从Google Drive下载并解压ZIP文件至Colab Notebook

import requests

file_id = '1fdFu5NGXe4rTLYKD5wOqk9dl-eJOefXo' # 替换为你的Google Drive文件ID
download_url = f'https://drive.google.com/uc?export=download&id={file_id}'
response = requests.get(download_url)
print(f"Content-Type: {response.headers.get('Content-Type')}")

import requests
import io
import zipfile
import os

# 替换为你的Google Drive文件ID
file_id = '1fdFu5NGXe4rTLYKD5wOqk9dl-eJOefXo' # 示例ID，请替换为实际ZIP文件的ID
download_url = f'https://drive.google.com/uc?export=download&id={file_id}'

# 目标保存路径
output_path = '/content/downloaded_zip.zip'
extraction_dir = '/content/extracted_data/'

print(f"尝试从 {download_url} 下载文件...")

# 处理Google Drive大文件下载时的病毒扫描警告
# Google Drive对于大文件可能会返回一个警告页面，需要模拟点击“下载”
def download_file_from_google_drive(id, destination):
    URL = "https://drive.google.com/uc?export=download"

    session = requests.Session()

    response = session.get(URL, params = { 'id' : id }, stream = True)
    token = get_confirm_token(response)

    if token:
        params = { 'id' : id, 'confirm' : token }
        response = session.get(URL, params = params, stream = True)

    save_response_content(response, destination)    

def get_confirm_token(response):
    for key, value in response.cookies.items():
        if key.startswith('download_warning'):
            return value
    return None

def save_response_content(response, destination):
    CHUNK_SIZE = 32768
    with open(destination, "wb") as f:
        for chunk in response.iter_content(CHUNK_SIZE):
            if chunk: # filter out keep-alive new chunks
                f.write(chunk)

# 执行下载
try:
    download_file_from_google_drive(file_id, output_path)
    print(f"文件已下载到: {output_path}")

    # 检查下载的文件是否是有效的ZIP文件
    if not os.path.exists(output_path) or os.path.getsize(output_path) == 0:
        print("错误：下载的文件为空或不存在。请检查文件ID和权限。")
    else:
        # 解压ZIP文件
        os.makedirs(extraction_dir, exist_ok=True)
        with zipfile.ZipFile(output_path, 'r') as zip_ref:
            zip_ref.extractall(extraction_dir)
        print(f"ZIP文件已成功解压到: {extraction_dir}")

except Exception as e:
    print(f"下载或解压过程中发生错误: {e}")
    print("请确认文件ID是否正确，以及文件是否设置为公开访问。")

# 1. 安装 gdown 库
!pip install gdown -q

import gdown
import zipfile
import os

# 替换为你的Google Drive文件ID
file_id = '1fdFu5NGXe4rTLYKD5wOqk9dl-eJOefXo' # 示例ID，请替换为实际ZIP文件的ID
output_path = '/content/downloaded_zip.zip'
extraction_dir = '/content/extracted_data/'

print(f"使用 gdown 从 Google Drive 下载文件 ID: {file_id}")

try:
    # 2. 使用 gdown 下载文件
    # quiet=False 会显示下载进度
    gdown.download(id=file_id, output=output_path, quiet=False)
    print(f"文件已下载到: {output_path}")

    # 检查下载的文件是否是有效的ZIP文件
    if not os.path.exists(output_path) or os.path.getsize(output_path) == 0:
        print("错误：下载的文件为空或不存在。请检查文件ID和权限。")
    else:
        # 3. 解压ZIP文件
        os.makedirs(extraction_dir, exist_ok=True)
        with zipfile.ZipFile(output_path, 'r') as zip_ref:
            zip_ref.extractall(extraction_dir)
        print(f"ZIP文件已成功解压到: {extraction_dir}")

except Exception as e:
    print(f"下载或解压过程中发生错误: {e}")
    print("请确认文件ID是否正确，以及文件是否设置为公开访问。")

# 验证解压内容 (可选)
# print("\n解压后的文件列表:")
# for root, dirs, files in os.walk(extraction_dir):
#     for name in files:
#         print(os.path.join(root, name))