使用python批量拉取分支下载主分支和分支的文件

最新推荐文章于 2024-07-01 13:05:35 发布

前端菜鸡(全栈版)

最新推荐文章于 2024-07-01 13:05:35 发布

阅读量585

点赞数 11

分类专栏： python 文章标签： python elasticsearch 开发语言

本文链接：https://blog.csdn.net/qq_45743174/article/details/136537124

版权

python 专栏收录该内容

1 篇文章 0 订阅

订阅专栏

getAllGithubBranch.py

#!/usr/bin/env python
# encoding: utf-8

import os
import subprocess

def export_git_branches_to_folders(local_repo_path, output_dir):
    """
    Clones all branches from a local git repository and exports them to separate folders.

    :param local_repo_path: The path to the local git repository.
    :param output_dir: The path to the output directory where branch folders will be created.
    """
    # 确保输出目录存在
    os.makedirs(output_dir, exist_ok=True)

    # 切换到Git仓库目录
    os.chdir(local_repo_path)

    # 获取所有远程分支列表
    branches = subprocess.check_output(['git', 'branch', '-r']).decode().splitlines()

    # 处理每个远程分支
    for branch in branches:
        branch = branch.strip()
        if '->' in branch:
            # 跳过引用头指针
            continue

        # 分支名格式化：去除"origin/"并将斜杠替换为下划线
        branch_name = branch.replace('origin/', '').replace('/', '_')

        # 创建分支对应的输出目录
        branch_dir = os.path.join(output_dir, branch_name)
        os.makedirs(branch_dir, exist_ok=True)

        # 使用git archive将分支内容导出到tar文件，然后解压到目标文件夹
        subprocess.run(['git', 'archive', '--format=tar', branch, '-o', 'temp.tar'])
        subprocess.run(['tar', '-xf', 'temp.tar', '-C', branch_dir])
        os.remove('temp.tar')

    print("All branches have been exported to folders.")

def clone_all_branches(repo_list_file, output_dir):
    """
    Clone all branches from each repository listed in a txt file.

    :param repo_list_file: The path to the txt file containing git repository URLs.
    :param output_dir: The base directory to clone the repositories into.
    """
    # 确保输出目录存在
    os.makedirs(output_dir, exist_ok=True)

    # 读取仓库列表文件
    with open(repo_list_file, 'r') as file:
        repos = file.readlines()

    # 克隆每个仓库的所有分支
    cloned_repos = []
    for repo_url in repos:
        repo_url = repo_url.strip()
        if not repo_url:
            continue

        # 从仓库URL中提取仓库名
        repo_name = os.path.basename(repo_url)
        if repo_name.endswith('.git'):
            repo_name = repo_name[:-4]

        # 克隆目录路径
        clone_dir = os.path.join(output_dir, repo_name)

        # 克隆仓库
        print(f'Cloning repository: {repo_url}')
        subprocess.run(['git', 'clone', repo_url, clone_dir])

        # 添加克隆的仓库路径到列表中
        cloned_repos.append(os.path.abspath(clone_dir))

    return cloned_repos

# 使用
# repo_list_file = txt文件路径
repo_list_file = 'github_url.txt'
# repo_dir = 仓库目录
repo_dir = '/repo'
# output_dir = 输出目录
output_dir = '/cloned_repositories'

cloned_repos_paths = clone_all_branches(repo_list_file, repo_dir)
for repo_path in cloned_repos_paths:
    print(repo_path)
    file_path = repo_path.split("/")[-1]
    print("out: ", output_dir+f"/{file_path}")
    repos = export_git_branches_to_folders(repo_path, output_dir+f"/{file_path}")