diff --git a/deepdoc/parser/pdf_parser.py b/deepdoc/parser/pdf_parser.py index 6c3324544dd1f2e552cbbfb1a7c43b402f427adc..c9a200374ddfa3c27d501c0a7d2a5c3e251543a7 100644 --- a/deepdoc/parser/pdf_parser.py +++ b/deepdoc/parser/pdf_parser.py @@ -830,6 +830,7 @@ class HuParser: pn = [bx["page_number"]] top = bx["top"] - self.page_cum_height[pn[0] - 1] bott = bx["bottom"] - self.page_cum_height[pn[0] - 1] + if pn[-1] - 1 >= len(self.page_images): return "" while bott * ZM > self.page_images[pn[-1] - 1].size[1]: bott -= self.page_images[pn[-1] - 1].size[1] / ZM pn.append(pn[-1] + 1)