Better PDF extraction

2024-07-10 16:20:40 -06:00 · 2024-07-10 16:20:40 -06:00 · 2aa39e86d7
commit 2aa39e86d7
parent 840a3030f7
1 changed files with 1 additions and 1 deletions
--- a/src/window.py
+++ b/src/window.py
@ -1347,7 +1347,7 @@ Generate a title following these rules:
            if len(reader.pages) == 0: return None
            text = ""
            for i, page in enumerate(reader.pages):
-                text += f"\n- Page {i}\n{page.extract_text()}\n"
+                text += f"\n- Page {i}\n{page.extract_text(extraction_mode='layout', layout_mode_space_vertically=False)}\n"
            return text

    def remove_attached_file(self, name):