extend text to <back> part of the document to capture funding, data a…

…vailability and other information
lfoppiano · Apr 3, 2024 · 6f06e96 · 6f06e96
1 parent 168d47b
commit 6f06e96
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/document_qa/grobid_processors.py b/document_qa/grobid_processors.py
@@ -815,6 +815,8 @@ def get_xml_nodes_body(soup: object, use_paragraphs: bool = True, verbose: bool
             # nodes.extend([subchild.find_all(tag_name) for subchild in child.find_all("body")])
             nodes.extend(
                 [subsubchild for subchild in child.find_all("body") for subsubchild in subchild.find_all(tag_name)])
+            nodes.extend(
+                [subsubchild for subchild in child.find_all("back") for subsubchild in subchild.find_all(tag_name)])
 
     if verbose:
         print(str(nodes))