sss

app.py

@@ -1,5 +1,5 @@
 import streamlit as st
-import PyPDF2
+import pdfplumber
 import io
 import spacy
 from docx import Document
@@ -41,10 +41,10 @@ job_descriptions = {
 }
 
 def extract_text_from_pdf(pdf_file):
-    pdf_reader = PyPDF2.PdfReader(pdf_file)
     text = ""
-    for page in pdf_reader.pages:
-        text += page.extract_text()
+    with pdfplumber.open(pdf_file) as pdf:
+        for page in pdf.pages:
+            text += page.extract_text() or ""
     return text
 
 def extract_text_from_docx(docx_file):

requirements.txt

@@ -1,5 +1,5 @@
 streamlit>=1.31.0
-PyPDF2>=3.0.1
+pdfplumber>=0.10.3
 python-docx>=1.1.0
 transformers>=4.37.2
 spacy>=3.7.2