构建企业级Python离线包仓库的服务部署全流程指南

pip install pandas tqdm pypiserver

import pandas as pd
import subprocess
from tqdm import tqdm

# 读取热门包列表
data = pd.read_csv("top-pypi-packages.csv")
# 过滤掉非字符串项目
data = data.loc[data["project"].apply(lambda x: isinstance(x, str)), "project"].values.tolist()

# 为每批5个包执行下载命令
for i in tqdm(range(0, len(data), 5)):
    command = "pip download -i https://mirrors.aliyun.com/pypi/simple/ " \
              "--python-version 3.13 --platform any --only-binary=:all: " \
              "-d ./python_packages {}".format(" ".join(data[i:i+5]))
    result = subprocess.run(command, shell=True, capture_output=True, text=True)
    
    # 检查命令是否成功执行
    if result.returncode != 0:
        print(f"下载失败: {data[i:i+5]}")
        print(f"错误信息: {result.stderr}")

# 调整参数，移除Python版本限制
command = "pip download -i https://mirrors.aliyun.com/pypi/simple/ " \
          "--platform any --only-binary=:all: -d ./python_packages {}".format(" ".join(data[i:i+5]))

from tenacity import retry, stop_after_attempt, wait_fixed

@retry(stop=stop_after_attempt(3), wait=wait_fixed(2))
def download_packages(packages):
    command = f"pip download -i https://mirrors.aliyun.com/pypi/simple/ --python-version 3.13 --platform any --only-binary=:all: -d ./python_packages {' '.join(packages)}"
    result = subprocess.run(command, shell=True, capture_output=True, text=True)
    if result.returncode != 0:
        raise Exception(f"下载失败: {result.stderr}")
    return result

pypi-server run -p 8080 -a update,download ./python_packages

# 创建密码文件
htpasswd -c .htpasswd username

# 启动带认证的服务
pypi-server run -p 8080 -P .htpasswd -a update,download ./python_packages

pip install package_name -i http://localhost:8080/simple/ --trusted-host localhost

[global]
index-url = http://localhost:8080/simple/
trusted-host = localhost

pip install package_name -i http://username:password@localhost:8080/simple/ --trusted-host localhost

#!/usr/bin/env python3
"""
Python离线包仓库构建工具
功能：
1. 从hugovk/top-pypi-packages获取热门包列表
2. 从阿里云镜像批量下载wheel文件
3. 创建本地PyPI服务
"""

import os
import sys
import pandas as pd
import subprocess
from tqdm import tqdm
from tenacity import retry, stop_after_attempt, wait_fixed

def download_top_packages():
    """下载热门Python包"""
    # 创建包存储目录
    os.makedirs("./python_packages", exist_ok=True)
    
    # 读取热门包列表
    data = pd.read_csv("top-pypi-packages.csv")
    data = data.loc[data["project"].apply(lambda x: isinstance(x, str)), "project"].values.tolist()
    
    print(f"共找到 {len(data)} 个包需要下载")
    
    # 批量下载
    for i in tqdm(range(0, len(data), 5)):
        download_packages(data[i:i+5])

@retry(stop=stop_after_attempt(3), wait=wait_fixed(2))
def download_packages(packages):
    """下载指定包列表"""
    command = f"pip download -i https://mirrors.aliyun.com/pypi/simple/ " \
              f"--python-version 3.13 --platform any --only-binary=:all: " \
              f"-d ./python_packages {' '.join(packages)}"
    
    print(f"正在下载: {' '.join(packages)}")
    result = subprocess.run(command, shell=True, capture_output=True, text=True)
    
    if result.returncode != 0:
        error_msg = f"下载失败: {packages}\n错误信息: {result.stderr}"
        print(error_msg)
        raise Exception(error_msg)
    
    return result

def start_pypi_server():
    """启动本地PyPI服务"""
    print("\n启动本地PyPI服务...")
    print("访问地址: http://localhost:8080/simple/")
    print("使用Ctrl+C停止服务")
    
    # 检查是否需要认证
    auth_args = []
    if os.path.exists(".htpasswd"):
        auth_args = ["-P", ".htpasswd"]
    
    # 启动服务
    subprocess.run([
        "pypi-server", "run", "-p", "8080", 
        "-a", "update,download", *auth_args,
        "./python_packages"
    ])

def main():
    """主函数"""
    if len(sys.argv) > 1 and sys.argv[1] == "server":
        start_pypi_server()
    else:
        # 下载热门包
        download_top_packages()
        print("\n所有包下载完成！")
        print("运行 'python script.py server' 启动本地PyPI服务")

if __name__ == "__main__":
    main()

import os
from pkginfo import Wheel

package_dir = "./python_packages"
invalid_packages = []

for filename in os.listdir(package_dir):
    if filename.endswith(".whl"):
        try:
            wheel = Wheel(os.path.join(package_dir, filename))
            # 验证必要字段
            assert wheel.name, "缺少包名"
            assert wheel.version, "缺少版本号"
        except Exception as e:
            invalid_packages.append((filename, str(e)))

if invalid_packages:
    print(f"发现 {len(invalid_packages)} 个无效包:")
    for pkg, error in invalid_packages:
        print(f"- {pkg}: {error}")
else:
    print("所有包验证通过！")