git_clone.py

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# @Filename :   clone.py
# @Date     :   18-2-6 12:36
# @Author   :   DebuggerX
import re
import urllib

import subprocess

import os

repositories = []


def get_page(url, index):
    html = urllib.urlopen('%s?page=%d' % (url, index)).read()
    if html and "Page not found" not in html and 'This organization has no more repositories' not in html:
        assert isinstance(html, str)
        shtmls = re.findall("href=\".+\" itemprop=\"name codeRepository\"", html)
        for shtml in shtmls:
            assert isinstance(shtml, str)
            repositories.append(shtml[6:shtml.find('" itemprop')])
        print("正在分析第%d页" % index)
        index += 1
        get_page(baseUrl, index)
    else:
        pass


if __name__ == '__main__':

    account = raw_input('请输入github用户名，将分析该账户下所有仓库\n')

    baseUrl = 'https://github.com/%s' % account
    print("开始分析仓库。。。")
    get_page(baseUrl, 1)
    print("总共得到%d条仓库信息" % len(repositories))
    print("开始抓取各个仓库")
    cmd = ''
    for repository in repositories:
        print('https://github.com%s' % repository)

    print('按任意键开始克隆以上所有仓库')
    subprocess.call("bash -c 'read' '-n' '1'", shell=True)

    for repository in repositories:
        os.system('git clone https://github.com%s.git' % repository)