Created
March 19, 2016 18:08
-
-
Save nloadholtes/e2e8870dfd96087dad1d to your computer and use it in GitHub Desktop.
An example of using ijson to process streaming JSON in a memory constrained way
This file contains hidden or 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
# | |
# This is the core of my handler function | |
# | |
batch_size = 100 # This needs to change based on the size of your objects | |
parser = ijson.parse(f) | |
counter = 0 | |
to_process = [] | |
for prefix, event, value in parser: | |
if (prefix, event) == ("item", "start_map"): | |
music_item = dict(albums=[]) | |
elif (prefix, event) == ("item.album", "start_array"): | |
album = dict() | |
elif (prefix, event) == ("item.album.item", "start_map"): | |
album = dict() | |
elif (prefix, event) == ("item.album.item", "end_map"): | |
album["id"] = program["album_id"] | |
music_item["album"].append(album) | |
elif (prefix, event) == ("item.album.item.title", "string"): | |
album["title"] = value | |
elif (prefix, event) == ("item", "end_map"): | |
to_process.append(music_item) | |
counter += 1 | |
if counter > batch_size: | |
write_to_mongo(to_process) | |
counter = 0 | |
to_process = [] | |
if to_process: | |
write_to_mongo(to_process) | |
# | |
# and we're done! | |
# |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment