File size: 26,555 Bytes
c293f7c | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 | #!/usr/bin/env python3
"""
Real-time Data Processing Pipeline
- RSS ingestion from Indian news sources
- Fake news detection processing
- Database storage and state aggregation
"""
import asyncio
import logging
import sqlite3
import json
import hashlib
import time
from datetime import datetime
from typing import Dict, List, Optional
from concurrent.futures import ThreadPoolExecutor
import feedparser
import requests
from enhanced_fake_news_detector import fake_news_detector
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# RSS Sources for Indian news
RSS_SOURCES = [
{"name": "Times of India", "url": "https://timesofindia.indiatimes.com/rssfeedstopstories.cms", "reliability": 0.8},
{"name": "Hindustan Times", "url": "https://www.hindustantimes.com/feeds/rss/india-news/index.xml", "reliability": 0.8},
{"name": "Indian Express", "url": "https://indianexpress.com/feed/", "reliability": 0.85},
{"name": "NDTV", "url": "https://feeds.feedburner.com/NDTV-LatestNews", "reliability": 0.8},
{"name": "News18", "url": "https://www.news18.com/rss/india.xml", "reliability": 0.7},
{"name": "Zee News", "url": "https://zeenews.india.com/rss/india-national-news.xml", "reliability": 0.7},
{"name": "Business Standard", "url": "https://www.business-standard.com/rss/home_page_top_stories.rss", "reliability": 0.75},
{"name": "Deccan Herald", "url": "https://www.deccanherald.com/rss-feed/", "reliability": 0.75},
{"name": "The Hindu", "url": "https://www.thehindu.com/news/national/feeder/default.rss", "reliability": 0.9},
{"name": "Economic Times", "url": "https://economictimes.indiatimes.com/rssfeedstopstories.cms", "reliability": 0.8},
{"name": "India Today", "url": "https://www.indiatoday.in/rss/1206578", "reliability": 0.8},
{"name": "Outlook", "url": "https://www.outlookindia.com/rss/main/", "reliability": 0.75},
]
# Indian states for location mapping
INDIAN_STATES = {
"Andhra Pradesh": {"lat": 15.9129, "lng": 79.7400, "population": 49386799, "capital": "Amaravati", "type": "state"},
"Arunachal Pradesh": {"lat": 28.2180, "lng": 94.7278, "population": 1382611, "capital": "Itanagar", "type": "state"},
"Assam": {"lat": 26.2006, "lng": 92.9376, "population": 31169272, "capital": "Dispur"},
"Bihar": {"lat": 25.0961, "lng": 85.3131, "population": 103804637, "capital": "Patna"},
"Chhattisgarh": {"lat": 21.2787, "lng": 81.8661, "population": 25540196, "capital": "Raipur"},
"Delhi": {"lat": 28.7041, "lng": 77.1025, "population": 16787941, "capital": "New Delhi"},
"Goa": {"lat": 15.2993, "lng": 74.1240, "population": 1457723, "capital": "Panaji"},
"Gujarat": {"lat": 23.0225, "lng": 72.5714, "population": 60383628, "capital": "Gandhinagar"},
"Haryana": {"lat": 29.0588, "lng": 76.0856, "population": 25353081, "capital": "Chandigarh"},
"Himachal Pradesh": {"lat": 31.1048, "lng": 77.1734, "population": 6864602, "capital": "Shimla"},
"Jharkhand": {"lat": 23.6102, "lng": 85.2799, "population": 32966238, "capital": "Ranchi"},
"Karnataka": {"lat": 15.3173, "lng": 75.7139, "population": 61130704, "capital": "Bengaluru"},
"Kerala": {"lat": 10.8505, "lng": 76.2711, "population": 33387677, "capital": "Thiruvananthapuram"},
"Madhya Pradesh": {"lat": 22.9734, "lng": 78.6569, "population": 72597565, "capital": "Bhopal"},
"Maharashtra": {"lat": 19.7515, "lng": 75.7139, "population": 112372972, "capital": "Mumbai"},
"Manipur": {"lat": 24.6637, "lng": 93.9063, "population": 2855794, "capital": "Imphal"},
"Meghalaya": {"lat": 25.4670, "lng": 91.3662, "population": 2964007, "capital": "Shillong"},
"Mizoram": {"lat": 23.1645, "lng": 92.9376, "population": 1091014, "capital": "Aizawl"},
