langchain/docs/modules/document_loaders/examples/html.ipynb

HTML

This covers how to load HTML documents into a document format that we can use downstream.

In [1]:

from langchain.document_loaders import UnstructuredHTMLLoader

In [2]:

loader = UnstructuredHTMLLoader("example_data/fake-content.html")

In [3]:

data = loader.load()

In [4]:

data

Out [4]:

[Document(page_content='My First Heading\n\nMy first paragraph.', lookup_str='', metadata={'source': 'example_data/fake-content.html'}, lookup_index=0)]

In [ ]: