EPubs

This covers how to load .epub documents into a document format that we can use downstream. You'll need to install the pandocs package for this loader to work.

In [1]:

from langchain.document_loaders import UnstructuredEPubLoader

In [2]:

loader = UnstructuredEPubLoader("winter-sports.epub")

In [3]:

data = loader.load()

Retain Elements

Under the hood, Unstructured creates different "elements" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying mode="elements".

In [4]:

loader = UnstructuredEPubLoader("winter-sports.epub", mode="elements")

In [5]:

data = loader.load()

In [6]:

data[0]

Out [6]:

Document(page_content='The Project Gutenberg eBook of Winter Sports in\nSwitzerland, by E. F. Benson', lookup_str='', metadata={'source': 'winter-sports.epub', 'page_number': 1, 'category': 'Title'}, lookup_index=0)

In [ ]:

2.7 KiB Raw Blame History

EPubs

Retain Elements

2.7 KiB

Raw Blame History