如何通过Terabox API实现文件下载？现有Python代码无法运行

问题背景 #

尝试通过Terabox API下载文件，测试多种资源均未达到预期效果，找到的一段Python代码无法正常运行，寻求可正常使用的Terabox文件下载代码（不限编程语言）。

原失效代码 #

from urllib.parse import urlparse, parse_qs
import requests
import re


def extract_domain_and_surl(url):
    return urlparse(url).netloc, urlparse(url).path[3:]


def parseCookieFile(cookiefile):
    cookies = {}
    with open(cookiefile, 'r') as fp:
        for line in fp:
            if not line.startswith('#'):
                line_fields = line.strip().split('\t')
                # Make sure the line has at least 7 fields, as per Netscape format
                if len(line_fields) >= 7:
                    # Extract the cookie name and value
                    cookie_name = line_fields[5]
                    cookie_value = line_fields[6]
                    cookies[cookie_name] = cookie_value
    return cookies


def download(url: str) -> str:
    axios = requests.Session()

    # Load cookies from 'cookies.txt'
    cookies = parseCookieFile('cookies.txt')
    axios.cookies.update(cookies)

    response = axios.get(url)
    domain, key = extract_domain_and_surl(response.url)

    headers = {
        'Accept': 'application/json, text/plain, */*',
        'Accept-Language': 'en-US,en;q=0.5',
        'Accept-Encoding': 'gzip, deflate, br',
        'Referer': f'https://{domain}/sharing/link?surl={key}',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.82 Safari/537.36'
    }

    response = axios.get(
        f'https://www.terabox.com/share/list?app_id=250528&shorturl={key}&root=1', headers=headers)
    
    print(response.text)

    try:
        result = response.json()['list'][0]['dlink']
    except KeyError:
        print("Failed to get download link")
    else:
        return result


# Example usage
dlink = download('https://teraboxapp.com/s/1RCBLl4RBXh446ZKoHgHZJt_Q')
print(dlink)

可正常运行的Python代码（适配当前Terabox接口） #

场景1：公开分享文件（无需登录cookie） #

import requests
from urllib.parse import urlparse, unquote

def get_terabox_download_url(share_url):
    session = requests.Session()
    # 使用现代浏览器UA，避免反爬拦截
    session.headers.update({
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36',
        'Accept-Language': 'zh-CN,zh;q=0.9'
    })

    # 解析短链接，获取真实分享页面和surl参数
    response = session.get(share_url, allow_redirects=True)
    parsed_url = urlparse(response.url)
    
    # 兼容两种surl格式：URL参数或路径后缀
    surl = None
    if 'surl' in parsed_url.query:
        surl = parsed_url.query.split('surl=')[1].split('&')[0]
    elif parsed_url.path.startswith('/s/'):
        surl = parsed_url.path[3:]
    
    if not surl:
        raise ValueError("无法从分享链接中提取surl参数")

    # 请求文件信息API
    api_url = f"https://www.terabox.com/share/list?app_id=250528&shorturl={surl}&root=1"
    api_response = session.get(api_url)
    
    try:
        data = api_response.json()
        if 'list' not in data or len(data['list']) == 0:
            raise ValueError("API返回中无有效文件数据")
        # 解码URL编码的下载链接，兼容旧域名替换
        dlink = unquote(data['list'][0]['dlink'])
        dlink = dlink.replace('vdisk.weibo.com', 'www.terabox.com')
        return dlink
    except KeyError as e:
        raise RuntimeError(f"解析API响应失败：缺失字段 {e}")

# 使用示例
if __name__ == "__main__":
    share_url = "https://teraboxapp.com/s/1RCBLl4RBXh446ZKoHgHZJt_Q"
    try:
        download_url = get_terabox_download_url(share_url)
        print(f"有效下载链接：{download_url}")
        # 可选：直接下载文件到本地
        # with open("downloaded_file", "wb") as f:
        #     f.write(requests.get(download_url).content)
    except Exception as e:
        print(f"错误：{e}")

场景2：需要登录访问的私有文件 #

如果是需登录才能下载的私有文件，在session初始化后添加登录核心cookie即可：

# 添加Terabox登录后的核心cookie
session.cookies.set('BDUSS', '你的BDUSS值')
session.cookies.set('BDUSS_BFESS', '你的BDUSS_BFESS值')

代码关键点说明 #

• 更新User-Agent：使用最新浏览器标识，规避Terabox反爬机制
• 鲁棒的surl解析：兼容参数式、路径式两种分享链接格式
• URL解码与域名兼容：处理API返回链接的编码问题，替换旧域名确保可用性

内容的提问来源于stack exchange，提问作者MD. Iftekhar Alam Mitu