harbor镜像仓库拉取所有镜像的信息(镜像版本，tag，大小，最后拉取时间)

# -*- coding: utf-8 -*-
# author: yuhaohao
import requests
from requests.auth import HTTPBasicAuth
from openpyxl import Workbook
from datetime import datetime
import urllib3
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)

# Harbor服务器信息
HARBOR_URL = "https://registry.test.com"
USERNAME = "test"
PASSWORD = "1345566"
PROJECT_NAME = "test"

# 关闭SSL验证（如果是自签名证书）
VERIFY_SSL = False


def get_all_repositories():
    repos = []
    page = 1
    while True:
        url = f"{HARBOR_URL}/api/v2.0/projects/{PROJECT_NAME}/repositories?page={page}&page_size=100"
        response = requests.get(url, auth=HTTPBasicAuth(USERNAME, PASSWORD), verify=VERIFY_SSL)
        response.raise_for_status()
        data = response.json()
        if not data:
            break
        repos.extend(data)
        page += 1
    return repos

def get_all_artifacts(repository_name):
    artifacts = []
    page = 1
    while True:
        url = f"{HARBOR_URL}/api/v2.0/projects/{PROJECT_NAME}/repositories/{repository_name}/artifacts?page={page}&page_size=100"
        response = requests.get(url, auth=HTTPBasicAuth(USERNAME, PASSWORD), verify=VERIFY_SSL)
        response.raise_for_status()
        data = response.json()
        if not data:
            break
        artifacts.extend(data)
        page += 1
    return artifacts

def format_pull_time(pull_time_str):
    if not pull_time_str:
        return ''
    try:
        dt = datetime.fromisoformat(pull_time_str.replace('Z', '+00:00'))
        return dt.strftime("%Y-%m-%d %H:%M:%S")
    except Exception:
        return ''

def main():
    repositories = get_all_repositories()
    all_data = []

    for repo in repositories:
        full_repo_name = repo['name']  # project_name/repo_name
        repo_name_only = full_repo_name.split('/')[1]  # 仓库名

        artifacts = get_all_artifacts(repo_name_only)

        for artifact in artifacts:
            size_bytes = artifact.get('size', 0)
            size_gb = size_bytes / (1024 * 1024 * 1024)
            last_pull_time = artifact.get('pull_time', '')
            formatted_pull_time = format_pull_time(last_pull_time)
            tags = artifact.get('tags', [])

            if tags:
                for tag in tags:
                    all_data.append({
                        '镜像名称': full_repo_name,
                        '镜像标签': tag['name'],
                        '镜像大小(GB)': round(size_gb, 2),
                        '最后拉取时间': formatted_pull_time
                    })
            else:
                all_data.append({
                    '镜像名称': full_repo_name,
                    '镜像标签': '',
                    '镜像大小(GB)': round(size_gb, 2),
                    '最后拉取时间': formatted_pull_time
                })

    # 根据 镜像名称 排序，保证同名镜像连在一起
    all_data.sort(key=lambda x: x['镜像名称'])

    # 写入Excel
    wb = Workbook()
    ws = wb.active
    ws.title = "Harbor镜像信息"

    # 写表头
    headers = ['镜像名称', '镜像标签', '镜像大小(GB)', '最后拉取时间']
    ws.append(headers)

    # 写数据
    for item in all_data:
        ws.append([
            item['镜像名称'],
            item['镜像标签'],
            item['镜像大小(GB)'],
            item['最后拉取时间']
        ])

    # 保存文件
    excel_file = "harbor镜像信息.xlsx"
    wb.save(excel_file)
    print(f"✅ 导出完成，文件保存为：{excel_file}")

if __name__ == "__main__":
    main()