diff --git a/data_chain/parser/handler/pdf_parser.py b/data_chain/parser/handler/pdf_parser.py index 70d1fbd833e9a9e1017dc0c8db1cd3cb0e56925c..f1552652c22f1e0dbe16890664d45bf38bf4a936 100644 --- a/data_chain/parser/handler/pdf_parser.py +++ b/data_chain/parser/handler/pdf_parser.py @@ -74,11 +74,11 @@ class PdfService(BaseService): table_df = table.to_pandas() table_lines = self.split_table(table_df) for line in table_lines: - table_data.extend([{ + table_data.append({ "text": line, "bbox": table_bbox, "type": "table", - } for line in table_lines]) + }) page.apply_redactions()