Skip to main content
Open In ColabOpen on GitHub

mhtml

MHTML 既用于电子邮件，也用于归档网页。MHTML（有时称为 MHT）是 MIME HTML 的缩写，它是一种将完整网页归档为单个文件的格式。当用户以 MHTML 格式保存网页时，该文件扩展名将包含 HTML 代码、图像、音频文件、Flash 动画等内容。

from langchain_community.document_loaders import MHTMLLoader
API 参考：MHTMLLoader
# Create a new loader object for the MHTML file
loader = MHTMLLoader(
    file_path="../../../../../../tests/integration_tests/examples/example.mht"
)

# Load the document from the file
documents = loader.load()

# Print the documents to see the results
for doc in documents:
    print(doc)
page_content='LangChain\nLANG CHAIN 🦜️🔗Official Home Page\xa0\n\n\n\n\n\n\n\nIntegrations\n\n\n\nFeatures\n\n\n\n\nBlog\n\n\n\nConceptual Guide\n\n\n\n\nPython Repo\n\n\nJavaScript Repo\n\n\n\nPython Documentation \n\n\nJavaScript Documentation\n\n\n\n\nPython ChatLangChain \n\n\nJavaScript ChatLangChain\n\n\n\n\nDiscord \n\n\nTwitter\n\n\n\n\nIf you have any comments about our WEB page, you can \nwrite us at the address shown above.  However, due to \nthe limited number of personnel in our corporate office, we are unable to \nprovide a direct response.\n\nCopyright © 2023-2023 LangChain Inc.\n\n\n' metadata={'source': '../../../../../../tests/integration_tests/examples/example.mht', 'title': 'LangChain'}