Facebook Business Page JSON parser for posts

[+Warwagon MVC]

Recently downloaded all my posts off Facebook. I did the HMTL first which worked, but it was just a single HTML file which was a single page with all my posts. Then I downloaded the file in JSON format. I wanted to save the text of each individual post as their own file.

So with the help of ChatGPT, I had it code me this app. Which opens the Posts JSON file. and lists them all on the left. When you click it, it shows you the post text on the right. You can search at the top of keywords.

You can also export Individually checked posts or everything, each in their own TXT file to a directory of your choosing.

Not sure if anyone else will find it useful.

 

You can also sort by name

 

 

import sys
import json
from PyQt5.QtWidgets import QApplication, QMainWindow, QWidget, QListWidget, QTextBrowser, QVBoxLayout, QPushButton, QFileDialog, QSplitter, QLineEdit, QListWidgetItem
from PyQt5.QtGui import QFont
from PyQt5.QtCore import Qt, QSettings
import os
import re

class FacebookProfileViewer(QMainWindow):
    def __init__(self):
        super().__init__(None)
        self.setWindowTitle("Facebook Profile Viewer")
        self.setGeometry(100, 100, 800, 600)

        self.central_widget = QSplitter()
        self.setCentralWidget(self.central_widget)

        self.post_list = QListWidget()
        self.post_list.itemClicked.connect(self.display_post)

        self.post_text_browser = QTextBrowser()

        self.load_button = QPushButton("Load JSON File")
        self.load_button.clicked.connect(self.load_data)

        self.sort_button = QPushButton("Sort by Name")
        self.sort_button.clicked.connect(self.sort_by_name)

        self.search_box = QLineEdit()
        self.search_box.textChanged.connect(self.filter_articles)

        self.select_all_button = QPushButton("Select All")
        self.select_all_button.clicked.connect(self.select_all)

        self.deselect_all_button = QPushButton("Deselect All")
        self.deselect_all_button.clicked.connect(self.deselect_all)

        self.save_button = QPushButton("Save Selected")
        self.save_button.clicked.connect(self.save_selected)

        self.save_all_button = QPushButton("Save All")
        self.save_all_button.clicked.connect(self.save_all)

        self.left_widget = QWidget()
        left_layout = QVBoxLayout()
        left_layout.addWidget(self.load_button)
        left_layout.addWidget(self.sort_button)
        left_layout.addWidget(self.search_box)
        left_layout.addWidget(self.select_all_button)
        left_layout.addWidget(self.deselect_all_button)
        left_layout.addWidget(self.save_button)
        left_layout.addWidget(self.save_all_button)
        left_layout.addWidget(self.post_list)
        self.left_widget.setLayout(left_layout)

        self.central_widget.addWidget(self.left_widget)
        self.central_widget.addWidget(self.post_text_browser)

        self.data = []
        self.post_data_dict = {}
        self.filtered_articles = []

        # Initialize QSettings for storing last save location
        self.settings = QSettings("MyCompany", "MyApp")

    def load_data(self):
        options = QFileDialog.Options()
        options |= QFileDialog.ReadOnly
        last_opened_folder = self.settings.value("last_opened_folder", os.path.expanduser("~"))
        file_dialog = QFileDialog.getOpenFileName(self, "Open JSON File", last_opened_folder, "JSON Files (*.json);;All Files (*)", options=options)
        if file_dialog[0]:
            json_file = file_dialog[0]
            with open(json_file, 'r', encoding='utf-8') as file:
                self.data = json.load(file)

            self.post_list.clear()
            self.post_data_dict.clear()
            seen_paragraphs = set()
            for entry in self.data:
                if "data" in entry and entry["data"]:
                    for post in entry["data"]:
                        if "post" in post:
                            post_text = post["post"]
                            post_text = post_text.replace("\u00e2\u0080\u0099", "'")
                            post_text = post_text.replace("\u00e2\u0080\u009c", '"').replace("\u00e2\u0080\u009d", '"')
                            post_paragraph = post_text.split('\n')[0]
                            if post_paragraph not in seen_paragraphs:
                                seen_paragraphs.add(post_paragraph)
                                self.post_data_dict[post_paragraph] = post_text
                                item = QListWidgetItem(post_paragraph)
                                item.setFlags(item.flags() | Qt.ItemIsUserCheckable)
                                item.setCheckState(Qt.Unchecked)
                                self.post_list.addItem(item)
            self.filtered_articles = list(self.post_data_dict.keys())

    def display_post(self, item):
        post_paragraph = item.text()
        post_text = self.post_data_dict.get(post_paragraph, "")
        self.post_text_browser.setPlainText(post_text)
        font = QFont()
        font.setPointSize(16)
        self.post_text_browser.setFont(font)

    def sort_by_name(self):
        sorted_paragraphs = sorted(self.post_data_dict.keys())
        self.post_list.clear()
        for paragraph in sorted_paragraphs:
            item = QListWidgetItem(paragraph)
            item.setFlags(item.flags() | Qt.ItemIsUserCheckable)
            item.setCheckState(Qt.Unchecked)
            self.post_list.addItem(item)

    def filter_articles(self):
        search_text = self.search_box.text()
        self.post_list.clear()
        for article in self.filtered_articles:
            if search_text.lower() in article.lower():
                item = QListWidgetItem(article)
                item.setFlags(item.flags() | Qt.ItemIsUserCheckable)
                item.setCheckState(Qt.Unchecked)
                self.post_list.addItem(item)

    def select_all(self):
        for i in range(self.post_list.count()):
            item = self.post_list.item(i)
            item.setCheckState(Qt.Checked)

    def deselect_all(self):
        for i in range(self.post_list.count()):
            item = self.post_list.item(i)
            item.setCheckState(Qt.Unchecked)

    def sanitize_filename(self, filename):
        # Remove special characters
        sanitized_name = re.sub(r'[^\w\d]+', '_', filename)
        # Limit filename length
        return sanitized_name[:50]  # You can adjust the length as needed

    def save_selected(self):
        selected_items = [self.post_list.item(i) for i in range(self.post_list.count()) if self.post_list.item(i).checkState() == Qt.Checked]
        last_save_folder = self.settings.value("last_save_folder", os.path.expanduser("~"))
        folder_path = QFileDialog.getExistingDirectory(self, "Choose Folder to Save Files", last_save_folder)
        if folder_path:
            self.settings.setValue("last_save_folder", folder_path)  # Save the last save folder
            for item in selected_items:
                post_paragraph = item.text()
                post_text = self.post_data_dict.get(post_paragraph, "")
                if post_text:
                    # Extract the first 6 words as the file name
                    words = post_paragraph.split()[:9]
                    file_name = "_".join(words)
                    file_name = self.sanitize_filename(file_name)
                    file_name = os.path.join(folder_path, file_name + ".txt")
                    with open(file_name, 'w', encoding='utf-8') as file:
                        file.write(post_text)

    def save_all(self):
        last_save_folder = self.settings.value("last_save_folder", os.path.expanduser("~"))
        folder_path = QFileDialog.getExistingDirectory(self, "Choose Folder to Save Files", last_save_folder)
        if folder_path:
            self.settings.setValue("last_save_folder", folder_path)  # Save the last save folder
            for article, text in self.post_data_dict.items():
                sanitized_filename = self.sanitize_filename(article)
                file_path = os.path.join(folder_path, sanitized_filename + ".txt")
                with open(file_path, 'w', encoding='utf-8') as file:
                    file.write(text)

if __name__ == "__main__":
    app = QApplication(sys.argv)
    viewer = FacebookProfileViewer()
    viewer.show()
    sys.exit(app.exec_())