分享一个爬取魔改版OneIndex资源源码，放外服用20-30M/s

yek2furw

发现一个大佬分享的oneindex，特别想要他的资源所以写了这个代码，打开即用

[Python] 纯文本查看 复制代码

import requests, re, urllib


class GetFileUrl(object):
    def __init__(self, url):
        self.url = url
        dict = {
            'name': 'Germey'
        }
        data = bytes(urllib.parse.urlencode(dict), encoding='utf8')
        headers = {
            'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/600.1.4 (KHTML, like Gecko) Mobile/12A365 MicroMessenger/5.4.1 NetType/WIFI'
        }
        req = urllib.request.Request(url=url, data=data, headers=headers, method='GET')

        # def get_data(self):
        self.response = urllib.request.urlopen(req)
        # print(self.response.read().decode('utf8'))

    def re_data(self):
        self.folder_list = []
        self.description_list = []
        data = self.response.read().decode('utf8')
        # print(data)
        # result = re.search(r'<a href=".." class="item" ><i class="material-icons">folder</i>..</a>(.+)</div></div></div>', data)
        result = re.findall(r'</a><a href="(.+?)" class="item" size="(\d+?)"><i class="material-icons">(\w+?)</i>',
                            data, re.M)
        # print(result.group())
        try:
            for item in result:
                # print(item)
                # item1 = urllib.request.quote(item[0])
                if item[2] == "folder":
                    self.folder_list.append((item[0], item[1]))
                else:
                    self.description_list.append((item[0], item[1]))
        except:
            print("没有匹配到链接..")

        return self.folder_list, self.description_list

    def get_file_url(self):
        urls = []
        for i in self.description_list:
            j = urllib.request.quote(i[0])
            urls.append((i, self.url + j))
        return urls


def download_file(url, file_pname, file_size, chunk_size=1024 * 4):
    """
    url: 下载链接
    file_pname: 文件保存路径
    chunk_size: 分块大小
    """
    download_size = 0
    response_data_file = requests.get(url, stream=True)
    with open(file_pname, 'wb') as f:
        for chunk in response_data_file.iter_content(chunk_size=chunk_size):
            if chunk:
                f.write(chunk)
                download_size += chunk_size
                print('\r%s 已下载%dM,共%dM,剩余%dM' % (file_pname, download_size/1024/1024, file_size/1024/1024, (file_size - download_size)/1024/1024), end = "")


def main(url):
    while True:
        try:
            geturl = GetFileUrl(url)
            break
        except urllib.error.HTTPError:
            print("链接没有打开，正在重试...")
    folder_name, file_name = geturl.re_data()
    for file_pname, file_size in file_name:
        file_url = url + urllib.request.quote(file_pname)
        download_file(file_url, file_pname, int(file_size))
        print("%s 下载完成"%file_pname)


if __name__ == '__main__':
    url = input("请输入网址：")
    main(url)

代码不完全，只能爬取当前页面，因为写了一半联系到了大佬，他把mover.io账号给我了，直接搬运不用走vps流量
原来搬运思路是先在vps挂载onedrive，然后直接用这个脚本下载到onedrive目录
想继续开发的大神可以继续开发，我只是提供一个思路
想练手没有onedrive的朋友们可以留下 昵称+前缀，我给你发5T的E5盘

alongzhenggang

老哥5t帐号怎么来的能说说吗

yek2furw

alongzhenggang 发表于 2021-8-21 18:36
老哥5t帐号怎么来的能说说吗

azg@heee5.onmicrosoft.com
Bax92626

alongzhenggang

yek2furw 发表于 2021-8-23 10:33
azg@heee5.onmicrosoft.com
Bax92626

   weiruan的?

叫我小王叔叔

提前开通api哦，我的管理员账号已经死了。悲催的是我只给我自己留了一个账号。