从谷歌文档中获取特定表中的InlineImage

pip install google-auth google-auth-oauthlib google-auth-httplib2 google-api-python-client

from google.oauth2 import service_account
from googleapiclient.discovery import build

# 替换为你的服务账号密钥文件路径
SERVICE_ACCOUNT_FILE = 'path/to/your/service-account-file.json'

# 替换为你的Google Docs文档ID
DOCUMENT_ID = 'your-google-docs-document-id'

# 使用服务账号进行身份验证
credentials = service_account.Credentials.from_service_account_file(
    SERVICE_ACCOUNT_FILE,
    scopes=['https://www.googleapis.com/auth/documents.readonly']
)

# 构建Google Docs API客户端
service = build('docs', 'v1', credentials=credentials)

# 获取文档内容
document = service.documents().get(documentId=DOCUMENT_ID).execute()

def find_images_in_table(document):
    images = []
    for element in document.get('body').get('content'):
        if 'table' in element:
            table = element['table']
            for row in table['tableRows']:
                for cell in row['tableCells']:
                    for content in cell['content']:
                        if 'paragraph' in content:
                            for element in content['paragraph']['elements']:
                                if 'inlineObjectElement' in element:
                                    inline_object_id = element['inlineObjectElement']['inlineObjectId']
                                    inline_object = document['inlineObjects'][inline_object_id]
                                    if 'inlineObjectProperties' in inline_object:
                                        embedded_object = inline_object['inlineObjectProperties']['embeddedObject']
                                        if 'imageProperties' in embedded_object:
                                            images.append(embedded_object['imageProperties']['contentUri'])
    return images

# 查找文档中的图片
images = find_images_in_table(document)

# 打印找到的图片URL
for image in images:
    print(image)