Source code for langchain_community.document_loaders.gutenberg

from typing import List

from langchain_core.documents import Document

from langchain_community.document_loaders.base import BaseLoader

[docs]class GutenbergLoader(BaseLoader): """Load from ``."""
[docs] def __init__(self, file_path: str): """Initialize with a file path.""" if not file_path.startswith(""): raise ValueError("file path must start with ''") if not file_path.endswith(".txt"): raise ValueError("file path must end with '.txt'") self.file_path = file_path
[docs] def load(self) -> List[Document]: """Load file.""" from urllib.request import urlopen elements = urlopen(self.file_path) text = "\n\n".join([str(el.decode("utf-8-sig")) for el in elements]) metadata = {"source": self.file_path} return [Document(page_content=text, metadata=metadata)]