Spaces:
Runtime error
Runtime error
File size: 10,455 Bytes
0f0e2ce 885ce0d d7e93db 7b31f93 8540cd7 1db1bf0 7b31f93 0f0e2ce 7b31f93 0f0e2ce 7b31f93 2288f21 7b31f93 0f0e2ce 2288f21 0f0e2ce 7b31f93 0f0e2ce 7b31f93 0f0e2ce 7b31f93 0f0e2ce 7b31f93 0f0e2ce 1780aff 0f0e2ce 2288f21 7b31f93 0f0e2ce 2288f21 7b31f93 0f0e2ce 2288f21 7b31f93 0f0e2ce 62cc7a7 0f0e2ce 2288f21 0f0e2ce 62cc7a7 7b31f93 885ce0d 7b31f93 2288f21 7b31f93 885ce0d 0f0e2ce 7b31f93 0f0e2ce 7b31f93 0f0e2ce 7b31f93 0f0e2ce 7b31f93 0f0e2ce 7b31f93 0f0e2ce 7b31f93 0f0e2ce 62cc7a7 7b31f93 0f0e2ce 2288f21 7b31f93 885ce0d 0f0e2ce 7b31f93 0f0e2ce 7b31f93 0f0e2ce 2288f21 7b31f93 0f0e2ce d7e93db 7b31f93 0f0e2ce 7b31f93 d7e93db 0f0e2ce 7b31f93 d7e93db 2288f21 7b31f93 885ce0d 2288f21 7b31f93 2288f21 7b31f93 0f0e2ce 7b31f93 0f0e2ce 2288f21 0f0e2ce 2288f21 7b31f93 0f0e2ce 7b31f93 2288f21 7b31f93 2288f21 1e4b6d9 2288f21 7b31f93 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 |
import asyncio
import csv
import logging
import os
from typing import List, Tuple
import aiohttp
import datetime
import difflib
import hashlib
from pathlib import Path
import feedparser
import gradio as gr
from huggingface_hub import InferenceClient
from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime
from sqlalchemy.orm import declarative_base, sessionmaker
from sqlalchemy.exc import SQLAlchemyError
import validators
# Configure logging
logging.basicConfig(level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)
# Configuration
HUGGINGFACE_API_KEY = os.getenv("HUGGINGFACE_API_KEY")
DEFAULT_MONITORING_INTERVAL = 300
MAX_MONITORING_INTERVAL = 600
CHANGE_FREQUENCY_THRESHOLD = 3
# Global variables
monitoring_tasks = {}
url_monitoring_intervals = {}
change_counts = {}
history = []
engine = None # Initialize the database engine globally
# Database setup
Base = declarative_base()
class Article(Base):
__tablename__ = 'articles'
id = Column(Integer, primary_key=True)
url = Column(String(255), nullable=False)
title = Column(String(255))
content = Column(Text)
hash = Column(String(32))
timestamp = Column(DateTime, default=datetime.datetime.utcnow)
# Utility functions
def sanitize_url(url: str) -> str:
return validators.url(url)
async def fetch_url_content(url: str,
session: aiohttp.ClientSession) -> Tuple[str, str]:
async with session.get(url) as response:
content = await response.text()
soup = BeautifulSoup(content, 'html.parser')
title = soup.title.string if soup.title else "No Title"
return title, content
def calculate_hash(content: str) -> str:
return hashlib.md5(content.encode('utf-8')).hexdigest()
async def save_to_database(url: str, title: str, content: str, hash: str):
session = Session()
try:
article = Article(url=url, title=title, content=content, hash=hash)
session.add(article)
session.commit()
except SQLAlchemyError as e:
logger.error(f"Database error: {e}")
session.rollback()
finally:
session.close()
def save_to_csv(storage_location: str, url: str, title: str, content: str,
timestamp: datetime.datetime):
try:
with open(storage_location, "a", newline='', encoding="utf-8") as csvfile:
csv_writer = csv.writer(csvfile)
csv_writer.writerow([
timestamp.strftime("%Y-%m-%d %H:%M:%S"), url, title, content
])
except Exception as e:
logger.error(f"Error saving to CSV: {e}")
async def monitor_url(url: str, interval: int, storage_location: str,
feed_rss: bool):
previous_hash = ""
async with aiohttp.ClientSession() as session:
while True:
try:
title, content = await fetch_url_content(url, session)
current_hash = calculate_hash(content)
if current_hash != previous_hash:
previous_hash = current_hash
timestamp = datetime.datetime.now()
if feed_rss:
await save_to_database(url, title, content,
current_hash)
if storage_location:
save_to_csv(storage_location, url, title, content,
timestamp)
history.append(
f"Change detected at {url} on {timestamp.strftime('%Y-%m-%d %H:%M:%S')}"
)
logger.info(f"Change detected at {url}")
change_counts[url] = change_counts.get(url, 0) + 1
if change_counts[url] >= CHANGE_FREQUENCY_THRESHOLD:
interval = max(60, interval // 2)
else:
change_counts[url] = 0
interval = min(interval * 2, MAX_MONITORING_INTERVAL)
url_monitoring_intervals[url] = interval
except Exception as e:
logger.error(f"Error monitoring {url}: {e}")
history.append(f"Error monitoring {url}: {e}")
await asyncio.sleep(interval)
async def start_monitoring(urls: List[str], storage_location: str,
feed_rss: bool):
for url in urls:
if url not in monitoring_tasks:
sanitized_url = sanitize_url(url)
if sanitized_url:
task = asyncio.create_task(
monitor_url(sanitized_url, DEFAULT_MONITORING_INTERVAL,
storage_location, feed_rss))
monitoring_tasks[sanitized_url] = task
else:
logger.warning(f"Invalid URL: {url}")
history.append(f"Invalid URL: {url}")
def stop_monitoring(url: str):
if url in monitoring_tasks:
monitoring_tasks[url].cancel()
del monitoring_tasks[url]
def generate_rss_feed():
session = Session()
try:
articles = session.query(Article).order_by(
Article.timestamp.desc()).limit(20).all()
feed = feedparser.FeedParserDict()
feed['title'] = 'Website Changes Feed'
feed['link'] = 'http://yourwebsite.com/feed'
feed['description'] = 'Feed of changes detected on monitored websites.'
