Colab环境下从Google Drive高效下载与解压公共Zip文件教程

import requests

file_id = '1fdFu5NGXe4rTLYKD5wOqk9dl-eJOefXo' # 替换为你的Google Drive文件ID
# 注意：此URL并非直接下载链接，而是用于演示问题
problematic_url = f'https://drive.google.com/file/d/{file_id}' 

response = requests.get(problematic_url)
print(f"Content-Type for problematic URL: {response.headers.get('Content-Type')}")

import requests
import io
import zipfile

# 替换为你的Google Drive文件ID
file_id = '1fdFu5NGXe4rTLYKD5wOqk9dl-eJOefXo' 
# 构建正确的直接下载URL
download_url = f'https://drive.google.com/uc?export=download&id={file_id}'

print(f"Attempting to download from: {download_url}")

# 使用requests库下载文件内容
response = requests.get(download_url, stream=True) # 使用stream=True以处理大文件
response.raise_for_status() # 检查请求是否成功

# 再次检查Content-Type，确保是zip文件
print(f"Content-Type for direct download URL: {response.headers.get('Content-Type')}")

# 将下载的内容加载到内存中
file_contents = io.BytesIO(response.content)

# 确保下载的内容是有效的Zip文件
if not zipfile.is_zipfile(file_contents):
    raise zipfile.BadZipFile("Downloaded content is not a valid zip file. Check file ID and permissions.")

# 解压Zip文件
try:
    with zipfile.ZipFile(file_contents, 'r') as zip_ref:
        # 替换为你的目标解压路径，例如'/content/'是Colab默认的工作目录
        zip_ref.extractall('/content/') 
    print("Zip file extracted successfully to /content/")
except zipfile.BadZipFile as e:
    print(f"Error extracting zip file: {e}. The downloaded file might still be corrupt or not a zip.")

# 替换为你的Google Drive文件ID
file_id = '1fdFu5NGXe4rTLYKD5wOqk9dl-eJOefXo' 
# 构建正确的直接下载URL
download_url = f'https://drive.google.com/uc?export=download&id={file_id}'
# 定义本地保存路径
output_path = '/content/downloaded_data.zip'

# 使用wget下载文件
# --no-check-certificate 选项在某些SSL证书问题时有用，但通常建议省略
# -O 选项指定输出文件名
!wget --no-check-certificate -O '{output_path}' '{download_url}'

# 验证文件是否成功下载并解压
import zipfile
import os

if os.path.exists(output_path):
    print(f"File downloaded successfully to {output_path}")
    if zipfile.is_zipfile(output_path):
        try:
            with zipfile.ZipFile(output_path, 'r') as zip_ref:
                zip_ref.extractall('/content/')
            print("Zip file extracted successfully to /content/")
        except zipfile.BadZipFile as e:
            print(f"Error extracting zip file: {e}. The downloaded file might be corrupt.")
    else:
        print(f"Error: {output_path} is not a valid zip file.")
else:
    print("Error: File download failed.")