Last active
October 16, 2022 05:49
-
-
Save gpirrotta/707f02bbe7e36e8e7238071a039fb43e to your computer and use it in GitHub Desktop.
Git Diff Visualcad
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 | |
import csv | |
f = open('../data/data_cad.json') | |
rows = json.load(f) | |
previous_article = {} | |
with open('../data/gitdiff.csv', mode='w') as csv_file: | |
fieldnames = ['data', 'articolo', 'type','no','size_article'] | |
writer = csv.DictWriter(csv_file, fieldnames=fieldnames) | |
writer.writeheader() | |
for row in rows: | |
source = row['source'] | |
for article in row['articles']: | |
status = '' | |
id = article['id'] | |
content = article['paragraphs'][0]['content'] | |
size = article['paragraphs'][0]['content_length'] | |
if id not in previous_article: | |
previous_article[id] = content | |
if 'status' in article: | |
status = article['status'] | |
elif previous_article[id] != content: | |
status = 'updated' #Updated article | |
previous_article[id] = content | |
elif previous_article[id] == content: | |
status = 'same' #Same article - no updated | |
if source =='2005-03-07': | |
status='same' | |
writer.writerow({'data': source, 'articolo': id, 'type': status, 'no': article['no'],'size_article': size}) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment