app.py

import time
import hashlib
import logging
import datetime
import gradio as gr
import csv
from urllib.parse import urlparse
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.keys import Keys
from selenium.common.exceptions import NoSuchElementException
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
from transformers import pipeline
import feedparser
from bs4 import BeautifulSoup
import threading
import os

# Configure logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# Define constants
DEFAULT_FILE_PATH = "scraped_data"
PURPOSE = f"You go to Culvers sites, you continuously seek changes on them since your last observation. Anything new that gets logged and dumped into csv, stored in your log folder at user/app/scraped_data."
HISTORY = []
CURRENT_TASK = None
STOP_THREADS = False

# Define a function to monitor URLs for changes
def monitor_urls(storage_location, urls, scrape_interval, content_type, stop_scraping_flag):
    global HISTORY
    previous_hashes = {url: "" for url in urls}  # Use a dictionary for better organization

    try:
        with webdriver.Chrome(service=Service(webdriver.ChromeDriverManager().install()), options=Options()) as driver:
            while not stop_scraping_flag[0]:
                for url in urls:
                    try:
                        driver.get(url)
                        time.sleep(2)  # Wait for the page to load
                        if content_type == "text":
                            current_content = driver.page_source
                        elif content_type == "media":
                            current_content = driver.find_elements(By.TAG_NAME, "img")
                        else:
                            current_content = driver.page_source
                        current_hash = hashlib.md5(str(current_content).encode('utf-8')).hexdigest()
                        if current_hash != previous_hashes[url]:
                            previous_hashes[url] = current_hash
                            date_time_str = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
                            HISTORY.append(f"Change detected at {url} on {date_time_str}")
                            with open(os.path.join(storage_location, f"{urlparse(url).hostname}_changes.csv"), "a", newline="") as csvfile:
                                csv_writer = csv.DictWriter(csvfile, fieldnames=["date", "time", "url", "change"])
                                csv_writer.writerow({"date": date_time_str.split()[0], "time": date_time_str.split()[1], "url": url, "change": "Content changed"})
                                logging.info(f"Change detected at {url} on {date_time_str}")
                    except (NoSuchElementException, Exception) as e:
                        logging.error(f"Error accessing {url}: {e}")
                time.sleep(scrape_interval * 60)  # Check every scrape_interval minutes
    except Exception as e:
        logging.error(f"Error starting ChromeDriver: {e}")

# Define a function to start scraping
def start_scraping(storage_location, urls, scrape_interval, content_type, stop_scraping_flag):
    global CURRENT_TASK, HISTORY

    CURRENT_TASK = f"Monitoring URLs: {', '.join(urls)}"
    HISTORY.append(f"Task started: {CURRENT_TASK}")

    for url in urls:
        # Create a folder for the URL
        hostname = urlparse(url).hostname
        folder_path = os.path.join(storage_location, hostname)
        os.makedirs(folder_path, exist_ok=True)

        # Log the initial observation
        try:
            with webdriver.Chrome(service=Service(webdriver.ChromeDriverManager().install()), options=Options()) as driver:
                driver.get(url)
                time.sleep(2)  # Wait for the page to load
                if content_type == "text":
                    initial_content = driver.page_source
                elif content_type == "media":
                    initial_content = driver.find_elements(By.TAG_NAME, "img")
                else:
                    initial_content = driver.page_source
                initial_hash = hashlib.md5(str(initial_content).encode('utf-8')).hexdigest()
                HISTORY.append(f"Initial observation at {url}: {initial_hash}")
                with open(os.path.join(folder_path, f"{hostname}_initial_observation.txt"), "w") as file:
                    file.write(f"Initial observation at {url}: {initial_hash}")
        except (NoSuchElementException, Exception) as e:
            HISTORY.append(f"Error accessing {url}: {e}")

    # Start a new thread for monitoring URLs
    threading.Thread(target=monitor_urls, args=(storage_location, urls, scrape_interval, content_type, stop_scraping_flag)).start()

    return f"Started scraping {', '.join(urls)} every {scrape_interval} minutes."

# Define a function to stop scraping
def stop_scraping(stop_scraping_flag):
    stop_scraping_flag[0] = True
    return "Scraping stopped."

# Define the Gradio interface
def create_interface():
    with gr.Blocks() as demo:
        with gr.Row():
            with gr.Column():
                message = gr.Textbox(label="Message")
                system_message = gr.Textbox(value="You are a helpful assistant.", label="System message")
                max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
                temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
                top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
                storage_location = gr.Textbox(value="scraped_data", label="Storage Location")
                urls = gr.Textbox(label="URLs (comma separated)")
                scrape_interval = gr.Slider(minimum=1, maximum=60, value=5, step=1, label="Scrape Interval (minutes)")
                content_type = gr.Radio(choices=["text", "media", "both"], value="text", label="Content Type")
                start_button = gr.Button("Start Scraping")
                stop_button = gr.Button("Stop Scraping")
                csv_output = gr.Textbox(label="CSV Output", interactive=False)

            with gr.Column():
                chat_history = gr.Chatbot(label="Chat History")
                response_box = gr.Textbox(label="Response")

        stop_scraping_flag = [False]
        start_button.click(start_scraping, inputs=[storage_location, urls, scrape_interval, content_type, stop_scraping_flag], outputs=csv_output)
        stop_button.click(stop_scraping, inputs=[stop_scraping_flag], outputs=[csv_output])
        message.submit(chat_interface, inputs=[message, chat_history, system_message, max_tokens, temperature, top_p], outputs=[chat_history, response_box])

        # Add a button to display the CSV content for a selected URL
        with gr.Row():
            selected_url = gr.Textbox(label="Select URL for CSV Content")
            csv_button = gr.Button("Display CSV Content")
            csv_output = gr.Textbox(label="CSV Content Output", interactive=False)

        csv_button.click(display_csv, inputs=[selected_url], outputs=csv_output)

        # Add a button to display the RSS feed for a selected URL
        with gr.Row():
            selected_url = gr.Textbox(label="Select URL for RSS Feed")
            rss_button = gr.Button("Generate RSS Feed")
            rss_output = gr.Textbox(label="RSS Feed Output", interactive=False)

        rss_button.click(generate_rss_feed, inputs=[selected_url], outputs=rss_output)

    return demo

if __name__ == "__main__":
    demo = create_interface()
    demo.launch()