Created
May 1, 2017 04:25
-
-
Save twobob/dad0a110b0c2b2eb4895d8e6e5e76760 to your computer and use it in GitHub Desktop.
Create a JSON file from a list of txt files parsing the values
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
# -*- coding: utf-8 -*- | |
''' | |
where .JPG.txt AI tag files are like | |
Tags for IMG_3150.JPG (Tag - Probability) | |
child - 0.9972 | |
fun - 0.9727 | |
little - 0.9688 | |
people - 0.9647 | |
cute - 0.9637 | |
et cetera | |
''' | |
import os, sys | |
import glob | |
import simplejson as json | |
from os.path import expanduser | |
directory = expanduser('~\\pictures\\clarifai\\') | |
JSONdirectory = expanduser('~\\pictures\\clarifai\\JSON\\') | |
thumbsdirectory = expanduser('~\\pictures\\clarifai\\thumbs\\') | |
lines_list = [] | |
data={} | |
finaldata=[] | |
emptyHolder = {} | |
txts=glob.glob1(directory, "*.txt") | |
with open(JSONdirectory+"data.JSON", 'w') as outfile: | |
for txt in txts: | |
lines_list = open(directory+txt).read().splitlines()[2:] | |
data['Question']=emptyHolder | |
data['img']={'filename':txt.replace('.JPG.txt', '.JPG')} | |
data['thumb']={'filename':txt.replace('.JPG.txt', '.THUMB.JPEG')} | |
data['Question']['content']={} | |
for i in lines_list: | |
data['Question']['content'][i.split(' - ')[0]]=i.split(' - ')[1] | |
finaldata.append(data) | |
json.dump({'Questions':finaldata}, outfile, sort_keys = True, indent = 4, ensure_ascii = False) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment