PyPDFParser#
- class langchain_community.document_loaders.parsers.pdf.PyPDFParser(password: str | bytes | None = None, extract_images: bool = False, *, extraction_mode: str = 'plain', extraction_kwargs: Dict[str, Any] | None = None)[来源]#
使用pypdf加载PDF
方法
__init__([password, extract_images, ...])lazy_parse(blob)懒解析 blob。
parse(blob)急切地将blob解析为一个或多个文档。
- Parameters:
password (可选[联合[str, bytes]])
extract_images (bool)
extraction_mode (str)
extraction_kwargs (可选[字典[字符串, 任意类型]])
- __init__(password: str | bytes | None = None, extract_images: bool = False, *, extraction_mode: str = 'plain', extraction_kwargs: Dict[str, Any] | None = None)[source]#
- Parameters:
password (str | bytes | None)
extract_images (bool)
extraction_mode (str)
extraction_kwargs (Dict[str, Any] | None)