feed['entries'] = [{
'title': article.title,
'link': article.url,
'description': article.content,
'published': article.timestamp
} for article in articles]
return feedparser.FeedGenerator().feed_from_dictionary(
feed).writeString('utf-8')
except SQLAlchemyError as e:
logger.error(f"Database error: {e}")
return None
finally:
session.close()
async def chatbot_response(message: str, history: List[Tuple[str, str]]):
try:
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1",
token=HUGGINGFACE_API_KEY)
response = await client.inference(message)
# Format the response as a dictionary
history.append({"role": "user", "content": message}) # Add user message
history.append({
"role": "assistant",
"content": response
}) # Add assistant response
return history, history
except Exception as e:
logger.error(f"Chatbot error: {e}")
history.append({"role": "user", "content": message}) # Add user message
history.append({
"role": "assistant",
"content": "Error: Could not get a response from the chatbot."
}) # Add error message
return history, history
def create_db_engine(db_url):
global engine, Base, Session
try:
engine = create_engine(db_url)
Base.metadata.create_all(engine)
Session = sessionmaker(bind=engine)
return "Database connected successfully!"
except SQLAlchemyError as e:
logger.error(f"Database error: {e}")
return f"Database error: {e}"
# Gradio interface
with gr.Blocks() as demo:
gr.Markdown("# Website Monitor and Chatbot")
with gr.Row():
with gr.Column(): # Side pane for database configuration
db_url = gr.Textbox(label="Database URL",
placeholder="e.g., sqlite:///monitoring.db")
db_connect_button = gr.Button("Connect to Database")
db_status = gr.Textbox(label="Database Status",
interactive=False,
value="Not connected")
db_connect_button.click(create_db_engine,
inputs=db_url,
outputs=db_status)
with gr.Column(): # Main pane for monitoring and chatbot
with gr.Tab("Configuration"):
target_urls = gr.Textbox(
label="Target URLs (comma-separated)",
placeholder=
"https://example.com, https://another-site.com")
storage_location = gr.Textbox(
label="Storage Location (CSV file path)",
placeholder="/path/to/your/file.csv")
feed_rss_checkbox = gr.Checkbox(label="Enable RSS Feed")
start_button = gr.Button("Start Monitoring")
stop_button = gr.Button("Stop Monitoring")
status_text = gr.Textbox(label="Status", interactive=False)
history_text = gr.Textbox(label="History",
lines=10,
interactive=False)
with gr.Tab("User-End View"):
feed_content = gr.JSON(label="RSS Feed Content")
with gr.Tab("Chatbot"):
chatbot_interface = gr.Chatbot(type='messages')
message_input = gr.Textbox(
placeholder="Type your message here...")
send_button = gr.Button("Send")
async def on_start_click(target_urls_str: str, storage_loc: str,
feed_enabled: bool):
urls = [url.strip() for url in target_urls_str.split(",")]
await start_monitoring(urls, storage_loc if storage_loc else None,
feed_enabled)
return "Monitoring started for valid URLs."
async def on_stop_click():
for url in list(monitoring_tasks.keys()):
stop_monitoring(url)
return "Monitoring stopped for all URLs."
start_button.click(
on_start_click,
inputs=[target_urls, storage_location, feed_rss_checkbox],
outputs=[status_text])
stop_button.click(on_stop_click, outputs=[status_text])
send_button.click(
chatbot_response,
inputs=[message_input, chatbot_interface],
outputs=[chatbot_interface, chatbot_interface])
async def update_feed_content():
return generate_rss_feed()
# Periodic update loop
async def periodic_update():
while True:
await asyncio.sleep(300) # Wait for 5 minutes
await update_feed_content()
# Start the periodic update task
asyncio.create_task(periodic_update())
if __name__ == "__main__":
demo.launch() |