""" Stake.com API discovery script. Intercepts all XHR/fetch network requests while navigating sports pages. Saves captured requests/responses to stake_discovery_results.json """ import json import time import sys import os import re from datetime import datetime # We'll collect everything here captured = { "graphql_requests": [], "rest_requests": [], "other_requests": [], "cookies": [], "headers_seen": {}, } GRAPHQL_URL = "https://stake.com/_api/graphql" TARGET_URLS = [ "https://stake.com/sports/soccer", "https://stake.com/sports/basketball", "https://stake.com/sports/tennis", ] # GraphQL operation names we care about INTERESTING_OPS = [ "sport", "event", "market", "match", "odds", "fixture", "upcoming", "prematch", "bet", "live", "soccer", "football", "basketball", "tennis", "league", "competition", "category", "sportEvent", "sportMarket", "sportBet", "sportLive", ] def is_interesting(url, body=None): url_lower = url.lower() if "graphql" in url_lower: return True if any(kw in url_lower for kw in ["sport", "event", "market", "odds", "bet", "match", "fixture"]): return True if body and any(kw in str(body).lower() for kw in ["sport", "event", "market", "odds"]): return True return False def truncate(data, max_len=3000): s = json.dumps(data, indent=2) if not isinstance(data, str) else data return s[:max_len] + "...[truncated]" if len(s) > max_len else s def run_discovery(): from playwright.sync_api import sync_playwright print("[*] Starting Playwright Chromium...") with sync_playwright() as p: browser = p.chromium.launch( headless=True, args=[ "--no-sandbox", "--disable-setuid-sandbox", "--disable-dev-shm-usage", "--disable-gpu", "--window-size=1280,900", ] ) context = browser.new_context( viewport={"width": 1280, "height": 900}, user_agent=( "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 " "(KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" ), locale="en-NG", timezone_id="Africa/Lagos", extra_http_headers={ "Accept-Language": "en-NG,en-GB;q=0.9,en;q=0.8", } ) page = context.new_page() # ── intercept responses ────────────────────────────────────────────── def handle_response(response): url = response.url method = response.request.method status = response.status req_headers = dict(response.request.headers) resp_headers = dict(response.headers) # skip static assets if any(url.endswith(ext) for ext in [ ".js", ".css", ".png", ".jpg", ".svg", ".woff", ".woff2", ".ico", ".gif", ".webp", ".map" ]): return if any(kw in url for kw in ["analytics", "gtm", "segment", "sentry", "hotjar", "intercom", "zendesk"]): return try: req_body_raw = response.request.post_data req_body = None if req_body_raw: try: req_body = json.loads(req_body_raw) except Exception: req_body = req_body_raw resp_body = None ct = resp_headers.get("content-type", "") if "json" in ct: try: resp_body = response.json() except Exception: pass if not is_interesting(url, req_body): return entry = { "url": url, "method": method, "status": status, "request_headers": req_headers, "request_body": req_body, "response_headers": resp_headers, "response_body": resp_body, "timestamp": datetime.utcnow().isoformat(), } if "graphql" in url.lower(): op_name = None if isinstance(req_body, dict): op_name = req_body.get("operationName", "") elif isinstance(req_body, list): op_name = [r.get("operationName", "") for r in req_body] entry["operation_name"] = op_name captured["graphql_requests"].append(entry) print(f" [GQL] {op_name} | status={status}") else: captured["rest_requests"].append(entry) print(f" [REST] {method} {url[:120]} | status={status}") except Exception as e: pass # network errors on in-flight requests are expected page.on("response", handle_response) # ── Phase 1: soccer ────────────────────────────────────────────────── print("\n[*] Navigating to stake.com/sports/soccer ...") try: page.goto("https://stake.com/sports/soccer", wait_until="networkidle", timeout=60000) except Exception as e: print(f" [warn] goto: {e}") time.sleep(4) # scroll to trigger lazy loads page.evaluate("window.scrollBy(0, 800)") time.sleep(2) page.evaluate("window.scrollBy(0, 800)") time.sleep(2) # ── Phase 2: click on a soccer event if any ─────────────────────── print("\n[*] Trying to click a soccer event ...") try: # try clicking first event link event_link = page.query_selector("a[href*='/sports/soccer/']") if event_link: href = event_link.get_attribute("href") print(f" Found event link: {href}") event_link.click() time.sleep(5) page.evaluate("window.scrollBy(0, 600)") time.sleep(2) except Exception as e: print(f" [warn] click event: {e}") # ── Phase 3: basketball ────────────────────────────────────────────── print("\n[*] Navigating to stake.com/sports/basketball ...") try: page.goto("https://stake.com/sports/basketball", wait_until="networkidle", timeout=60000) except Exception as e: print(f" [warn] goto basketball: {e}") time.sleep(4) page.evaluate("window.scrollBy(0, 800)") time.sleep(2) # ── Phase 4: tennis ────────────────────────────────────────────────── print("\n[*] Navigating to stake.com/sports/tennis ...") try: page.goto("https://stake.com/sports/tennis", wait_until="networkidle", timeout=60000) except Exception as e: print(f" [warn] goto tennis: {e}") time.sleep(4) page.evaluate("window.scrollBy(0, 800)") time.sleep(2) # ── Phase 5: try stake.com/ng ──────────────────────────────────────── print("\n[*] Checking stake.com/ng redirect ...") try: page.goto("https://stake.com/ng/sports/soccer", wait_until="networkidle", timeout=30000) final_url = page.url print(f" Final URL after /ng: {final_url}") except Exception as e: print(f" [warn] ng redirect: {e}") time.sleep(3) # ── Grab cookies ───────────────────────────────────────────────────── captured["cookies"] = context.cookies() print(f"\n[*] Captured {len(captured['cookies'])} cookies") browser.close() # ── Summarize ──────────────────────────────────────────────────────────── print(f"\n[*] Total GraphQL requests captured: {len(captured['graphql_requests'])}") print(f"[*] Total REST requests captured: {len(captured['rest_requests'])}") # Deduplicate GraphQL by operation name gql_by_op = {} for req in captured["graphql_requests"]: op = req.get("operation_name") key = str(op) if key not in gql_by_op: gql_by_op[key] = req print(f"\n[*] Unique GraphQL operations: {len(gql_by_op)}") for op, req in sorted(gql_by_op.items()): print(f" - {op}") # Save full results out_path = "/home/cyborg/Desktop/claude/arb_bot/tools/stake_discovery_results.json" with open(out_path, "w") as f: json.dump({ "graphql_by_operation": gql_by_op, "all_graphql": captured["graphql_requests"], "rest_requests": captured["rest_requests"], "cookies": captured["cookies"], }, f, indent=2, default=str) print(f"\n[*] Full results saved to: {out_path}") return gql_by_op, captured["rest_requests"] if __name__ == "__main__": gql_ops, rest = run_discovery() print("\n" + "="*70) print("GRAPHQL OPERATIONS DETAIL") print("="*70) for op_name, req in sorted(gql_ops.items()): print(f"\n--- Operation: {op_name} ---") print(f" URL: {req['url']}") print(f" Method: {req['method']}") print(f" Status: {req['status']}") body = req.get("request_body") if body: print(f" Request Body:") print(" " + json.dumps(body, indent=4)[:2000].replace("\n", "\n ")) resp = req.get("response_body") if resp: print(f" Response (truncated):") print(" " + json.dumps(resp, indent=4)[:2000].replace("\n", "\n ")) print("\n" + "="*70) print("REST REQUESTS DETAIL") print("="*70) for req in rest[:20]: print(f"\n {req['method']} {req['url'][:120]}") print(f" Status: {req['status']}")