular 中的 observables 在 API http 请求的所有页面中获取数据?
- node.js - 如何使用 mongoose 获取最近添加的文档?
- python - 名称以下划线开头的变量/方法是内部的还是受保护的?
- cmake - Cmake添加外部项目?
- c# - 如何修复“路径中的非法字符”。在文件路径中?
- regex - 如何在vim中搜索所有不包含'/'的字符串?
- blockchain - 是否有必要使用加密货币进行支付,使用区块链?
- php - 当声明数组变量在视图中未定义但使用控制器 laravel 5.7 时该怎么办
- bash - 如何验证 IP 地址范围(Shell 脚本)
- c# - 异步文件读取比同步或手动线程慢 40 倍