将4个下载的文件合并为一个

Question

我目前有 4 个文件，我使用 linux 命令 split 将其分解为 50 meg 文件。

我目前正在尝试这个，但它告诉我找不到文件。

import requests
import tempfile
import os
import subprocess as sp

def download_files_from_github(path, model_name):
    if model_name == "u2net":
        part1 = tempfile.NamedTemporaryFile(delete=False)
        part2 = tempfile.NamedTemporaryFile(delete=False)
        part3 = tempfile.NamedTemporaryFile(delete=False)
        part4 = tempfile.NamedTemporaryFile(delete=False)
        try:
            part1_content = requests.get('https://github.com/nadermx/backgroundremover/raw/main/models/u2aa')
            part1.write(part1_content.content)
            part1.close()
            part2_content = requests.get('https://github.com/nadermx/backgroundremover/raw/main/models/u2ab')
            part2.write(part2_content.content)
            part2.close()
            part3_content = requests.get('https://github.com/nadermx/backgroundremover/raw/main/models/u2ac')
            part3.write(part3_content.content)
            part3.close()
            part4_content = requests.get('https://github.com/nadermx/backgroundremover/raw/main/models/u2ad')
            part4.write(part4_content.content)
            part4.close()
            stuff = sp.run('cat %s %s %s %s > %s' % (part1.name, part2.name, part3.name, part4.name, path))
            print(stuff)
        finally:
            os.remove(part1.name)
            os.remove(part2.name)
            os.remove(part3.name)
            os.remove(part4.name)


download_files_from_github('~/.u2net/u2net.pth', 'u2net')

我得到了这个错误

$ python tests.py
Traceback (most recent call last):
  File "tests.py", line 34, in <module>
    download_files_from_github('~/.u2net/u2net.pth', 'u2net')
  File "tests.py", line 25, in download_files_from_github
    stuff = sp.run('cat %s %s %s %s > %s' % (part1.name, part2.name, part3.name, part4.name, path))
  File "/usr/lib/python3.6/subprocess.py", line 423, in run
    with Popen(*popenargs, **kwargs) as process:
  File "/usr/lib/python3.6/subprocess.py", line 729, in __init__
    restore_signals, start_new_session)
  File "/usr/lib/python3.6/subprocess.py", line 1364, in _execute_child
    raise child_exception_type(errno_num, err_msg, err_filename)
FileNotFoundError: [Errno 2] No such file or directory: 'cat /tmp/tmp28877_uq /tmp/tmpx2t9s9we /tmp/tmpj4g8ahhw /tmp/tmpty1x7pjv > ~/.u2net/u2net.pth': 'cat /tmp/tmp28877_uq /tmp/tmpx2t9s9we /tmp/tmpj4g8ahhw /tmp/tmpty1x7pjv > ~/.u2net/u2net.pth'

Answer 1

正如用户建议的那样，subprocess 认为您想将整个命令作为一个单独的东西执行，但失败了。

一个不错的选择是将subprocess.run 字符串参数替换为一个列表：

# pass a list directly
stuff = sp.run(["cat", part1.name, part2.name, part3.name, part4.name, ">", path])

这对我有用。

Answer 2

即使问题已经解决了，如果我不得不这样做，我会做如下的事情：

def download_files_from_github(git_paths, out_file, model_name):
    if model_name == "u2net":
        download_status = {}
        with open(out_file, 'wb') as out:
                for git_path in git_paths:
                    response = requests.get(git_path)
                    out.write(response.content)
                    download_status[git_path] = response.status_code
        return download_status

然后调用程序并捕获响应 status_code（这很重要，因为如果您为其中一个 url 获得 404 status_code，您可能希望在调用程序中丢弃输出文件，或者您可能希望在下载函数中引发错误如果 status_code 为 404，则为自身）

status = download_files_from_github(['https://github.com/nadermx/backgroundremover/raw/main/models/u2aa',
 'https://github.com/nadermx/backgroundremover/raw/main/models/u2ab',
 'https://github.com/nadermx/backgroundremover/raw/main/models/u2acc',
 'https://github.com/nadermx/backgroundremover/raw/main/models/u2ad'],
'<your consolidated out file>', 'u2net')

print(status)

Answer 3

尝试改变

stuff = sp.run('cat %s %s %s %s > %s' % (part1.name, part2.name, part3.name, part4.name, path))

到

stuff = sp.run(f'cat {part1.name} {part2.name} {part3.name} {part4.name} > {path}'.split())

您需要将列表传递给 sp.run，而不是字符串。我所做的基本上是创建执行字符串，然后将其拆分为命令和参数列表。