libere-tes-chaine-de-mots/import_data/11_importation_facebook_page_publications.py

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[ ]:

#%% 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', 'FacebookBusiness', 'posts', 'profile_posts_1.json')]

try:
    with open(fb_data_path[0], "r", encoding="raw-unicode-escape") as posts:
        posts_json = json.loads(convert_encoding_meta(posts.read()))
except Exception as e:
    print(f"Error reading JSON file: {e}")
    exit(1)

#%% In[ ]:
posts_medias = []
for post in posts_json:
    # data
    data_post_items = post['data']
    texte_post_list = []
    for item in data_post_items:
        if item.get('post'):
            texte_post_list.append(item['post'])
    texte = "\n".join(texte_post_list)
    # attachments
    for attachment in post['attachments']:
        if attachment.get('data'):
            for data_item in attachment['data']:
                if data_item.get('media'):
                    media = data_item['media']
                    if len(texte) > 1:
                        posts_medias.append({"network": "FacebookBusiness",
                                             "type": "posts",
                                             "index": "rs_facebookbusiness_posts",
                                             "chemin": fb_data_path[0],
                                             "texte": texte,
                                             "creation_timestamp": media["creation_timestamp"]})

#%% In[ ]:
posts_medias_df = pd.DataFrame(posts_medias)

#%% In[ ]:
posts_medias_df.fillna(value="", inplace=True)

#%% In[ ]:
posts_medias_df.drop_duplicates(subset=['texte', 'creation_timestamp'], inplace=True)

#%% In[ ]:
documents_to_database(posts_medias_df)