#!/usr/bin/env python3
"""TSC: temukan frasa persis yang masih mengandung klaim di #1905 dan #1936."""
import base64, html, json, re, urllib.request, importlib.util

WS = "/home/mantapman/.hermes/profiles/atun/workspace"
spec = importlib.util.spec_from_file_location("cfg_tsc", f"{WS}/cfg_tsc.py")
m = importlib.util.module_from_spec(spec); spec.loader.exec_module(m)
AUTH = base64.b64encode(f'{m.CFG["user"]}:{m.CFG["pass"]}'.encode()).decode()
UA = {"User-Agent": "Mozilla/5.0"}

for pid, pola in ((1905, r"BPOM|Halal|MUI|Kemenkes|permanen|tanpa risiko"),
                  (1936, r"Rp1?\d{3}|permanen|90%|20%")):
    r = urllib.request.Request(f'https://{m.CFG["domain"]}/wp-json/wp/v2/posts/{pid}?context=edit&_fields=content',
                               headers={"Authorization": f"Basic {AUTH}", **UA})
    with urllib.request.urlopen(r, timeout=150) as x:
        raw = json.loads(x.read())["content"]["raw"]
    print(f"\n{'='*90}\n### #{pid}")
    for mm in re.finditer(pola, raw, re.I):
        s = max(0, mm.start() - 260); e = min(len(raw), mm.end() + 200)
        print("   RAW  :", re.sub(r"\s+", " ", raw[s:e])[:420])