langchain_community.document_transformers.html2text
.Html2TextTransformer¶
- class langchain_community.document_transformers.html2text.Html2TextTransformer(ignore_links: bool = True, ignore_images: bool = True)[source]¶
Replace occurrences of a particular search pattern with a replacement string
- Parameters
ignore_links (bool) – Whether links should be ignored; defaults to True.
ignore_images (bool) – Whether images should be ignored; defaults to True.
Example
Methods
__init__
([ignore_links, ignore_images])atransform_documents
(documents, **kwargs)Asynchronously transform a list of documents.
transform_documents
(documents, **kwargs)Transform a list of documents.
- __init__(ignore_links: bool = True, ignore_images: bool = True) None [source]¶
- Parameters
ignore_links (bool) –
ignore_images (bool) –
- Return type
None
- async atransform_documents(documents: Sequence[Document], **kwargs: Any) Sequence[Document] [source]¶
Asynchronously transform a list of documents.