get_data.py

'''
File: get_data.py
Project: PatternsRecognizer
Author: Milko Videv (milko.videv@thalesgroup.com)
-----
Last Modified: Friday, 1st March 2024 6:04:04 pm
Modified By: Milko Videv (milko.videv@thalesgroup.com>)
-----
Copyright 2017 - 2024, Thales DIS, MCS SSH
-----
HISTORY:
Date      	By	Comments
----------	---	---------------------------------------------------------
'''

from random import random
from fastdownload import download_url
from fastai.vision.all import *
from time import sleep
from fastbook import search_images_ddg
from fastcore.all import *

def search_images_fastbook(term, max_images=30):
    print(f"Searching for {max_images} {term}")
    return search_images_ddg(term, max_images=max_images)

def get_images(target_path, count, searches):
    path = Path(target_path)    

    for o in searches:
        dest = (path/o)
        dest.mkdir(exist_ok=True, parents=True)
        download_images(dest, urls=search_images_fastbook(f'{o} patterns images', max_images=count))
        sleep(10)
        resize_images(path/o, max_size=400, dest=path/o)

    print(f"Checking for bad images ...")
    failed = verify_images(get_image_files(path))
    failed.map(Path.unlink)
    print(f"Removed {len(failed)} bad images")

if __name__ == "__main__":
    if len(sys.argv) < 3 or not sys.argv[2].isdigit():
        print("Use: python get_data.py <target path> <images count> <one or more pattern kinds>\n")
        print("Example: python get_data.py patterns 1 bulgarian indian japanese")
    else:        
        target_path = sys.argv[1]
        count = sys.argv[2]
        searches = sys.argv[3:] if len(sys.argv) > 3 else "bulgarian"

        if len(searches) == 0:
            print(f"Nothing to search for. Exitting.")
            sys.exit()

        #print(target_path, int(count), searches)
        get_images(target_path, int(count), searches)