使用python上传下载文件

使用python上传下载文件

前面我们使用nginx配置了文件上传下载服务器，本文我们学习使用python3上传下载相关文件。

1. 下载文件

# python3， 下载文件并保存

import urllib.request
import os

def download_file(filename):
    # url为拼接出的真实下载地址
    url = f"http://127.0.0.1:88/{filename}"

    # headers为认证信息, YWRtaW46YWRtaW4= 为user:password的base64编码
    headers = {
        'Authorization': 'Basic YWRtaW46YWRtaW4=',
    }

    # 以下代码为获取本地文件大小与下载文件大小，如果相同则返回成功，否则继续下载（断点续传）
    request =urllib.request.Request(url, headers=headers)
    response = urllib.request.urlopen(request)
    total_size = response.length
    local_size = 0
    if os.path.exists(filename):
        local_size = os.path.getsize(filename)
    if total_size == local_size:
        return
    
    headers = {
        'Authorization': 'Basic YWRtaW46YWRtaW4=',
        'Range': 'bytes=%d-' % (local_size),
    }
    request =urllib.request.Request(url, headers=headers)
    response = urllib.request.urlopen(request)
    CHUNK = 128 * 1024
    with open(filename,"ab") as f:
        while True:
            chunk = response.read(CHUNK)
            if not chunk:
                break
            f.write(chunk)

2. 文件sha1校验

对于从服务器上下载大文件，一般需要进行md5/sha1校验，我们假定服务器上已存在下载文件的sha1值，校验值的文件名为原文件名+后缀.sha1

import urllib.request
import hashlib

def check_file_sha1(filename):
    # url为拼接出sha1的真实下载地址
    url = f"http://127.0.0.1/{filename}.sha1"

    # headers为认证信息
    headers = {
        'Authorization': 'Basic YWRtaW46YWRtaW4=',
    }

    request =urllib.request.Request(url, headers=headers)
    response = urllib.request.urlopen(request)
    origin_sha1 = str(response.read(), 'utf-8')

    # 计算本地文件的sha1值并进行对比
    myhash = hashlib.sha1()
    CHUNK = 128 * 1024
    with open(filename,"rb") as f:
        while True:
            chunk = f.read(CHUNK)
            if not chunk:
                break
            myhash.update(chunk)
    now_sha1 = myhash.hexdigest()

    if origin_sha1 == now_sha1:
        return True
    else:
        return False

3. 上传文件

# filepath 需要上传的文件的路径，如果仅包含文件名，则默认为当前路径

import requests

def upload(filepath):
    # url为拼接出的真实上传地址
    url = f"http://127.0.0.1/upload"

    # headers为认证信息
    headers = {
        'Authorization': 'Basic YWRtaW46YWRtaW4=',
    }

    files = {
        "file": open(filepath, 'rb')
    }

    response = requests.post(url, files=files, headers=headers)
    print (response.text)

参考资料

1. Python3 urllib.request库的基本使用, https://blog.csdn.net/kkfd1002/article/details/80306398
2. python3 Requests常用操作, https://www.jianshu.com/p/c6b6aafe72bd
3. python3 的md5和sha1加密, https://blog.csdn.net/xiaozhiit/article/details/82794003