
    dh*                     :    S SK JrJr  S SKJrJr   " S S\5      rg)    )AnySequence)BaseDocumentTransformerDocumentc                   v    \ rS rSrSrSS\S\SS4S jjrS\\   S	\	S\\   4S
 jr
S\\   S	\	S\\   4S jrSrg)Html2TextTransformer   a  Replace occurrences of a particular search pattern with a replacement string

Arguments:
    ignore_links: Whether links should be ignored; defaults to True.
    ignore_images: Whether images should be ignored; defaults to True.

Example:
    .. code-block:: python
        from langchain_community.document_transformers import Html2TextTransformer
        html2text = Html2TextTransformer()
        docs_transform = html2text.transform_documents(docs)
ignore_linksignore_imagesreturnNc                     Xl         X l        g N)r
   r   )selfr
   r   s      k/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/document_transformers/html2text.py__init__Html2TextTransformer.__init__   s    (*    	documentskwargsc                 <    SS K nUR                  5       nU R                  Ul        U R                  Ul        / nU HC  n[        UR                  UR                  5      0 UR                  ES9nUR                  U5        ME     U$ ! [         a    [        S5      ef = f)Nr   z\html2text package not found, please 
                install it with `pip install html2text`)page_contentmetadata)
	html2textImportError	HTML2Textr
   r   r   handler   r   append)r   r   r   r   hnew_documentsdnew_documents           r   transform_documents(Html2TextTransformer.transform_documents   s    
	 !**,,A#XXann51::L   .	 
 %  	; 	s   B Bc                    #    [         e7fr   )NotImplementedError)r   r   r   s      r   atransform_documents)Html2TextTransformer.atransform_documents3   s     
 "!s   	)r   r
   )TT)__name__
__module____qualname____firstlineno____doc__boolr   r   r   r   r"   r&   __static_attributes__ r   r   r   r      sx    +T + +QU +H%  
(		6"H%" " 
(		"r   r   N)typingr   r   langchain_core.documentsr   r   r   r/   r   r   <module>r2      s      F2"2 2"r   