Files
langchain-python/langchain
Matt Robinson 3dfe1cf60e feat: document loader for epublications (#2202)
### Summary

Adds a new document loader for processing e-publications. Works with
`unstructured>=0.5.4`. You need to have
[`pandoc`](https://pandoc.org/installing.html) installed for this loader
to work.

### Testing

```python
from langchain.document_loaders import UnstructuredEPubLoader

loader = UnstructuredEPubLoader("winter-sports.epub", mode="elements")
data = loader.load()
data[0]
```
2023-03-30 20:45:31 -07:00
..
2023-03-29 22:55:21 -07:00
2023-03-22 23:15:04 -07:00
2023-03-29 16:17:54 -04:00
2023-03-14 12:37:48 -07:00
2023-03-14 20:00:22 -07:00
2023-03-30 07:34:13 -07:00
2023-03-16 21:58:06 -07:00
2022-10-24 14:51:15 -07:00
2022-11-12 11:22:32 -08:00
2023-03-30 20:41:56 -07:00
2023-03-30 10:14:05 -04:00
2023-02-20 21:15:45 -08:00
2023-03-29 22:29:38 -07:00
2023-01-19 14:48:30 -08:00