Created
December 19, 2017 20:41
-
-
Save pochemuto/19f4e37bde520b39cd816e4015c47deb to your computer and use it in GitHub Desktop.
Checks that scraper database contains rom hashes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import csv | |
import hashlib | |
import sys | |
import os | |
HASH_DATA_FILE = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'scraper/hash.csv') | |
def load(): | |
result = {} | |
with open(HASH_DATA_FILE) as hash_data: | |
reader = csv.reader(hash_data) | |
for row in reader: | |
result[row[0]] = row[3] | |
return result | |
def sha(filepath): | |
sha_func = hashlib.sha1() | |
with open(filepath, 'rb') as input_file: | |
bytes = input_file.read() | |
sha_func.update(bytes) | |
return sha_func.hexdigest() | |
if __name__ == '__main__': | |
if len(sys.argv) == 1: | |
print("Too few arguments") | |
exit(1) | |
files = sys.argv[1:] | |
if len(sys.argv) == 2 and os.path.isdir(sys.argv[1]): | |
files = os.listdir(sys.argv[1]) | |
hashes = load() | |
for filename in files: | |
if not os.path.isfile(filename): | |
print('skipped ' + filename) | |
continue | |
shasum = sha(filename) | |
found = shasum in hashes | |
if found: | |
print('OK ' + filename + ' ~~~ ' + hashes[shasum]) | |
else: | |
print('MISSED ' + filename) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment