scraper.py

from curl_cffi import requests
from bs4 import BeautifulSoup
import json

LIVE_MATCH_URL = "https://www.espncricinfo.com/series/indian-premier-league-2024-1411166/chennai-super-kings-vs-royal-challengers-bengaluru-1st-match-1422119/live-cricket-score"

def bypass_firewall():
    print("========================================")
    print("   TLS FINGERPRINT SPOOFER ENGAGED      ")
    print("========================================")
    print("Deploying curl-cffi to impersonate Chrome 120 TLS handshake at the C-level...")
    try:
        # Instead of launching a whole physical browser, we use the specific encryption
        # signature of Chrome 120. Cloudflare looks at the raw binary packet and is tricked.
        response = requests.get(
            LIVE_MATCH_URL, 
            impersonate="chrome120",
            headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"}
        )
        
        soup = BeautifulSoup(response.text, 'html.parser')
        title = soup.find('title')
        
        if title:
            print(f"\n[TARGET TAB VISUAL]: {title.text}")
            
        if "Access Denied" in response.text or "Cloudflare" in response.text:
           print("\n[!] TLS Spoofing failed. Our datacenter IP is likely blocked completely.")
        else:
           print("\n[+] SUCCESS! WE BROKE THE WALL.")
           print("[+] Checking for Next.js internal JSON database...")
           
           next_data = soup.find('script', id='__NEXT_DATA__')
           if next_data:
               print("[+] INTERNAL DATABASE LOCATED!")
               live_json = json.loads(next_data.string)
               print("[+] RAW DATA ACQUIRED.")
           else:
               print("[-] We broke the wall, but they moved the data. HTML parsing required.")

    except Exception as e:
        print(f"\n[!] Critical Error: {e}")

if __name__ == "__main__":
    bypass_firewall()