Search rtf files in a directory. (At the time requires python2 (due to pyth))

search_rtf_in_directory.py

import argparse
import os

from pyth.plugins.rtf15.reader import Rtf15Reader
from pyth.plugins.plaintext.writer import PlaintextWriter


def get_text(filename):
    with open(filename) as f:
        doc = Rtf15Reader.read(f)
    return PlaintextWriter.write(doc).getvalue()


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('search_term')
    parser.add_argument('directory')
    args = parser.parse_args()

    term = args.search_term.lower()

    for root, _, filenames in os.walk(args.directory):
        for filename in filenames:
            if not filename.lower().endswith('.rtf') or filename.startswith('~'):
                continue

            try:
                text = get_text(os.path.join(root, filename))
            except ValueError:
                print('Could not parse {}'.format(filename))

            if term in text.lower():
                print(filename)

 
if __name__ == '__main__':
    exit(main())