Spaces:
Runtime error
Runtime error
acecalisto3
commited on
Update app2.py
Browse files
app2.py
CHANGED
@@ -19,7 +19,8 @@ import validators
|
|
19 |
from bs4 import BeautifulSoup
|
20 |
|
21 |
# Configure logging
|
22 |
-
logging.basicConfig(level=logging.INFO,
|
|
|
23 |
logger = logging.getLogger(__name__)
|
24 |
|
25 |
# Configuration
|
@@ -37,6 +38,7 @@ history = []
|
|
37 |
# Database setup
|
38 |
Base = declarative_base()
|
39 |
|
|
|
40 |
class Article(Base):
|
41 |
__tablename__ = 'articles'
|
42 |
id = Column(Integer, primary_key=True)
|
@@ -46,6 +48,7 @@ class Article(Base):
|
|
46 |
hash = Column(String(32))
|
47 |
timestamp = Column(DateTime, default=datetime.datetime.utcnow)
|
48 |
|
|
|
49 |
async def create_db_engine(db_url):
|
50 |
try:
|
51 |
engine = create_engine(db_url)
|
@@ -54,17 +57,23 @@ async def create_db_engine(db_url):
|
|
54 |
except SQLAlchemyError as e:
|
55 |
logger.error(f"Database error: {e}")
|
56 |
raise
|
|
|
|
|
57 |
def sanitize_url(url: str) -> str:
|
58 |
return url if validators.url(url) else None
|
59 |
|
60 |
-
|
|
|
|
|
61 |
async with session.get(url) as response:
|
62 |
content = await response.text()
|
63 |
soup = BeautifulSoup(content, 'html.parser')
|
64 |
title = soup.title.string if soup.title else "No Title"
|
65 |
return title, content
|
66 |
|
67 |
-
|
|
|
|
|
68 |
try:
|
69 |
article = Article(url=url, title=title, content=content, hash=hash)
|
70 |
session.add(article)
|
@@ -73,18 +82,24 @@ async def save_to_database(session, url: str, title: str, content: str, hash: st
|
|
73 |
logger.error(f"Database error: {e}")
|
74 |
await session.rollback()
|
75 |
|
76 |
-
|
|
|
|
|
77 |
try:
|
78 |
os.makedirs(os.path.dirname(storage_location), exist_ok=True)
|
79 |
with open(storage_location, "a", newline='', encoding="utf-8") as csvfile:
|
80 |
csv_writer = csv.writer(csvfile)
|
81 |
-
csv_writer.writerow([
|
|
|
|
|
82 |
except IOError as e:
|
83 |
logger.error(f"IOError saving to CSV: {e}")
|
84 |
except Exception as e:
|
85 |
logger.error(f"Unexpected error saving to CSV: {e}")
|
86 |
|
87 |
-
|
|
|
|
|
88 |
previous_hash = ""
|
89 |
async with aiohttp.ClientSession() as session:
|
90 |
while True:
|
@@ -98,14 +113,19 @@ async def monitor_url(url: str, interval: int, storage_location: str, feed_rss:
|
|
98 |
|
99 |
if feed_rss:
|
100 |
try:
|
101 |
-
await save_to_database(db_session, url, title,
|
|
|
102 |
except SQLAlchemyError as e:
|
103 |
-
logger.error(
|
|
|
104 |
|
105 |
if storage_location:
|
106 |
-
await save_to_csv(storage_location, url, title,
|
|
|
107 |
|
108 |
-
history.append(
|
|
|
|
|
109 |
logger.info(f"Change detected at {url}")
|
110 |
|
111 |
change_counts[url] = change_counts.get(url, 0) + 1
|
@@ -125,23 +145,29 @@ async def monitor_url(url: str, interval: int, storage_location: str, feed_rss:
|
|
125 |
|
126 |
await asyncio.sleep(interval)
|
127 |
|
128 |
-
|
|
|
|
|
129 |
global db_session
|
130 |
for url in urls:
|
131 |
if url not in monitoring_tasks:
|
132 |
sanitized_url = sanitize_url(url)
|
133 |
if sanitized_url:
|
134 |
-
task = asyncio.create_task(
|
|
|
|
|
135 |
monitoring_tasks[sanitized_url] = task
|
136 |
else:
|
137 |
logger.warning(f"Invalid URL: {url}")
|
138 |
history.append(f"Invalid URL: {url}")
|
139 |
return "Monitoring started"
|
140 |
|
|
|
141 |
async def cleanup_resources(url: str):
|
142 |
# Add any cleanup logic here, e.g., closing database connections
|
143 |
pass
|
144 |
|
|
|
145 |
def stop_monitoring(url: str):
|
146 |
if url in monitoring_tasks:
|
147 |
monitoring_tasks[url].cancel()
|
@@ -149,11 +175,6 @@ def stop_monitoring(url: str):
|
|
149 |
del monitoring_tasks[url]
|
150 |
return "Monitoring stopped"
|
151 |
|
152 |
-
async def on_start_click(target_urls_str: str, storage_loc: str, feed_enabled: bool):
|
153 |
-
urls = [url.strip() for url in target_urls_str.split(",")] # Split the input by commas
