Dmitry Beresnev
commited on
Commit
·
d34f6ef
1
Parent(s):
9e5d0ad
fix logger
Browse files- app/services/news_monitor.py +11 -5
- app/services/news_monitor_twikit.py +16 -11
app/services/news_monitor.py
CHANGED
|
@@ -9,13 +9,19 @@ from datetime import datetime, timedelta
|
|
| 9 |
from typing import List, Dict, Optional
|
| 10 |
import streamlit as st
|
| 11 |
import time
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
try:
|
| 14 |
import snscrape.modules.twitter as sntwitter
|
| 15 |
SNSCRAPE_AVAILABLE = True
|
| 16 |
except ImportError:
|
| 17 |
SNSCRAPE_AVAILABLE = False
|
| 18 |
-
|
| 19 |
|
| 20 |
|
| 21 |
class FinanceNewsMonitor:
|
|
@@ -207,7 +213,7 @@ class FinanceNewsMonitor:
|
|
| 207 |
max_tweets: Total tweets to fetch (distributed across sources)
|
| 208 |
"""
|
| 209 |
if not SNSCRAPE_AVAILABLE:
|
| 210 |
-
|
| 211 |
return _self._get_mock_news()
|
| 212 |
|
| 213 |
all_tweets = []
|
|
@@ -256,14 +262,14 @@ class FinanceNewsMonitor:
|
|
| 256 |
failed_sources += 1
|
| 257 |
error_msg = str(e).lower()
|
| 258 |
if 'blocked' in error_msg or '404' in error_msg:
|
| 259 |
-
|
| 260 |
else:
|
| 261 |
-
|
| 262 |
continue
|
| 263 |
|
| 264 |
# If Twitter/X blocked all sources, fall back to mock data
|
| 265 |
if failed_sources >= len(_self.SOURCES) or len(all_tweets) == 0:
|
| 266 |
-
|
| 267 |
return _self._get_mock_news()
|
| 268 |
|
| 269 |
# Sort by impact and timestamp
|
|
|
|
| 9 |
from typing import List, Dict, Optional
|
| 10 |
import streamlit as st
|
| 11 |
import time
|
| 12 |
+
import logging
|
| 13 |
+
import re
|
| 14 |
+
|
| 15 |
+
# Configure logging
|
| 16 |
+
logging.basicConfig(level=logging.INFO)
|
| 17 |
+
logger = logging.getLogger(__name__)
|
| 18 |
|
| 19 |
try:
|
| 20 |
import snscrape.modules.twitter as sntwitter
|
| 21 |
SNSCRAPE_AVAILABLE = True
|
| 22 |
except ImportError:
|
| 23 |
SNSCRAPE_AVAILABLE = False
|
| 24 |
+
logger.warning("snscrape not available. Install with: pip install snscrape")
|
| 25 |
|
| 26 |
|
| 27 |
class FinanceNewsMonitor:
|
|
|
|
| 213 |
max_tweets: Total tweets to fetch (distributed across sources)
|
| 214 |
"""
|
| 215 |
if not SNSCRAPE_AVAILABLE:
|
| 216 |
+
logger.info("snscrape not available - using mock data")
|
| 217 |
return _self._get_mock_news()
|
| 218 |
|
| 219 |
all_tweets = []
|
|
|
|
| 262 |
failed_sources += 1
|
| 263 |
error_msg = str(e).lower()
|
| 264 |
if 'blocked' in error_msg or '404' in error_msg:
|
| 265 |
+
logger.warning(f"Twitter/X API blocked access for {source_name}")
|
| 266 |
else:
|
| 267 |
+
logger.error(f"Error scraping {source_name}: {e}")
|
| 268 |
continue
|
| 269 |
|
| 270 |
# If Twitter/X blocked all sources, fall back to mock data
|
| 271 |
if failed_sources >= len(_self.SOURCES) or len(all_tweets) == 0:
|
| 272 |
+
logger.warning("Twitter/X API unavailable - falling back to mock data for demonstration")
|
| 273 |
return _self._get_mock_news()
|
| 274 |
|
| 275 |
# Sort by impact and timestamp
|
app/services/news_monitor_twikit.py
CHANGED
|
@@ -11,8 +11,13 @@ import streamlit as st
|
|
| 11 |
import os
|
| 12 |
import asyncio
|
| 13 |
import re
|
|
|
|
| 14 |
from dotenv import load_dotenv
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
# Load environment variables
|
| 17 |
load_dotenv()
|
| 18 |
|
|
@@ -21,7 +26,7 @@ try:
|
|
| 21 |
TWIKIT_AVAILABLE = True
|
| 22 |
except ImportError:
|
| 23 |
TWIKIT_AVAILABLE = False
|
| 24 |
-
|
| 25 |
|
| 26 |
|
| 27 |
class FinanceNewsMonitor:
|
|
@@ -208,8 +213,8 @@ class FinanceNewsMonitor:
|
|
| 208 |
password = os.getenv('TWITTER_PASSWORD')
|
| 209 |
|
| 210 |
if not all([username, email, password]):
|
| 211 |
-
|
| 212 |
-
|
| 213 |
return False
|
| 214 |
|
| 215 |
await self.client.login(
|
|
@@ -219,11 +224,11 @@ class FinanceNewsMonitor:
|
|
| 219 |
)
|
| 220 |
|
| 221 |
self.authenticated = True
|
| 222 |
-
|
| 223 |
return True
|
| 224 |
|
| 225 |
except Exception as e:
|
| 226 |
-
|
| 227 |
return False
|
| 228 |
|
| 229 |
async def _scrape_twitter_async(self, max_tweets: int = 100) -> List[Dict]:
|
|
@@ -284,16 +289,16 @@ class FinanceNewsMonitor:
|
|
| 284 |
failed_sources += 1
|
| 285 |
error_msg = str(e).lower()
|
| 286 |
if 'rate limit' in error_msg:
|
| 287 |
-
|
| 288 |
elif 'unauthorized' in error_msg or 'forbidden' in error_msg:
|
| 289 |
-
|
| 290 |
else:
|
| 291 |
-
|
| 292 |
continue
|
| 293 |
|
| 294 |
# If all sources failed, fall back to mock data
|
| 295 |
if failed_sources >= len(self.SOURCES) or len(all_tweets) == 0:
|
| 296 |
-
|
| 297 |
return self._get_mock_news()
|
| 298 |
|
| 299 |
# Sort by impact and timestamp
|
|
@@ -311,7 +316,7 @@ class FinanceNewsMonitor:
|
|
| 311 |
max_tweets: Total tweets to fetch (distributed across sources)
|
| 312 |
"""
|
| 313 |
if not TWIKIT_AVAILABLE:
|
| 314 |
-
|
| 315 |
return _self._get_mock_news()
|
| 316 |
|
| 317 |
try:
|
|
@@ -322,7 +327,7 @@ class FinanceNewsMonitor:
|
|
| 322 |
loop.close()
|
| 323 |
return result
|
| 324 |
except Exception as e:
|
| 325 |
-
|
| 326 |
return _self._get_mock_news()
|
| 327 |
|
| 328 |
def _categorize_tweet(self, text: str, source_specialization: List[str]) -> str:
|
|
|
|
| 11 |
import os
|
| 12 |
import asyncio
|
| 13 |
import re
|
| 14 |
+
import logging
|
| 15 |
from dotenv import load_dotenv
|
| 16 |
|
| 17 |
+
# Configure logging
|
| 18 |
+
logging.basicConfig(level=logging.INFO)
|
| 19 |
+
logger = logging.getLogger(__name__)
|
| 20 |
+
|
| 21 |
# Load environment variables
|
| 22 |
load_dotenv()
|
| 23 |
|
|
|
|
| 26 |
TWIKIT_AVAILABLE = True
|
| 27 |
except ImportError:
|
| 28 |
TWIKIT_AVAILABLE = False
|
| 29 |
+
logger.warning("twikit not available. Install with: pip install twikit")
|
| 30 |
|
| 31 |
|
| 32 |
class FinanceNewsMonitor:
|
|
|
|
| 213 |
password = os.getenv('TWITTER_PASSWORD')
|
| 214 |
|
| 215 |
if not all([username, email, password]):
|
| 216 |
+
logger.warning("Twitter credentials not found in environment variables")
|
| 217 |
+
logger.info("Set TWITTER_USERNAME, TWITTER_EMAIL, TWITTER_PASSWORD in .env")
|
| 218 |
return False
|
| 219 |
|
| 220 |
await self.client.login(
|
|
|
|
| 224 |
)
|
| 225 |
|
| 226 |
self.authenticated = True
|
| 227 |
+
logger.info("Successfully authenticated with Twitter/X")
|
| 228 |
return True
|
| 229 |
|
| 230 |
except Exception as e:
|
| 231 |
+
logger.error(f"Twitter authentication failed: {e}")
|
| 232 |
return False
|
| 233 |
|
| 234 |
async def _scrape_twitter_async(self, max_tweets: int = 100) -> List[Dict]:
|
|
|
|
| 289 |
failed_sources += 1
|
| 290 |
error_msg = str(e).lower()
|
| 291 |
if 'rate limit' in error_msg:
|
| 292 |
+
logger.warning(f"Rate limited for {source_name}")
|
| 293 |
elif 'unauthorized' in error_msg or 'forbidden' in error_msg:
|
| 294 |
+
logger.warning(f"Access denied for {source_name}")
|
| 295 |
else:
|
| 296 |
+
logger.error(f"Error scraping {source_name}: {e}")
|
| 297 |
continue
|
| 298 |
|
| 299 |
# If all sources failed, fall back to mock data
|
| 300 |
if failed_sources >= len(self.SOURCES) or len(all_tweets) == 0:
|
| 301 |
+
logger.warning("Twitter/X scraping failed - falling back to mock data")
|
| 302 |
return self._get_mock_news()
|
| 303 |
|
| 304 |
# Sort by impact and timestamp
|
|
|
|
| 316 |
max_tweets: Total tweets to fetch (distributed across sources)
|
| 317 |
"""
|
| 318 |
if not TWIKIT_AVAILABLE:
|
| 319 |
+
logger.info("Twikit not available - using mock data")
|
| 320 |
return _self._get_mock_news()
|
| 321 |
|
| 322 |
try:
|
|
|
|
| 327 |
loop.close()
|
| 328 |
return result
|
| 329 |
except Exception as e:
|
| 330 |
+
logger.error(f"Error in async scraping: {e}")
|
| 331 |
return _self._get_mock_news()
|
| 332 |
|
| 333 |
def _categorize_tweet(self, text: str, source_specialization: List[str]) -> str:
|