古腾堡
Project Gutenberg 是一个免费电子书在线库。
此笔记本介绍如何将链接加载到Gutenberg电子书转换为我们可以在下游使用的文档格式。
from langchain_community.document_loaders import GutenbergLoader
API 参考：GutenbergLoader
loader = GutenbergLoader("https://www.gutenberg.org/cache/epub/69972/pg69972.txt")
data = loader.load()
data[0].page_content[:300]
'The Project Gutenberg eBook of The changed brides, by Emma Dorothy\r\n\n\nEliza Nevitte Southworth\r\n\n\n\r\n\n\nThis eBook is for the use of anyone anywhere in the United States and\r\n\n\nmost other parts of the world at no cost and with almost no restrictions\r\n\n\nwhatsoever. You may copy it, give it away or re-u'
data[0].metadata
{'source': 'https://www.gutenberg.org/cache/epub/69972/pg69972.txt'}