mirror of https://github.com/hwchase17/langchain
gutenberg books (#946)
Co-authored-by: zanderchase <zander@unfold.ag> Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>pull/949/head
parent
6a4f602156
commit
3e1901e1aa
@ -0,0 +1,83 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bda1f3f5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Gutenberg\n",
|
||||
"\n",
|
||||
"This covers how to load links to Gutenberg e-books into a document format that we can use downstream."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "9bfd5e46",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import GutenbergLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "700e4ef2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = GutenbergLoader('https://www.gutenberg.org/cache/epub/69972/pg69972.txt')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "b6f28930",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "7d436441",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "3b74d755",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -0,0 +1,28 @@
|
||||
"""Loader that loads .txt web files."""
|
||||
from typing import List
|
||||
|
||||
from langchain.docstore.document import Document
|
||||
from langchain.document_loaders.base import BaseLoader
|
||||
|
||||
|
||||
class GutenbergLoader(BaseLoader):
|
||||
"""Loader that uses urllib to load .txt web files."""
|
||||
|
||||
def __init__(self, file_path: str):
|
||||
"""Initialize with file path."""
|
||||
if not file_path.startswith("https://www.gutenberg.org"):
|
||||
raise ValueError("file path must start with 'https://www.gutenberg.org'")
|
||||
|
||||
if not file_path.endswith(".txt"):
|
||||
raise ValueError("file path must end with '.txt'")
|
||||
|
||||
self.file_path = file_path
|
||||
|
||||
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)]
|
Loading…
Reference in New Issue