marker-io / convert_single.py
Ritvik19's picture
Add all files and directories
c8a32e7
raw
history blame
No virus
1.25 kB
import argparse
import os
from marker.convert import convert_single_pdf
from marker.logger import configure_logging
from marker.models import load_all_models
from marker.output import save_markdown
configure_logging()
def main():
parser = argparse.ArgumentParser()
parser.add_argument("filename", help="PDF file to parse")
parser.add_argument("output", help="Output base folder path")
parser.add_argument("--max_pages", type=int, default=None, help="Maximum number of pages to parse")
parser.add_argument("--langs", type=str, help="Languages to use for OCR, comma separated", default=None)
parser.add_argument("--batch_multiplier", type=int, default=2, help="How much to increase batch sizes")
args = parser.parse_args()
langs = args.langs.split(",") if args.langs else None
fname = args.filename
model_lst = load_all_models()
full_text, images, out_meta = convert_single_pdf(fname, model_lst, max_pages=args.max_pages, langs=langs, batch_multiplier=args.batch_multiplier)
fname = os.path.basename(fname)
subfolder_path = save_markdown(args.output, fname, full_text, images, out_meta)
print(f"Saved markdown to the {subfolder_path} folder")
if __name__ == "__main__":
main()