import pandas as pd import json import os from pathlib import Path from utils.documents_to_database import documents_to_database from utils.convert_encoding_meta import convert_encoding_meta #%% In[ ]: # Get the current file's directory try: # This will work when running as a script script_dir = Path(__file__).parent.parent except NameError: # This will work in interactive environments script_dir = Path().absolute() project_root = script_dir fb_data_path = [os.path.join(project_root, 'import_data', 'data', 'Facebook', 'comments_and_reactions', 'comments.json')] with open(fb_data_path[0], "r", encoding="raw-unicode-escape") as posts: comments_json = json.loads(convert_encoding_meta(posts.read())) #%% In[ ]: facebook_comments = [] for comment in comments_json['comments_v2']: if comment.get('data'): for data_item in comment['data']: if data_item.get('comment'): comment = data_item['comment'] facebook_comments.append({"network": "Facebook", "type": "comments", "index": "rs_facebook_comments_and_reactions", "chemin": fb_data_path[0], "texte": comment["comment"], "creation_timestamp": comment["timestamp"]}) #%% In[ ]: facebook_comments_df = pd.DataFrame(facebook_comments) #%% In[ ]: documents_to_database(facebook_comments_df)