Microsoft Excel

UnstructuredExcelLoader用于加载Microsoft Excel文件。该加载器适用于.xlsx和.xls文件。页面内容将是Excel文件的原始文本。如果您在"elements"模式下使用加载器，则Excel文件的HTML表示将在文档元数据中以"text_as_html"键的形式提供。

from langchain.document_loaders import UnstructuredExcelLoader

loader = UnstructuredExcelLoader(
    "example_data/stanley-cups.xlsx",
    mode="elements"
)
docs = loader.load()
docs[0]

Document(page_content='\n \n \n Team\n Location\n Stanley Cups\n \n \n Blues\n STL\n 1\n \n \n Flyers\n PHI\n 2\n \n \n Maple Leafs\n TOR\n 13\n \n \n', metadata={'source': 'example_data/stanley-cups.xlsx', 'filename': 'stanley-cups.xlsx', 'file_directory': 'example_data', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'page_number': 1, 'page_name': 'Stanley Cups', 'text_as_html': '<table border="1" class="dataframe">\n <tbody>\n <tr>\n <td>Team</td>\n <td>Location</td>\n <td>Stanley Cups</td>\n </tr>\n <tr>\n <td>Blues</td>\n <td>STL</td>\n <td>1</td>\n </tr>\n <tr>\n <td>Flyers</td>\n <td>PHI</td>\n <td>2</td>\n </tr>\n <tr>\n <td>Maple Leafs</td>\n <td>TOR</td>\n <td>13</td>\n </tr>\n </tbody>\n</table>', 'category': 'Table'})