Last active
September 14, 2023 10:06
-
-
Save deltronzero/7c23bacf97b4b61c7a2f2950ef6f35d8 to your computer and use it in GitHub Desktop.
split one large bloodhound file into multiple smaller files to work around memory limitations
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
import json | |
file_name = "20210312152708_computers.json" | |
type = "computers" | |
object_limit = 10000 | |
print(f"[*] loading {file_name}") | |
data = json.loads(open(file_name,'r').read().encode().decode('utf-8-sig')) | |
total_objects = data['meta']['count'] | |
object_count = 0 | |
file_count = 0 | |
while object_count < total_objects: | |
a = {} | |
a[type] = data[type][object_count:][:object_limit] | |
object_count += len(a[type]) | |
a['meta'] = data['meta'] | |
a['meta']['count'] = object_count | |
f_split = file_name.split(".") | |
file_name_out = f"{f_split[0]}_{file_count}.{f_split[1]}" | |
print(f"[*] writing {file_name_out} - {object_count} of {total_objects}") | |
f_out = open(file_name_out, "w") | |
json.dump(a, f_out) | |
f_out.close() | |
file_count += 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment