"""One-off: probe pornxp listing regex parts. DELETE after fixing scraper."""
from app.extractors._fetch import browser_get
import re
r = browser_get("https://pornxp.ph/", timeout=20.0, follow_redirects=True)
html = r.text
print(f"len: {len(html)}")
patterns = [
("data-id alone",
r']*>.*?
![]()
([^<]+)
([^<]+)
'),
("full original",
r'.*?(?P
[^<]+)</div>'),
]
for name, p in patterns:
n = len(list(re.finditer(p, html, re.DOTALL | re.IGNORECASE)))
print(f"{name}: {n}")
# Bonus — peek at 5th card to see if anything quirky
all_ids = re.findall(r'<div class="item preview"\s+data-id="(\d+)"', html)
print(f"\nall card ids: {all_ids[:8]}...")
# Find card 5 raw — by index
positions = [m.start() for m in re.finditer(r'<div class="item preview"', html)]
if len(positions) >= 5:
print(f"\nCard #5 raw (first 500 chars):\n{html[positions[4]:positions[4]+500]!r}")