"Nagaland": {"lat": 26.1584, "lng": 94.5624, "population": 1980602, "capital": "Kohima"},
"Odisha": {"lat": 20.9517, "lng": 85.0985, "population": 42000000, "capital": "Bhubaneswar"},
"Punjab": {"lat": 31.1471, "lng": 75.3412, "population": 27704236, "capital": "Chandigarh"},
"Rajasthan": {"lat": 27.0238, "lng": 74.2179, "population": 68621012, "capital": "Jaipur"},
"Sikkim": {"lat": 27.5330, "lng": 88.5122, "population": 607688, "capital": "Gangtok"},
"Tamil Nadu": {"lat": 11.1271, "lng": 78.6569, "population": 72138958, "capital": "Chennai"},
"Telangana": {"lat": 18.1124, "lng": 79.0193, "population": 35000000, "capital": "Hyderabad"},
"Tripura": {"lat": 23.9408, "lng": 91.9882, "population": 3671032, "capital": "Agartala"},
"Uttar Pradesh": {"lat": 26.8467, "lng": 80.9462, "population": 199581477, "capital": "Lucknow"},
"Uttarakhand": {"lat": 30.0668, "lng": 79.0193, "population": 10116752, "capital": "Dehradun"},
"West Bengal": {"lat": 22.9868, "lng": 87.8550, "population": 91347736, "capital": "Kolkata", "type": "state"},
# Union Territories (8)
"Andaman and Nicobar Islands": {"lat": 11.7401, "lng": 92.6586, "population": 380581, "capital": "Port Blair", "type": "ut"},
"Chandigarh": {"lat": 30.7333, "lng": 76.7794, "population": 1055450, "capital": "Chandigarh", "type": "ut"},
"Dadra and Nagar Haveli and Daman and Diu": {"lat": 20.3974, "lng": 72.8328, "population": 615724, "capital": "Daman", "type": "ut"},
"Delhi": {"lat": 28.7041, "lng": 77.1025, "population": 32941309, "capital": "New Delhi", "type": "ut"},
"Jammu and Kashmir": {"lat": 34.0837, "lng": 74.7973, "population": 12267032, "capital": "Srinagar (Summer), Jammu (Winter)", "type": "ut"},
"Ladakh": {"lat": 34.1526, "lng": 77.5771, "population": 290492, "capital": "Leh", "type": "ut"},
"Lakshadweep": {"lat": 10.5667, "lng": 72.6417, "population": 64473, "capital": "Kavaratti", "type": "ut"},
"Puducherry": {"lat": 11.9416, "lng": 79.8083, "population": 1247953, "capital": "Puducherry", "type": "ut"}
}
# Global variables
processing_active = False
live_events = []
processed_count = 0
def fetch_single_rss_source(source: Dict) -> List[Dict]:
"""Fetch events from a single RSS source"""
events = []
try:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
}
response = requests.get(source['url'], headers=headers, timeout=30)
feed = feedparser.parse(response.content)
# Get latest entries
for entry in feed.entries[:5]: # 5 entries per source
event = {
'source': source['name'],
'title': entry.title,
'content': entry.get('summary', entry.get('description', '')),
'url': entry.get('link', ''),
'timestamp': datetime.now(),
'reliability': source['reliability']
}
events.append(event)
except Exception as e:
logger.error(f"❌ RSS fetch failed for {source['name']}: {e}")
return events
async def fetch_rss_data():
"""Fetch data from all RSS sources"""
events = []
# Use ThreadPoolExecutor for concurrent RSS fetching
with ThreadPoolExecutor(max_workers=8) as executor:
futures = []
for source in RSS_SOURCES:
future = executor.submit(fetch_single_rss_source, source)
futures.append(future)
# Collect results
for future in futures:
try:
source_events = future.result(timeout=30)
events.extend(source_events)
except Exception as e:
logger.error(f"RSS fetch failed: {e}")
logger.info(f"📊 Fetched {len(events)} events from {len(RSS_SOURCES)} sources")
return events
def extract_location(text: str) -> Optional[str]:
"""Extract Indian state from text. Returns None if no location is found.
Uses a comprehensive city→state mapping for 200+ Indian cities.
Removed the random fallback — unknown location = None, not random noise.
"""
if not text:
return None
text_lower = text.lower()
# ── Tier 1: Direct state name match ───────────────────────────────────────
for state in INDIAN_STATES.keys():
if state.lower() in text_lower:
return state
# ── Tier 2: Comprehensive city → state mapping (200+ cities) ──────────────
CITY_TO_STATE: Dict[str, str] = {
# Maharashtra
"mumbai": "Maharashtra", "bombay": "Maharashtra", "pune": "Maharashtra",
"nagpur": "Maharashtra", "nashik": "Maharashtra", "aurangabad": "Maharashtra",
"solapur": "Maharashtra", "kolhapur": "Maharashtra", "thane": "Maharashtra",
"navi mumbai": "Maharashtra", "amravati": "Maharashtra", "latur": "Maharashtra",
"dhule": "Maharashtra", "jalgaon": "Maharashtra", "akola": "Maharashtra",
"nanded": "Maharashtra", "satara": "Maharashtra", "sangli": "Maharashtra",
"ahmednagar": "Maharashtra", "ratnagiri": "Maharashtra",
# Delhi
"delhi": "Delhi", "new delhi": "Delhi", "noida": "Delhi",
"gurgaon": "Delhi", "gurugram": "Delhi", "faridabad": "Delhi",
"dwarka": "Delhi", "rohini": "Delhi", "janakpuri": "Delhi",
# Karnataka
"bangalore": "Karnataka", "bengaluru": "Karnataka", "mysore": "Karnataka",
"mysuru": "Karnataka", "hubli": "Karnataka", "dharwad": "Karnataka",
"mangalore": "Karnataka", "mangaluru": "Karnataka", "belgaum": "Karnataka",
"belagavi": "Karnataka", "gulbarga": "Karnataka", "kalaburagi": "Karnataka",
"davangere": "Karnataka", "bellary": "Karnataka", "bijapur": "Karnataka",
"shimoga": "Karnataka", "tumkur": "Karnataka", "udupi": "Karnataka",
# Tamil Nadu
"chennai": "Tamil Nadu", "madras": "Tamil Nadu", "coimbatore": "Tamil Nadu",
"madurai": "Tamil Nadu", "salem": "Tamil Nadu", "tiruchirappalli": "Tamil Nadu",
"trichy": "Tamil Nadu", "vellore": "Tamil Nadu", "tiruppur": "Tamil Nadu",
"erode": "Tamil Nadu", "tirunelveli": "Tamil Nadu", "ooty": "Tamil Nadu",
"kanchipuram": "Tamil Nadu", "thanjavur": "Tamil Nadu",
# West Bengal
"kolkata": "West Bengal", "calcutta": "West Bengal", "howrah": "West Bengal",
"durgapur": "West Bengal", "asansol": "West Bengal", "siliguri": "West Bengal",
"darjeeling": "West Bengal", "bardhaman": "West Bengal", "haldia": "West Bengal",
"kharagpur": "West Bengal", "malda": "West Bengal",
# Uttar Pradesh
"lucknow": "Uttar Pradesh", "kanpur": "Uttar Pradesh", "agra": "Uttar Pradesh",
"varanasi": "Uttar Pradesh", "allahabad": "Uttar Pradesh", "prayagraj": "Uttar Pradesh",
"meerut": "Uttar Pradesh", "ghaziabad": "Uttar Pradesh", "aligarh": "Uttar Pradesh",
"moradabad": "Uttar Pradesh", "bareilly": "Uttar Pradesh", "mathura": "Uttar Pradesh",
"vrindavan": "Uttar Pradesh", "gorakhpur": "Uttar Pradesh", "noida": "Uttar Pradesh",
"saharanpur": "Uttar Pradesh", "jhansi": "Uttar Pradesh", "ayodhya": "Uttar Pradesh",
# Gujarat
"ahmedabad": "Gujarat", "surat": "Gujarat", "vadodara": "Gujarat",
"baroda": "Gujarat", "rajkot": "Gujarat", "bhavnagar": "Gujarat",
"jamnagar": "Gujarat", "gandhinagar": "Gujarat", "anand": "Gujarat",
"morbi": "Gujarat", "nadiad": "Gujarat",
# Rajasthan
"jaipur": "Rajasthan", "jodhpur": "Rajasthan", "udaipur": "Rajasthan",
"kota": "Rajasthan", "bikaner": "Rajasthan", "ajmer": "Rajasthan",
"alwar": "Rajasthan", "bharatpur": "Rajasthan", "pushkar": "Rajasthan",
"sikar": "Rajasthan", "churu": "Rajasthan",
# Madhya Pradesh
"bhopal": "Madhya Pradesh", "indore": "Madhya Pradesh", "jabalpur": "Madhya Pradesh",
"gwalior": "Madhya Pradesh", "ujjain": "Madhya Pradesh", "sagar": "Madhya Pradesh",
"rewa": "Madhya Pradesh", "satna": "Madhya Pradesh",
# Andhra Pradesh
"visakhapatnam": "Andhra Pradesh", "vizag": "Andhra Pradesh",
"vijayawada": "Andhra Pradesh", "guntur": "Andhra Pradesh",
"tirupati": "Andhra Pradesh", "kurnool": "Andhra Pradesh",
"nellore": "Andhra Pradesh", "rajahmundry": "Andhra Pradesh",
"kakinada": "Andhra Pradesh",
# Telangana
"hyderabad": "Telangana", "secunderabad": "Telangana", "warangal": "Telangana",
"karimnagar": "Telangana", "khammam": "Telangana", "nizamabad": "Telangana",
# Kerala
"kochi": "Kerala", "cochin": "Kerala", "thiruvananthapuram": "Kerala",
"trivandrum": "Kerala", "kozhikode": "Kerala", "calicut": "Kerala",
"thrissur": "Kerala", "kollam": "Kerala", "palakkad": "Kerala",
"kannur": "Kerala", "kottayam": "Kerala", "alappuzha": "Kerala",
# Punjab
"amritsar": "Punjab", "ludhiana": "Punjab", "jalandhar": "Punjab",
"patiala": "Punjab", "bathinda": "Punjab", "mohali": "Punjab",
"chandigarh": "Punjab", "pathankot": "Punjab",
# Haryana
"gurgaon": "Haryana", "gurugram": "Haryana", "faridabad": "Haryana",
"panipat": "Haryana", "ambala": "Haryana", "hisar": "Haryana",
"rohtak": "Haryana", "karnal": "Haryana", "sonipat": "Haryana",
# Bihar
"patna": "Bihar", "gaya": "Bihar", "muzaffarpur": "Bihar",
"bhagalpur": "Bihar", "darbhanga": "Bihar", "purnia": "Bihar",
"bodh gaya": "Bihar", "nalanda": "Bihar",
# Odisha
"bhubaneswar": "Odisha", "cuttack": "Odisha", "rourkela": "Odisha",
"sambalpur": "Odisha", "berhampur": "Odisha", "puri": "Odisha",
# Assam
"guwahati": "Assam", "dispur": "Assam", "silchar": "Assam",
"dibrugarh": "Assam", "jorhat": "Assam", "nagaon": "Assam",
# Jharkhand
"ranchi": "Jharkhand", "jamshedpur": "Jharkhand", "dhanbad": "Jharkhand",
"bokaro": "Jharkhand", "hazaribagh": "Jharkhand",
# Uttarakhand
"dehradun": "Uttarakhand", "haridwar": "Uttarakhand", "rishikesh": "Uttarakhand",
"nainital": "Uttarakhand", "mussoorie": "Uttarakhand", "roorkee": "Uttarakhand",
# Himachal Pradesh
"shimla": "Himachal Pradesh", "manali": "Himachal Pradesh",
"dharamsala": "Himachal Pradesh", "solan": "Himachal Pradesh",
"kullu": "Himachal Pradesh",
# Jammu & Kashmir
"srinagar": "Jammu and Kashmir", "jammu": "Jammu and Kashmir",
"anantnag": "Jammu and Kashmir", "baramulla": "Jammu and Kashmir",
"pulwama": "Jammu and Kashmir", "sopore": "Jammu and Kashmir",
# North East
"imphal": "Manipur", "shillong": "Meghalaya", "aizawl": "Mizoram",
"kohima": "Nagaland", "agartala": "Tripura", "itanagar": "Arunachal Pradesh",
"gangtok": "Sikkim",
# Goa
"panaji": "Goa", "margao": "Goa", "vasco": "Goa", "mapusa": "Goa",
# Chhattisgarh
"raipur": "Chhattisgarh", "bhilai": "Chhattisgarh", "bilaspur": "Chhattisgarh",
"durg": "Chhattisgarh", "korba": "Chhattisgarh",
}
# Check multi-word cities first (longest match wins)
sorted_cities = sorted(CITY_TO_STATE.keys(), key=len, reverse=True)
for city in sorted_cities:
if city in text_lower:
return CITY_TO_STATE[city]
# ── Tier 3: Return None (no random fallback — data quality first) ──────────
return None
def categorize_content(content: str) -> str:
"""Categorize content into topics"""
content_lower = content.lower()
categories = {
'Politics': ['election', 'government', 'minister', 'party', 'vote', 'parliament', 'policy', 'bjp', 'congress'],
'Health': ['covid', 'vaccine', 'medicine', 'doctor', 'hospital', 'health', 'disease', 'medical'],
'Technology': ['5g', 'internet', 'app', 'phone', 'digital', 'cyber', 'ai', 'tech', 'smartphone'],
'Economy': ['rupee', 'inflation', 'price', 'market', 'economy', 'business', 'finance', 'stock'],
'Social': ['caste', 'religion', 'community', 'protest', 'violence', 'social', 'hindu', 'muslim'],
'Infrastructure': ['road', 'bridge', 'railway', 'airport', 'construction', 'development', 'metro'],
'Education': ['school', 'college', 'university', 'student', 'education', 'exam', 'neet', 'jee'],
'Environment': ['pollution', 'climate', 'environment', 'forest', 'wildlife', 'green', 'carbon'],
'Sports': ['cricket', 'football', 'hockey', 'olympics', 'ipl', 'sports', 'match', 'tournament'],
'Entertainment': ['bollywood', 'movie', 'film', 'actor', 'actress', 'celebrity', 'entertainment'],
'Crime': ['murder', 'rape', 'theft', 'crime', 'police', 'arrest', 'investigation', 'court'],
'Disaster': ['flood', 'earthquake', 'cyclone', 'fire', 'accident', 'disaster', 'emergency']
}
# Score each category
category_scores = {}
for category, keywords in categories.items():
score = sum(1 for keyword in keywords if keyword in content_lower)
if score > 0:
category_scores[category] = score
# Return category with highest score
if category_scores:
return max(category_scores.items(), key=lambda x: x[1])[0]
return 'General'
async def process_event(event: Dict) -> Optional[Dict]:
"""Process event with fake news detection"""
try:
# Extract location
state = extract_location(f"{event['title']} {event['content']}")
# Fake news analysis - using real detection
analysis = await fake_news_detector.detect_fake_news(
event['title'],
event['content'],
event['source'],
event.get('url', '')
)
# Create processed event
processed_event = {
'event_id': f"{event['source']}_{hashlib.md5(event['title'].encode()).hexdigest()}_{int(time.time())}",
'source': event['source'],
'title': event['title'],
'content': event['content'],
'summary': event['content'][:300] + '...' if len(event['content']) > 300 else event['content'],
'url': event.get('url', ''),
'state': state,
'category': categorize_content(event['content']),
'fake_news_verdict': analysis['verdict'],
'fake_news_confidence': analysis['confidence'],
'fake_news_score': analysis['fake_score'],
'ml_classification_result': json.dumps(analysis['components']['ml_classification']),
'linguistic_analysis_result': json.dumps(analysis['components']['linguistic_analysis']),
'source_credibility_result': json.dumps(analysis['components']['source_credibility']),
'fact_check_result': json.dumps(analysis['components']['fact_checking']),
'satellite_verification_result': json.dumps(analysis['components']['satellite_verification']) if analysis['components']['satellite_verification'] else None,
'cross_reference_score': analysis['components']['cross_reference_score'],
'indian_context_result': json.dumps(analysis['components']['indian_context']),
'indic_bert_embeddings': json.dumps(analysis['indic_bert_embeddings']),
'timestamp': event['timestamp']
}
return processed_event
except Exception as e:
logger.error(f"Event processing failed: {e}")
return None
def store_event(event: Dict):
"""Store event in database and update aggregations"""
try:
# Create data directory if it doesn't exist
import os
data_dir = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'data')
os.makedirs(data_dir, exist_ok=True)
db_path = os.path.join(data_dir, 'enhanced_fake_news.db')
conn = sqlite3.connect(db_path)
cursor = conn.cursor()
# Store event
cursor.execute('''
INSERT OR REPLACE INTO events
(event_id, source, title, content, summary, url, state, category,
fake_news_verdict, fake_news_confidence, fake_news_score,
ml_classification_result, linguistic_analysis_result, source_credibility_result,
fact_check_result, satellite_verification_result, cross_reference_score,
indian_context_result, indic_bert_embeddings, timestamp)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
''', (
event['event_id'], event['source'], event['title'], event['content'],
event['summary'], event['url'], event['state'], event['category'],
event['fake_news_verdict'], event['fake_news_confidence'], event['fake_news_score'],
event['ml_classification_result'], event['linguistic_analysis_result'],
event['source_credibility_result'], event['fact_check_result'],
event['satellite_verification_result'], event['cross_reference_score'],
event['indian_context_result'], event['indic_bert_embeddings'], event['timestamp']
))
# Update state aggregations
update_state_aggregations(event['state'], cursor)
# Add to live events
live_events.append(event)
if len(live_events) > 200: # Keep only latest 200 events
live_events.pop(0)
conn.commit()
