extract_pdf.py

from pypdf import PdfReader

reader = PdfReader("1-s2.0-S2405844024055324-main.pdf")
text = ""
for page in reader.pages:
    text += page.extract_text() + "\n"

# Limit output to avoid token limit issues, or save to file and read chunks. 
# I'll save to a text file.
with open("paper_content.txt", "w", encoding="utf-8") as f:
    f.write(text)

print("PDF content extracted to paper_content.txt")