test_script.py

import logging
import json
from configparser import ConfigParser
from playwright.sync_api import sync_playwright
import constants
from post_utils import scrape_single_post_data

# Setup logging
logger = logging.getLogger()
handler = logging.StreamHandler()
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
handler.setFormatter(formatter)
logger.addHandler(handler)
logger.setLevel(logging.INFO)

# Load config
config = ConfigParser()
config.read('config.ini')

# Test URL (corrected to use threads.net instead of threads.com)
test_url = 'https://www.threads.net/@shygirlmoney/post/DDIWjdeSfyz?xmt=AQF0S7clUBWbZI55Oa1IhNIesFRIZRK0KeAr65S15AuD2g'

# Run the test
with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    context = browser.new_context()
    page = context.new_page()
    
    # Scrape the post
    result = scrape_single_post_data(page, test_url, config, logger, constants)
    
    # Print the result
    if result:
        print("\n\nRESULT:\n" + json.dumps(result, indent=2, ensure_ascii=False))
        print(f"\nImage URLs: {result.get('image_urls', [])}")
    else:
        print("Failed to scrape the post.")
    
    # Close the browser
    browser.close()