""" OddsJam Scraper with Auto-2FA Scrapes arbitrage and positive EV data from OddsJam. Uses local Maildir to automatically retrieve 2FA codes via subprocess. """ import os import re import time import glob import json import subprocess import psycopg2 from datetime import datetime, timezone from playwright.sync_api import sync_playwright # Configuration ODDSJAM_EMAIL = 'admin@cashhive.ai' MAILDIR_PATH = '/home/admin/Maildir' DB_URL_FILE = '/var/www/html/eventheodds/.env' def load_db_url(): """Load database URL from .env file""" try: with open(DB_URL_FILE) as f: for line in f: if line.startswith('SPORTS_DATABASE_URL='): url = line.strip().split('=', 1)[1] return url.strip('"').split('?')[0] except Exception as e: print(f'Error loading DB URL: {e}') return None def get_oddsjam_code_from_content(content): """Extract 6-digit code from email content""" if 'oddsjam.com' not in content.lower(): return None if 'verification code' not in content.lower(): return None lines = content.split('\n') for line in lines: line = line.strip() if re.match(r'^\d{6}$', line): return line return None def wait_for_new_code(min_timestamp, timeout=180): """ Wait for a new 2FA code to arrive AFTER min_timestamp. Uses sudo to read emails. """ print(f' Waiting for 2FA code (email must be newer than {min_timestamp})...') start_time = time.time() while time.time() - start_time < timeout: time.sleep(5) # Find recent OddsJam emails using sudo try: # Get list of recent files cmd = f"sudo find {MAILDIR_PATH}/new {MAILDIR_PATH}/cur -type f -mmin -5 2>/dev/null" result = subprocess.run(cmd, shell=True, capture_output=True, text=True) files = [f.strip() for f in result.stdout.strip().split('\n') if f.strip()] for filepath in files: # Get mtime stat_result = subprocess.run(f'stat -c %Y "{filepath}"', shell=True, capture_output=True, text=True) try: mtime = float(stat_result.stdout.strip()) except: continue if mtime < min_timestamp: continue # Read file content with sudo cat_result = subprocess.run(f'sudo cat "{filepath}"', shell=True, capture_output=True, text=True) content = cat_result.stdout code = get_oddsjam_code_from_content(content) if code: print(f' Found NEW 2FA code: {code}') return code except Exception as e: print(f' Error checking emails: {e}') elapsed = int(time.time() - start_time) print(f' Still waiting... ({elapsed}s)') return None def scrape_oddsjam(conn): """Main scraping function""" total_records = 0 with sync_playwright() as p: browser = p.chromium.launch(headless=True) context = browser.new_context( viewport={'width': 1920, 'height': 1080}, user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36' ) page = context.new_page() # Step 1: Navigate to login print('Step 1: Navigating to OddsJam login...') page.goto('https://oddsjam.com/login', wait_until='networkidle') time.sleep(2) # Step 2: Enter email print('Step 2: Entering email...') page.fill('#email-address', ODDSJAM_EMAIL) time.sleep(1) # Record the timestamp BEFORE clicking sign in login_trigger_time = time.time() # Step 3: Click Sign In print('Step 3: Clicking Sign In...') page.click('button.bg-brand-blue') time.sleep(3) # Step 4: Wait for 2FA screen print('Step 4: Waiting for 2FA screen...') try: page.wait_for_selector('input[data-input-otp="true"]', timeout=10000) except: print(' 2FA input not found') # Get the 2FA code from local mail print('Step 5: Retrieving 2FA code from local mail...') code = wait_for_new_code(min_timestamp=login_trigger_time, timeout=180) if not code: print(' ERROR: Could not retrieve 2FA code') browser.close() return 0 print(f'Step 6: Entering 2FA code: {code}') otp_input = page.locator('input[data-input-otp="true"]') otp_input.fill(code) time.sleep(5) # Wait for redirect print('Step 7: Waiting for login to complete...') page.wait_for_load_state('networkidle') time.sleep(3) current_url = page.url print(f' Current URL: {current_url}') # Step 8: Navigate to Arbitrage page print('Step 8: Navigating to Arbitrage page...') page.goto('https://oddsjam.com/betting-tools/arbitrage', wait_until='networkidle') time.sleep(5) # Check if logged in user_data = page.evaluate('window.__NEXT_DATA__?.props?.pageProps?.fallback?.["auth/user"]?.user') if user_data: print(f' Logged in as: {user_data.get("email", "unknown")}') else: print(' WARNING: User appears not logged in') # Save debug files html = page.content() text = page.inner_text('body') with open('/tmp/oddsjam_debug_arb.html', 'w') as f: f.write(html) with open('/tmp/oddsjam_debug_arb.txt', 'w') as f: f.write(text) print(f' Saved debug files (HTML: {len(html)}, Text: {len(text)})') # Step 9: Navigate to Positive EV page print('Step 9: Navigating to Positive EV page...') try: page.goto('https://oddsjam.com/betting-tools/positive-ev', wait_until='networkidle', timeout=30000) time.sleep(5) html = page.content() text = page.inner_text('body') with open('/tmp/oddsjam_debug_ev.html', 'w') as f: f.write(html) with open('/tmp/oddsjam_debug_ev.txt', 'w') as f: f.write(text) print(f' Saved debug files (HTML: {len(html)}, Text: {len(text)})') except Exception as e: print(f' Error navigating to Positive EV: {e}') browser.close() return total_records def main(): print('=' * 60) print('ODDSJAM SCRAPER WITH AUTO-2FA') print(f'Time: {datetime.now(timezone.utc).isoformat()}') print('=' * 60) db_url = load_db_url() if not db_url: print('ERROR: No database URL found') return try: conn = psycopg2.connect(db_url) total = scrape_oddsjam(conn) conn.close() print(f'\nTotal records scraped: {total}') except Exception as e: print(f'ERROR: {e}') import traceback traceback.print_exc() if __name__ == '__main__': main()