langchain_community.document_loaders.parsers.pdf
.PyPDFParser¶
- class langchain_workspace.document_loaders.parsers.pdf.PyPDFParser(password: Optional[Union[str, bytes]] = None, extract_images: bool = False, *, extraction_mode: str = 'plain', extraction_kwargs: Optional[Dict[str, Any]] = None)[source]¶
使用 pypdf 加载 PDF
方法
__init__
([password, extract_images, ...])lazy_parse
(blob)懒加载解析blob。
parse
(blob)贪婪地将blob解析为文档或文档。
- 参数
password (Optional[Union[str, bytes]]) –
extract_images (bool) –
extraction_mode (str) –
extraction_kwargs (Optional[Dict[str, Any]]) –
- __init__(password: Optional[Union[str, bytes]] = None, extract_images: bool = False, *, extraction_mode: str = 'plain', extraction_kwargs: Optional[Dict[str, Any]] = None)[source]¶
- 参数
password (Optional[Union[str, bytes]]) –
extract_images (bool) –
extraction_mode (str) –
extraction_kwargs (Optional[Dict[str, Any]]) –