file name is extract_pdf_metadata.py
import PyPDF2
import sys
def extract_academic_metadata(pdf_file):
try:
pdf = PyPDF2.PdfReader(open(pdf_file, 'rb'))
metadata = pdf.metadata
# for key, value in metadata.items():
# print(f'{key}: {value}')
publisher_name = metadata.get('/Subject', 'N/A')
# You can add more custom metadata fields as needed
print(f'Journal: {publisher_name}')
except Exception as e:
print(f'Error: {e}')
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: python extract_metadata.py <pdf_file>")
else:
pdf_file = sys.argv[1]
extract_academic_metadata(pdf_file)