PyDrive2下载共享Google Drive文件遇错求助：实现全量下载

我使用PyDrive2批量下载Google Drive共享文件夹中的文件，部分文件可正常下载，但处理不同类型文件时出现报错。需求是优先将文件转为纯文本格式下载，无法转换则按原格式下载，已完成认证流程并处理了部分已知错误，但仍存在两类核心错误：

1. Use Export with Docs Editors files
2. The requested conversion is not supported.

代码片段1 #

# Paginate file lists by specifying number of max results
for file_list in drive.ListFile({'q': 'trashed=false', 'maxResults': 500}):
    print('Received %s files from Files.list()' % len(file_list))  # <= 10
    for i, file1 in enumerate(file_list):
        print('\ntitle: %s, id: %s' % (file1['title'], file1['id']))
        print('Downloading {} from GDrive ({}/{})'.format(file1['title'], i, len(file_list)))
        if file1['title'] in ['SOPs']:
            continue
        #file1.GetContentFile(file1['title'], mimetype="text/plain", remove_bom=True)
        try:
            #file1.GetContentFile(file1['title'])
            file1.GetContentFile(file1['title'], mimetype="text/plain", remove_bom=True)
        except errors.HttpError as err:
            print(err)
            continue
        except ApiRequestError as err:
            print(err)
            continue
        except:
            print(f'Some other error')
            continue

代码片段2 #

from pydrive2.auth import GoogleAuth
from pydrive2.drive import GoogleDrive
from googleapiclient.errors import HttpError

GoogleAuth.DEFAULT_SETTINGS['client_config_file'] = '/Users/kk/acs/client_secrets.json'


def main():
    gauth = GoogleAuth()
    gauth.LocalWebserverAuth()
    drive = GoogleDrive(gauth)

    for file_list in drive.ListFile({'q': 'trashed=false', 'maxResults': 500}):
        print('Received %s files from Files.list()' % len(file_list))  # <= 10
        for i, file1 in enumerate(file_list):
            print('\ntitle: %s, id: %s' % (file1['title'], file1['id']))
            print('Downloading {} from GDrive ({}/{})'.format(file1['title'], i, len(file_list)))

            #file1.GetContentFile(file1['title'], mimetype="text/plain", remove_bom=True)
            file1.GetContentFile(file1['title'])



    # errors:
    # pydrive2.files.ApiRequestError: <HttpError 400 when requesting https://www.googleapis.com/drive/v2/files/1k*********6UEZb7/export?mimeType=text%2Fplain&alt=media returned "Export only supports Docs Editors files.". Details: "[{'message': 'Export only supports Docs Editors files.', 'domain': 'global', 'reason': 'badRequest'}]">

    # googleapiclient.errors.HttpError: <HttpError 403 when requesting https://www.googleapis.com/drive/v2/files/1kd*********UEZb7?acknowledgeAbuse=false&alt=media returned "Only files with binary content can be downloaded. Use Export with Docs Editors files.". Details: "[{'message': 'Only files with binary content can be downloaded. Use Export with Docs Editors files.', 'domain': 'global', 'reason': 'fileNotDownloadable', 'location': 'alt', 'locationType': 'parameter'}]">

    # pydrive2.files.ApiRequestError: <HttpError 400 when requesting https://www.googleapis.com/drive/v2/files/1s-*********2mOw/export?mimeType=text%2Fplain&alt=media returned "The requested conversion is not supported.". Details: "[{'message': 'The requested conversion is not supported.', 'domain': 'global', 'reason': 'badRequest', 'location': 'convertTo', 'locationType': 'parameter'}]">


if __name__ == '__main__':
    main()

核心逻辑 #

Google Drive文件分为两类，需分别处理：

• Docs Editors文件：如Google Docs/Sheets/Slides，无法直接下载原文件，必须通过Export接口转换格式
• 普通二进制文件：如PDF、图片、压缩包等，可直接调用下载接口获取原文件

通过判断文件的mimeType区分类型，先尝试转纯文本，失败则回退到原格式下载。

优化后代码 #

from pydrive2.auth import GoogleAuth
from pydrive2.drive import GoogleDrive
from googleapiclient.errors import HttpError
from pydrive2.files import ApiRequestError

GoogleAuth.DEFAULT_SETTINGS['client_config_file'] = '/Users/kk/acs/client_secrets.json'

# 定义Google Docs编辑器类文件的MIME类型
DOCS_EDITORS_MIMETYPES = [
    'application/vnd.google-apps.document',
    'application/vnd.google-apps.spreadsheet',
    'application/vnd.google-apps.presentation',
    'application/vnd.google-apps.form',
    'application/vnd.google-apps.drawing'
]

def download_file(file1):
    print(f'\ntitle: {file1["title"]}, id: {file1["id"]}')
    print(f'Downloading {file1["title"]} from GDrive')
    
    # 跳过指定文件夹
    if file1['title'] == 'SOPs':
        return
    
    file_mime = file1['mimeType']
    success = False

    # 第一步：尝试导出为纯文本
    try:
        if file_mime in DOCS_EDITORS_MIMETYPES:
            # Docs类文件调用Export接口转纯文本
            file1.GetContentFile(f'{file1["title"]}.txt', mimetype='text/plain', remove_bom=True)
        else:
            # 普通文件尝试转纯文本（如PDF等支持转换的格式）
            file1.GetContentFile(f'{file1["title"]}_text.txt', mimetype='text/plain', remove_bom=True)
        print(f'✅ 成功转为纯文本下载：{file1["title"]}')
        success = True
    except (HttpError, ApiRequestError) as err:
        error_msg = str(err)
        # 针对两类核心错误，回退到原格式下载
        if "Export only supports Docs Editors files" in error_msg or "Only files with binary content can be downloaded" in error_msg:
            try:
                file1.GetContentFile(file1['title'])
                print(f'🔄 转为纯文本失败，已下载原格式：{file1["title"]}')
                success = True
            except Exception as e:
                print(f'❌ 原格式下载失败：{file1["title"]} - {str(e)}')
        elif "The requested conversion is not supported" in error_msg:
            try:
                file1.GetContentFile(file1['title'])
                print(f'⚠️ 不支持转为纯文本，已下载原格式：{file1["title"]}')
                success = True
            except Exception as e:
                print(f'❌ 原格式下载失败：{file1["title"]} - {str(e)}')
        else:
            print(f'❌ 未知错误：{file1["title"]} - {str(err)}')
    except Exception as e:
        print(f'❌ 其他错误：{file1["title"]} - {str(e)}')
    
    if not success:
        print(f'❌ 最终下载失败：{file1["title"]}')

def main():
    gauth = GoogleAuth()
    gauth.LocalWebserverAuth()
    drive = GoogleDrive(gauth)

    for file_list in drive.ListFile({'q': 'trashed=false', 'maxResults': 500}):
        print(f'\n📥 收到 {len(file_list)} 个文件')
        for file1 in file_list:
            download_file(file1)

if __name__ == '__main__':
    main()

关键说明 #

1. 类型区分：通过mimeType判断是否为Docs Editors文件，避免对普通文件调用Export接口
2. 错误针对性处理：捕获两类核心错误后直接回退到原格式下载，减少无效重试
3. 文件名区分：导出纯文本时添加_text.txt后缀，避免与原文件重名（可根据需求调整）
4. 异常细化：不再用通配符捕获所有异常，便于定位问题

额外建议 #

• Google Sheets转纯文本可能丢失格式，可优先尝试导出为CSV（text/csv）再转纯文本
• 若需遍历子文件夹，可判断mimeType是否为application/vnd.google-apps.folder，然后递归调用下载逻辑
• 增加日志记录功能，方便后续排查下载失败的文件

内容的提问来源于stack exchange，提问作者user1717931