debug_sebi.py

"""Find PDF URL - dump raw HTML to find the JavaScript that loads the PDF."""
import requests

url = "https://www.sebi.gov.in/filings/public-issues/apr-2026/manipal-health-enterprises-limited_100763.html"
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}
r = requests.get(url, headers=headers, timeout=30)

# Dump raw HTML to file for inspection
with open("sebi_raw.html", "w", encoding="utf-8") as f:
    f.write(r.text)

print(f"Status: {r.status_code}")
print(f"HTML length: {len(r.text)} chars")
print(f"Saved to sebi_raw.html")