From 36fbaa946e171c403d32346b74e445c2858bc257 Mon Sep 17 00:00:00 2001 From: Blade He Date: Tue, 3 Dec 2024 11:50:31 -0600 Subject: [PATCH] Add the statement when transferring the last fund name of previous PDF page: The last fund name of previous PDF page: page_text = f"\nThe last fund name of previous PDF page: {previous_page_fund_name}\n{page_text}" --- core/data_extraction.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/core/data_extraction.py b/core/data_extraction.py index dfaefd3..18309b4 100644 --- a/core/data_extraction.py +++ b/core/data_extraction.py @@ -183,7 +183,7 @@ class DataExtraction: # The purpose is to get fund name if the first records without fund name # example document: 431073795, page index 1727 to 1728 logger.info(f"Transfer previous page fund name: {previous_page_fund_name} to be the pre-fix of page text") - page_text = f"\n{previous_page_fund_name}\n{page_text}" + page_text = f"\nThe last fund name of previous PDF page: {previous_page_fund_name}\n{page_text}" extract_data = self.extract_data_by_page( page_num,