pypdf2 to pypdf (#1684)

### What problem does this PR solve?

pypdf and PyPDF2 possible Infinite Loop when a comment isn't followed by
a character #59

### Type of change

- [x] Refactoring

deepdoc/parser/pdf_parser.py

@@ -23,7 +23,7 @@ import logging
 from PIL import Image, ImageDraw
 import numpy as np
 from timeit import default_timer as timer
-from PyPDF2 import PdfReader as pdf2_read
+from pypdf import PdfReader as pdf2_read
 
 from api.utils.file_utils import get_project_base_directory
 from deepdoc.vision import OCR, Recognizer, LayoutRecognizer, TableStructureRecognizer

requirements.txt

@@ -79,3 +79,4 @@ word2number==1.1
 xgboost==2.1.0
 xpinyin==0.7.6
 zhipuai==2.0.1
+pypdf==4.3.0

requirements_arm.txt

@@ -153,3 +153,4 @@ groq==0.9.0
 wikipedia==1.4.0
 Bio==1.7.1
 arxiv==2.1.3
+pypdf==4.3.0

requirements_dev.txt

@@ -138,3 +138,4 @@ groq==0.9.0
 wikipedia==1.4.0
 Bio==1.7.1
 arxiv==2.1.3
+pypdf==4.3.0