From 7867014d0b665c25c9432cdd248d4b15d0d396b9 Mon Sep 17 00:00:00 2001 From: lucas-morin Date: Thu, 5 Dec 2024 13:20:00 +0100 Subject: [PATCH] Create a XML backend for PubMed documents based on the pubmed_parser library --- docling/backend/xml_backend.py | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/docling/backend/xml_backend.py b/docling/backend/xml_backend.py index ff01eed3..73b5ca0c 100755 --- a/docling/backend/xml_backend.py +++ b/docling/backend/xml_backend.py @@ -1,12 +1,10 @@ -import hashlib import logging from io import BytesIO from pathlib import Path -from pprint import pprint -from typing import Final, Set, Union - +from typing import Set, Union import pubmed_parser # type: ignore from bs4 import BeautifulSoup + from docling_core.types.doc import ( DocItemLabel, DoclingDocument,