The below Python script uses Chromium via Playwright to scrape Donald Trump's posts at Truth Social every 20 minutes, to deposit them in cells O23 and O24 of a specified GoogleSheet. If it is text, it will post the text of the post. If it is an image-only post, we will post only the image. Of course, this is just what I do; you can modify it to do whatever you like with the output. I'm also tight on space, which is why I don't do things like give a timestamp for the most-recent post.

To install dependencies, in terminal, enter:
pip install playwright gspread oauth2client
playwright install


Google stuff:
Create a service account in the Google Cloud Console.
Enable the Google Sheets API for your project.
Download the credentials.json file and place it in the same directory as your script.
Share your Google Sheet with the service account's email address.

For reference in case you run into incompatibilities, I'm running Python 3.11.3.



Python script:
from playwright.sync_api import sync_playwright
import json
import time
import gspread
from oauth2client.service_account import ServiceAccountCredentials
import re
import html

def fetch_api_data():
    api_url = "https://truthsocial.com/api/v1/accounts/107780257626128497/statuses"
    top_post_data = None

    with sync_playwright() as p:
        # Launch a browser with custom arguments for off-screen window
        browser = p.chromium.launch(
            headless=False,
            args=["--window-position=-10000,-10000"]  # Launch Chromium off-screen
        )
        context = browser.new_context()
        page = context.new_page()

        # Navigate to the main page to simulate browser behavior
        page.goto("https://truthsocial.com/@realDonaldTrump")

        # Fetch API data directly using the browser's environment
        print("Fetching API data...")
        response_text = page.evaluate(
            """
            async (apiUrl) => {
                const response = await fetch(apiUrl);
                return await response.text();  // Return raw response text for debugging
            }
            """,
            api_url,
        )

        # Parse the top-most post
        try:
            posts = json.loads(response_text)
            if posts and isinstance(posts, list):
                top_post = posts[0]  # The first post in the array

                # Check if the post is a reblog (repost)
                if top_post.get("reblog"):
                    post_content = top_post["reblog"]
                else:
                    post_content = top_post

                # Initialize variables
                title = "No title found"
                description = "No description found"

                # Extract text content
                content_html = post_content.get("content", "")
                # Remove HTML tags and unescape HTML entities
                text_content = re.sub('<[^<]+?>', '', content_html)
                text_content = html.unescape(text_content).strip()

                # Extract media attachments
                media_attachments = post_content.get("media_attachments", [])

                # Determine the type of post and set title and description accordingly
                if text_content and media_attachments:
                    # Post with both text and image
                    title = text_content
                    description = media_attachments[0].get("url", "No image URL found")
                elif text_content:
                    # Text-only post
                    title = text_content
                    description = ""  # No description for text-only post
                elif media_attachments:
                    # Image-only post
                    title = "Image Post"
                    description = media_attachments[0].get("url", "No image URL found")
                else:
                    # Neither text nor image
                    print("No text or media attachments found in the top post.")

                top_post_data = (title, description)
            else:
                print("No posts available in the response.")
        except json.JSONDecodeError as e:
            print(f"Error parsing JSON: {e}")
        except Exception as e:
            print(f"An error occurred: {e}")

        # Close the browser
        browser.close()

    return top_post_data

def append_to_google_sheet(data, starting_cell="A1"):
    try:
        # Define the scope and authenticate with the Google Sheets API
        scope = ["https://spreadsheets.google.com/feeds", "https://www.googleapis.com/auth/drive"]
        creds = ServiceAccountCredentials.from_json_keyfile_name("credentials.json", scope)
        client = gspread.authorize(creds)

        # Open the Google Sheet; replace YOURSPREADSHEETIDHERE with your google sheets spreadsheet ID
        sheet = client.open_by_url("https://docs.google.com/spreadsheets/d/YOURSPREADSHEETIDHERE/").sheet1

        # Determine the starting row and column from the cell reference (e.g., A1)
        starting_row = int(''.join(filter(str.isdigit, starting_cell)))  # Extract row number
        starting_col_letters = ''.join(filter(str.isalpha, starting_cell)).upper()  # Extract column letters

        # Convert column letters to index (e.g., 'AA' -> 27)
        def column_letter_to_number(column_letters):
            number = 0
            for char in column_letters:
                number = number * 26 + (ord(char) - ord('A') + 1)
            return number

        starting_col = column_letter_to_number(starting_col_letters)

        # Write data to the sheet starting from the specified cell
        if data:
            title, description = data
            current_row = starting_row
            sheet.update_cell(current_row, starting_col, title)
            sheet.update_cell(current_row + 1, starting_col, description)
            print(f"Data successfully written to Google Sheets starting at {starting_cell}.")
        else:
            print("No data to write.")
    except Exception as e:
        print(f"An error occurred while writing to Google Sheets: {e}")

if __name__ == "__main__":
    while True:
        try:
            # Fetch data every 20 minutes
            print("Running scraper...")
            post_data = fetch_api_data()
            if post_data:
                append_to_google_sheet(post_data, starting_cell="A1")
            else:
                print("No new data fetched.")
        except Exception as e:
            print(f"An unexpected error occurred in the main loop: {e}")

        print("Sleeping for 20 minutes...")
        time.sleep(20 * 60)  # 20 minutes in seconds