conn.close()
verdict_emoji = "🔴" if event['fake_news_verdict'] == 'fake' else "🟢" if event['fake_news_verdict'] == 'real' else "🟡"
logger.info(f"✅ Stored: {event['title'][:60]}... | {event['state']} | {verdict_emoji} {event['fake_news_verdict'].upper()} ({event['fake_news_confidence']:.2f})")
except Exception as e:
logger.error(f"Failed to store event: {e}")
def update_state_aggregations(state: str, cursor):
"""Update state-level aggregations"""
try:
# Get recent events for this state (last 24 hours)
cursor.execute('''
SELECT fake_news_verdict, fake_news_score, category, title
FROM events
WHERE state = ? AND timestamp >= datetime('now', '-24 hours')
ORDER BY timestamp DESC
''', (state,))
recent_events = cursor.fetchall()
if recent_events:
# Calculate metrics — use column names; works for both sqlite3.Row and psycopg2 RealDictRow
total_events = len(recent_events)
fake_count = sum(1 for e in recent_events if e['fake_news_verdict'] == 'fake')
real_count = sum(1 for e in recent_events if e['fake_news_verdict'] == 'real')
uncertain_count= sum(1 for e in recent_events if e['fake_news_verdict'] == 'uncertain')
scores = [e['fake_news_score'] for e in recent_events if e['fake_news_score'] is not None]
avg_score = float(sum(scores) / len(scores)) if scores else 0.0
# Get trending categories
categories = [e['category'] for e in recent_events if e['category']]
category_counts = {}
for cat in categories:
category_counts[cat] = category_counts.get(cat, 0) + 1
trending_topics = [cat for cat, _ in sorted(category_counts.items(), key=lambda x: x[1], reverse=True)[:5]]
# Get recent headlines
recent_headlines = [e['title'] for e in recent_events[:5] if e['title']]
# Update aggregations
cursor.execute('''
UPDATE state_aggregations
SET total_events = ?, fake_news_count = ?, real_news_count = ?,
uncertain_count = ?, avg_fake_score = ?,
trending_topics = ?, recent_headlines = ?, last_updated = CURRENT_TIMESTAMP
WHERE state = ?
''', (
total_events, fake_count, real_count, uncertain_count, avg_score,
json.dumps(trending_topics), json.dumps(recent_headlines), state
))
except Exception as e:
logger.error(f"Failed to update state aggregations for {state}: {e}")
async def real_time_processing_loop():
"""Main real-time processing loop"""
global processing_active, processed_count
processing_active = True
logger.info("🚀 Starting REAL-TIME fake news detection processing")
logger.info(f"📊 Monitoring {len(RSS_SOURCES)} RSS sources")
logger.info(f"🗺️ Covering {len(INDIAN_STATES)} Indian states")
cycle_count = 0
while processing_active:
try:
cycle_count += 1
start_time = time.time()
logger.info(f"🔄 Processing cycle #{cycle_count} started")
# Fetch RSS data
events = await fetch_rss_data()
# Process events with fake news detection
processed_events = 0
for event in events:
processed_event = await process_event(event)
if processed_event:
store_event(processed_event)
processed_events += 1
processed_count += 1
end_time = time.time()
cycle_duration = end_time - start_time
logger.info(f"📊 Cycle #{cycle_count} completed in {cycle_duration:.2f}s")
logger.info(f" 📰 Fetched: {len(events)} events")
logger.info(f" ✅ Processed: {processed_events} events")
logger.info(f" 🗺️ Live events: {len(live_events)}")
logger.info(f" 📈 Total processed: {processed_count}")
# Wait 3 minutes before next cycle
await asyncio.sleep(180)
except Exception as e:
logger.error(f"Processing loop error: {e}")
await asyncio.sleep(60) # Wait 1 minute on error
def get_processing_stats():
"""Get current processing statistics"""
return {
'processing_active': processing_active,
'live_events_count': len(live_events),
'total_processed': processed_count,
'live_events': live_events[-10:] if live_events else [] # Latest 10 events
}
if __name__ == "__main__":
# Test the processor
asyncio.run(real_time_processing_loop()) |