refine table parser (#120)

2025-12-08 20:42:30 +08:00 · 2024-03-12 18:56:04 +08:00
parent f1f09df901
commit 0feb085c88
6 changed files with 20 additions and 15 deletions
--- a/deepdoc/parser/ppt_parser.py
+++ b/deepdoc/parser/ppt_parser.py
@ -42,7 +42,9 @@ class HuPptParser(object):
            BytesIO(fnm))
        txts = []
        self.total_page = len(ppt.slides)
-        for i, slide in enumerate(ppt.slides[from_page: to_page]):
+        for i, slide in enumerate(ppt.slides):
+            if i < from_page: continue
+            if i >= to_page:break
            texts = []
            for shape in slide.shapes:
                txt = self.__extract(shape)