文件下载-进度条展示

主要包含逻辑

• 支持进度条展示
• 支持断点续传
• 支持检测文件是否已经存在
• 支持检测老版本问题存在并做删除处理

代码实现

import os
import requests
# import wget
import fnmatch
from tqdm import tqdm
import time
import re


def get_cookie():
    """
    从明道云拉取cookie信息
    """
    apiurl = 'https://cooperation.XXX.com:443/api/v2/open/worksheet/getFilterRows'
    headers = {
        "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36 Edg/101.0.1210.39"}
    body = {
        "appKey": "f7b8e6816d39a931",
        "sign": "ODlkNTVhNDdjZDhjNmYwODhjYjExZTU4NGFmODFkZDQzZjRlNGMzMzJlODdhNzhmNTVjYmQ4ZTA1MzAzNzc3Mw==",
        "worksheetId": "hxggzjxx",
        "viewId": "634509562b5b0f8d7a182f39",
        "pageSize": 5000,
        "pageIndex": 1,
        "filters": [
            {
                "controlId": "leibie",
                "dataType": 2,
                "spliceType": 1,
                "filterType": 2,
                "values": ["应用商店审核平台"]}]
    }

    res_data = requests.post(apiurl, json=body, headers=headers).json()['data']['rows']
    for i in res_data:
        if i['leibie'] == '应用商店审核平台' and i['jianmingcheng'] == 'cookie':
            cookie = i['quzhi']
        elif i['leibie'] == '应用商店审核平台' and i['jianmingcheng'] == 'Authorization':
            Authorization = i['quzhi']

    headers = {"Authorization": Authorization,
               "Connection": "keep-alive",
               "Cookie": cookie,
               "Host": "appstore.XXX.com",
               "Referer": "https://appstore.XXX.com/cms/",
               "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36 Edg/101.0.1210.39"
               }
    return headers


headers = get_cookie()


def getv23app_info():
    """
    获取V23上上架的应用
    """
    url = f'https://appstore.XXX.com/prod-api/store-admin-app/getAppList?pageNum=1&pageSize=4000&pkgInstallMode=1&app_name=&searchAppIds=&app_status=101&store_version=11&app_arch=4&appid=&region=&app_mode=1&package_mode=&supWayland=0&appFrom='
    res = requests.get(url, headers=headers).json()['rows']
    res = sorted(res, key=lambda x: x['urge_upt_times'], reverse=True)
    return res


def download_file_with_progress(url, output_path):
    """
    下载并提供进度展示功能，支持断点续传
    """
    local_size = 0
    if os.path.exists(output_path):
        local_size = os.path.getsize(output_path)

    headers = {"Range": f"bytes={local_size}-"}
    response = requests.get(url, headers=headers, stream=True)
    total_size = int(response.headers.get('content-length', 0)) + local_size
    block_size = 1024  # 1 Kibibyte
    progress_bar = tqdm(total=total_size, initial=local_size, unit='iB', unit_scale=True)

    with open(output_path, 'ab') as file:
        for data in response.iter_content(block_size):
            progress_bar.update(len(data))
            file.write(data)
    progress_bar.close()

    if total_size != 0 and progress_bar.n != total_size:
        print("ERROR: Something went wrong")


def download_app(appinfo):
    """
    Check for apps that meet the community test criteria and get download links and app names
    """

    app_name = appinfo['app_name']
    appid = appinfo['appid']

    appinfoid = appinfo['app_info_id']
    appinfo_url = f'https://appstore.XXX.com/prod-api/store-admin-app/getAppDetail/{appinfoid}'
    ressrc = requests.get(appinfo_url, headers=headers).json()['datas']
    res = ressrc['appPackages']
    for j in res:
        if j['pkgArch'] in ['X86', 'x86', '全架构'] and '社区版V23' in j[
            'supSysStr']:  # Here is the filtered Community Edition app
            download_url = f'https://home-store-img.XXX.com/{j["fileSaveKey"]}'
            pkgVersion = j['pkgVersion']

            download_name = f'{appid}_{app_name}_{pkgVersion}.deb'
            download_name = re.sub(r'[:]', ".",download_name)  # Some apps have colons in their version numbers, which need to be handled

            # Check if the file already exists
            if os.path.exists(download_name):
                # Get file size on server
                head_response = requests.head(download_url)
                total_size = int(head_response.headers.get('content-length', 0))

                # Get local file size
                local_size = os.path.getsize(download_name)

                if local_size == total_size:
                    print(f'{download_name} 已存在且完整，跳过下载。')
                    continue
                else:
                    time.sleep(1)
                    local_size_now = os.path.getsize(download_name)

                    if local_size_now != local_size:
                        print(f'{download_name} 有其他程序在下载……')
                        continue

                    print(f'{download_name} 已存在但不完整，准备断点续传……')
            else:
                print(f'准备下载 {download_name} 应用')

            download_file_with_progress(download_url, download_name)
            print(f'{download_name} 应用下载完成！')


def main():
    appinfo = getv23app_info()
    for i in appinfo:
        download_app(i)


if __name__ == '__main__':
    main()