|
154 |
-
result = await start_monitoring(urls, storage_loc if storage_loc else None, feed_enabled)
|
155 |
-
return result
|
156 |
-
|
157 |
|
158 |
def generate_rss_feed():
|
159 |
session = Session()
|
@@ -178,9 +199,11 @@ def generate_rss_feed():
|
|
178 |
finally:
|
179 |
session.close()
|
180 |
|
|
|
181 |
async def chatbot_response(message: str, history: List[Tuple[str, str]]):
|
182 |
try:
|
183 |
-
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1",
|
|
|
184 |
response = await client.text_generation(message, max_new_tokens=100)
|
185 |
|
186 |
history.append((message, response[0]['generated_text']))
|
@@ -188,9 +211,11 @@ async def chatbot_response(message: str, history: List[Tuple[str, str]]):
|
|
188 |
return history, history
|
189 |
except Exception as e:
|
190 |
logger.error(f"Chatbot error: {e}")
|
191 |
-
history.append((message,
|
|
|
192 |
return history, history
|
193 |
|
|
|
194 |
async def update_db_status(db_status):
|
195 |
while True:
|
196 |
try:
|
@@ -200,10 +225,12 @@ async def update_db_status(db_status):
|
|
200 |
await db_status.update(value="Disconnected")
|
201 |
await asyncio.sleep(60) # Check every minute
|
202 |
|
|
|
203 |
async def update_feed_content(db_session):
|
204 |
try:
|
205 |
-
articles = await db_session.
|
206 |
-
|
|
|
207 |
'title': 'Website Changes Feed',
|
208 |
'link': 'http://yourwebsite.com/feed',
|
209 |
'description': 'Feed of changes detected on monitored websites.',
|
@@ -224,10 +251,11 @@ async def periodic_update_with_error_handling(db_session):
|
|
224 |
while True:
|
225 |
try:
|
226 |
await asyncio.sleep(300) # Wait for 5 minutes
|
227 |
-
await update_feed_content(db_session)
|
228 |
except Exception as e:
|
229 |
logger.error(f"Error in periodic update: {e}")
|
230 |
|
|
|
231 |
async def main():
|
232 |
global db_session
|
233 |
try:
|
@@ -303,4 +331,5 @@ async def main():
|
|
303 |
|
304 |
|
305 |
if __name__ == "__main__":
|
306 |
-
asyncio.run(main())
|
|
|
|
19 |
from bs4 import BeautifulSoup
|
20 |
|
21 |
# Configure logging
|
22 |
+
logging.basicConfig(level=logging.INFO,
|
23 |
+
format='%(asctime)s - %(levelname)s - %(message)s')
|
24 |
logger = logging.getLogger(__name__)
|
25 |
|
26 |
# Configuration
|
|
|
38 |
# Database setup
|
39 |
Base = declarative_base()
|
40 |
|
41 |
+
|
42 |
class Article(Base):
|
43 |
__tablename__ = 'articles'
|
44 |
id = Column(Integer, primary_key=True)
|
|
|
48 |
hash = Column(String(32))
|
49 |
timestamp = Column(DateTime, default=datetime.datetime.utcnow)
|
50 |
|
51 |
+
|
52 |
async def create_db_engine(db_url):
|
53 |
try:
|
54 |
engine = create_engine(db_url)
|
|
|
57 |
except SQLAlchemyError as e:
|
58 |
logger.error(f"Database error: {e}")
|
59 |
raise
|
60 |
+
|
61 |
+
|
62 |
def sanitize_url(url: str) -> str:
|
63 |
return url if validators.url(url) else None
|
64 |
|
65 |
+
|
66 |
+
async def fetch_url_content(url: str,
|
67 |
+
session: aiohttp.ClientSession) -> Tuple[str, str]:
|
68 |
async with session.get(url) as response:
|
69 |
content = await response.text()
|
70 |
soup = BeautifulSoup(content, 'html.parser')
|
71 |
title = soup.title.string if soup.title else "No Title"
|
72 |
return title, content
|
73 |
|
74 |
+
|
75 |
+
async def save_to_database(session, url: str, title: str, content: str,
|
76 |
+
hash: str):
|
77 |
try:
|
78 |
article = Article(url=url, title=title, content=content, hash=hash)
|
79 |
session.add(article)
|
|
|
82 |
logger.error(f"Database error: {e}")
|
83 |
await session.rollback()
|
84 |
|
85 |
+
|
86 |
+
async def save_to_csv(storage_location: str, url: str, title: str,
|
87 |
+
content: str, timestamp: datetime.datetime):
|
88 |
try:
|
89 |
os.makedirs(os.path.dirname(storage_location), exist_ok=True)
|
90 |
with open(storage_location, "a", newline='', encoding="utf-8") as csvfile:
|
91 |
csv_writer = csv.writer(csvfile)
|
92 |
+
csv_writer.writerow([
