Update app.py

app.py

@@ -1,11 +1,105 @@
+import datetime
+import os
+import csv
+import time
+import hashlib
+import logging
 import gradio as gr
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+from selenium.webdriver.chrome.options import Options
+from webdriver_manager.chrome import ChromeDriverManager
 from huggingface_hub import InferenceClient
 
+# Configure logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
+# Define constants
+PREFIX = "Task started at {date_time_str}. Purpose: {purpose}"
+TASK_PROMPT = "Current task: {task}. History:\n{history}"
+
+# Define current date/time
+date_time_str = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+
+# Define purpose
+purpose = """
+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.
 """
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# Define history
+history = []
+
+# Define current task
+current_task = None
+
+# Default file path
+default_file_path = "user/app/scraped_data/culver/culvers_changes.csv"
+
+# Ensure the directory exists
+os.makedirs(os.path.dirname(default_file_path), exist_ok=True)
+
+# Function to monitor URLs for changes
+def monitor_urls(storage_location, url1, url2, scrape_interval, content_type):
+    global history
+    urls = [url1, url2]
+    previous_hashes = ["", ""]
+    
+    # Ensure the directory exists
+    os.makedirs(os.path.dirname(storage_location), exist_ok=True)
+    
+    with open(storage_location, "w", newline='') as csvfile:
+        csv_toolkit = csv.DictWriter(csvfile, fieldnames=["date", "time", "url", "change"])
+        csv_toolkit.writeheader()
+        
+        options = Options()
+        options.headless = True
+        options.add_argument("--disable-gpu")
+        options.add_argument("--no-sandbox")
+        options.add_argument("--disable-dev-shm-usage")
+        
+        with webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=options) as driver:
+            try:
+                while True:
+                    for i, url in enumerate(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[i]:
+                                previous_hashes[i] = 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}")
+                                csv_toolkit.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 Exception as e:
+                            logging.error(f"Error accessing {url}: {e}")
+                    
+                    time.sleep(scrape_interval * 60)  # Check every scrape_interval minutes
+            except KeyboardInterrupt:
+                logging.info("Monitoring stopped by user.")
+            finally:
+                driver.quit()
+
+# Define main function to handle user input
+def handle_input(storage_location, url1, url2, scrape_interval, content_type):
+    global current_task, history
+
+    current_task = f"Monitoring URLs: {url1}, {url2}"
+    history.append(f"Task started: {current_task}")
+    monitor_urls(storage_location, url1, url2, scrape_interval, content_type)
+    return TASK_PROMPT.format(task=current_task, history="\n".join(history))
+
+# Define the chat response function
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 def respond(
     message,
@@ -39,9 +133,7 @@ def respond(
         response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -55,9 +147,15 @@ demo = gr.ChatInterface(
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),
+        gr.Textbox(value=default_file_path, label="Storage Location"),
+        gr.Textbox(value="https://www.culver.k12.in.us/", label="URL 1"),
+        gr.Textbox(value="https://www.facebook.com/CulverCommunitySchools", label="URL 2"),
+        gr.Slider(minimum=1, maximum=60, value=5, step=1, label="Scrape Interval (minutes)"),
+        gr.Radio(choices=["text", "media", "both"], value="text", label="Content Type"),
     ],
+    title="Culvers Site Monitor and Chatbot",
+    description="Monitor changes on Culvers' websites and log them into a CSV file. Also, chat with a friendly chatbot."
 )
 
-
 if __name__ == "__main__":
     demo.launch()