o Zh @sHddlZddlmZmZmZmZmZddlmZm Z GdddeZ dS)N)AnyListOptionalSequenceUnion)BaseDocumentTransformerDocumentc @szeZdZdZ    ddeeeeefdeeeeefdeded e d df d d Z d e e d e d e e fddZ dS)MarkdownifyTransformeramConverts HTML documents to Markdown format with customizable options for handling links, images, other tags and heading styles using the markdownify library. Arguments: strip: A list of tags to strip. This option can't be used with the convert option. convert: A list of tags to convert. This option can't be used with the strip option. autolinks: A boolean indicating whether the "automatic link" style should be used when a a tag's contents match its href. Defaults to True. heading_style: Defines how headings should be converted. Accepted values are ATX, ATX_CLOSED, SETEXT, and UNDERLINED (which is an alias for SETEXT). Defaults to ATX. kwargs: Additional options to pass to markdownify. Example: .. code-block:: python from langchain_community.document_transformers import MarkdownifyTransformer markdownify = MarkdownifyTransformer() docs_transform = markdownify.transform_documents(docs) More configuration options can be found at the markdownify GitHub page: https://github.com/matthewwithanm/python-markdownify NTATXstripconvert autolinks heading_stylekwargsreturncKsBt|tr|gn||_t|tr|gn||_||_||_||_dS)N) isinstancestrr r r radditional_options)selfr r r rrrl/var/www/html/lang_env/lib/python3.10/site-packages/langchain_community/document_transformers/markdownify.py__init__s  zMarkdownifyTransformer.__init__ documentsc Kszddlm}Wn tytdwg}|D],}|d |j|j|j|j|jd|jdd}t dd|}| t ||j d q|S) Nr) markdownifyz`markdownify package not found, please install it with `pip install markdownify`)htmlr r r r  z\n\s*\nz )metadatar)r ImportErrorZ page_contentr r r rrreplaceresubappendrr)rrrrZconverted_documentsdocZmarkdown_contentZcleaned_markdownrrrtransform_documents*s4   z*MarkdownifyTransformer.transform_documents)NNTr )__name__ __module__ __qualname____doc__rrrrboolrrrrr$rrrrr s4 r ) r typingrrrrrZlangchain_core.documentsrrr rrrrs