|
93 |
+
timestamp.strftime("%Y-%m-%d %H:%M:%S"), url, title, content
|
94 |
+
])
|
95 |
except IOError as e:
|
96 |
logger.error(f"IOError saving to CSV: {e}")
|
97 |
except Exception as e:
|
98 |
logger.error(f"Unexpected error saving to CSV: {e}")
|
99 |
|
100 |
+
|
101 |
+
async def monitor_url(url: str, interval: int, storage_location: str,
|
102 |
+
feed_rss: bool, db_session):
|
103 |
previous_hash = ""
|
104 |
async with aiohttp.ClientSession() as session:
|
105 |
while True:
|
|
|
113 |
|
114 |
if feed_rss:
|
115 |
try:
|
116 |
+
await save_to_database(db_session, url, title,
|
117 |
+
content, current_hash)
|
118 |
except SQLAlchemyError as e:
|
119 |
+
logger.error(
|
120 |
+
f"Database error while saving {url}: {e}")
|
121 |
|
122 |
if storage_location:
|
123 |
+
await save_to_csv(storage_location, url, title,
|
124 |
+
content, timestamp)
|
125 |
|
126 |
+
history.append(
|
127 |
+
f"Change detected at {url} on {timestamp.strftime('%Y-%m-%d %H:%M:%S')}"
|
128 |
+
)
|
129 |
logger.info(f"Change detected at {url}")
|
130 |
|
131 |
change_counts[url] = change_counts.get(url, 0) + 1
|
|
|
145 |
|
146 |
await asyncio.sleep(interval)
|
147 |
|
148 |
+
|
149 |
+
async def start_monitoring(urls: List[str], storage_location: str,
|
150 |
+
feed_rss: bool):
|
151 |
global db_session
|
152 |
for url in urls:
|
153 |
if url not in monitoring_tasks:
|
154 |
sanitized_url = sanitize_url(url)
|
155 |
if sanitized_url:
|
156 |
+
task = asyncio.create_task(
|
157 |
+
monitor_url(sanitized_url, DEFAULT_MONITORING_INTERVAL,
|
158 |
+
storage_location, feed_rss, db_session))
|
159 |
monitoring_tasks[sanitized_url] = task
|
160 |
else:
|
161 |
logger.warning(f"Invalid URL: {url}")
|
162 |
history.append(f"Invalid URL: {url}")
|
163 |
return "Monitoring started"
|
164 |
|
165 |
+
|
166 |
async def cleanup_resources(url: str):
|
167 |
# Add any cleanup logic here, e.g., closing database connections
|
168 |
pass
|
169 |
|
170 |
+
|
171 |
def stop_monitoring(url: str):
|
172 |
if url in monitoring_tasks:
|
173 |
monitoring_tasks[url].cancel()
|
|
|
175 |
del monitoring_tasks[url]
|
176 |
return "Monitoring stopped"
|
177 |
|
|
|
|
|
|
|
|
|
|
|
178 |
|
179 |
def generate_rss_feed():
|
180 |
session = Session()
|
|
|
199 |
finally:
|
200 |
session.close()
|
201 |
|
202 |
+
|
203 |
async def chatbot_response(message: str, history: List[Tuple[str, str]]):
|
204 |
try:
|
205 |
+
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1",
|
206 |
+
token=HUGGINGFACE_API_KEY)
|
207 |
response = await client.text_generation(message, max_new_tokens=100)
|
208 |
|
209 |
history.append((message, response[0]['generated_text']))
|
|
|
211 |
return history, history
|
212 |
except Exception as e:
|
213 |
logger.error(f"Chatbot error: {e}")
|
214 |
+
history.append((message,
|
215 |
+
"Error: Could not get a response from the chatbot."))
|
216 |
return history, history
|
217 |
|
218 |
+
|
219 |
async def update_db_status(db_status):
|
220 |
while True:
|
221 |
try:
|
|
|
225 |
await db_status.update(value="Disconnected")
|
226 |
await asyncio.sleep(60) # Check every minute
|
227 |
|
228 |
+
|
229 |
async def update_feed_content(db_session):
|
230 |
try:
|
231 |
+
articles = await db_session.query(Article).order_by(
|
232 |
+
Article.timestamp.desc()).limit(20).all()
|
233 |
+
feed {
|
234 |
'title': 'Website Changes Feed',
|
235 |
'link': 'http://yourwebsite.com/feed',
|
236 |
'description': 'Feed of changes detected on monitored websites.',
|
|
|
251 |
while True:
|
252 |
try:
|
253 |
await asyncio.sleep(300) # Wait for 5 minutes
|
254 |
+
await update_feed_content(db_session)
|
255 |
except Exception as e:
|
256 |
logger.error(f"Error in periodic update: {e}")
|
257 |
|
258 |
+
|
259 |
async def main():
|
260 |
global db_session
|
261 |
try:
|
|
|
331 |
|
332 |
|
333 |
if __name__ == "__main__":
|
334 |
+
asyncio.run(main())
|
335 |
+
|