def main():
parser = argparse.ArgumentParser(
description='Function to extract metadata and split a PDF containing multiple journal articles. Set up for '
'Buffalo Law Review book reviews.'
)
parser.add_argument('filename',
help='PDF file to analyze and split.',
type=str,
)
parser.add_argument('-v', '--verbose',
action='store_true',
dest='verbose',
help='Print status messages.',
)
parser.add_argument('-t', '--test',
action='store_true',
help="Test only. Don't output any files. Use with debug options to see test output.",
)
parser.add_argument('--write-csv-only',
action="store_true",
dest="csvOnly",
help="Write CSV file, but don't split PDFs. Test flag takes precedence.",
)
parser.add_argument('-d', '--debug',
dest='debug',
type=int,
help="Set debug level (1-6). Levels 1-4 offer increasing levels of output. Level 5 displays "
"the PDF text. Level 6 prints all of the records.",
default=0,
)
parser.add_argument('-o', '--output-file',
dest='destination',
type=str,
help='Use supplied filename as filename template for output files.',
)
parser.add_argument('-i', '--input-file',
dest='input_file',
type=str,
help="Import CSV file to be used for PDF splitting. Must be in same format as export.")
args = parser.parse_args()
# Split filename from extension before passing to the various functions. Use input filename for template
# if no output filename specified.
if args.destination:
output_file, output_extension = os.path.splitext(args.destination)
else:
output_file, output_extension = os.path.splitext(args.filename)
# If importCSV is specified, read that file and get start_pdf_page and end_pdf_page to pass to SplitPDFs
# If no importCSV is selected, process args.filename
if args.input_file:
start_pdf_page, end_pdf_page = journaltools.importcsv(args.input_file, args.debug)
else:
# Fetch OCR page text from PDF file
page_text = journaltools.getpdf(args.filename, 0, args.verbose, args.debug)
# Process pages
title, start_page, start_pdf_page, end_pdf_page, author = processpdfnew(
args.verbose, args.debug, page_text)
# Export CSV file, or show what output would be if test flag is set
journaltools.exportcsvnew(output_file, args.verbose, args.debug, args.test, title, start_page, start_pdf_page,
end_pdf_page, author)
# Split Original PDF into separate documents for each piece, unless test or csvOnly flags are set
if not args.test and not args.csvOnly:
journaltools.splitpdf(args.filename, args.verbose, args.debug, start_pdf_page, end_pdf_page, output_file)
)
parser.add_argument('-i', '--input-file',
dest='input_file',
type=str,
help="Import CSV file to be used for PDF splitting. Must be in same format as export. "
"Default is filename with .csv extension.")
args = parser.parse_args()
# Split filename from extension before passing to the various functions. Use input filename for template
# if no output filename specified.
if args.destination:
output_file, output_extension = os.path.splitext(args.destination)
else:
output_file, output_extension = os.path.splitext(args.filename)
# Set input CSV filename. If no filename provided, use the input filename with CSV extension.
if args.input_file:
input_file = args.input_file
else:
input_file, input_extension = os.path.splitext(args.filename)
input_file = input_file + '.csv'
# Read CSVfile and get starting and ending PDF pages to pass to splitpdf
if os.path.exists(input_file):
start_pdf_page, end_pdf_page = journaltools.importcsv(input_file, args.debug)
# Split Original PDF into separate documents for each piece, unless test flag is set
if not args.test:
journaltools.splitpdf(args.filename, args.verbose, args.debug, start_pdf_page, end_pdf_page, output_file)
else:
print(f'{input_file} not present. Please specify a valid CSV file to use for the split points.')