#!/usr/bin/env python3 """Analisa hc71: artikel baru studiosoft.id + jejak & jadwal Threads/FB/LI per artikel HC.""" import json, re, sys, time from datetime import datetime, timezone sys.path.insert(0, "/home/mantapman/.hermes/profiles/atun/workspace") from repliz_client import ReplizClient, ACC import repliz_openssl_transport from openssl_fetch import fetch repliz_openssl_transport.install(verbose=False) WS = "/home/mantapman/.hermes/profiles/atun/workspace" OUT = "/tmp/hc71_analisa.json" def strip_chunked(b: bytes) -> bytes: if not re.match(rb"^[0-9a-fA-F]{1,7}\r\n", b): return b out = bytearray(); i = 0 while i < len(b): j = b.find(b"\r\n", i) if j == -1: break try: size = int(b[i:j].split(b";")[0].strip(), 16) except ValueError: break if size == 0: break out += b[j + 2:j + 2 + size] i = j + 2 + size + 2 return bytes(out) print("=== ARTIKEL TERBARU studiosoft.id ===") arts = [] for page in (1, 2): st, head, body = fetch("https://studiosoft.id/wp-json/wp/v2/posts?per_page=50&page=%d" "&_fields=id,link,title,date,slug,categories" % page) print("page", page, "status", st) if st != 200: break try: arr = json.loads(strip_chunked(body).decode("utf-8", "replace")) except Exception as e: print("parse gagal", e, body[:150]) break for x in arr: arts.append({"id": x.get("id"), "link": x.get("link"), "slug": x.get("slug"), "date": x.get("date"), "title": (x.get("title") or {}).get("rendered") if isinstance(x.get("title"), dict) else x.get("title")}) if len(arr) < 50: break json.dump(arts, open("/tmp/hc71_articles.json", "w"), ensure_ascii=False, indent=1) for a in arts[:14]: print(" ", a["date"], a["id"], a["slug"], "|", (a["title"] or "")[:70]) HC_SLUGS = [ "9-contoh-konten-digital-marketing-rumah-sakit-yang-edukatif-dan-tetap-etis", "10-channel-digital-marketing-rumah-sakit-yang-wajib-dikelola-di-era-online", "7-strategi-digital-marketing-rumah-sakit-untuk-menambah-pasien-setiap-bulan", "cara-klinik-kecantikan-di-surabaya-bisa-ditemukan-lebih-cepat-di-google", "strategi-seo-terbaik-untuk-klinik-kecantikan-di-surabaya-tingkatkan-pasien-lewat-google", "tips-seo-digital-marketing-surabaya-optimasi-local-untuk-klinik-dan-bengkel-lokal", "7-aplikasi-mental-health-anak-usia-4-10-tahun-yang-harus-dicoba-orang-tua", "pembuatan-website-rumah-sakit", "jasa-digital-marketing-rs", "jasa-digital-marketing-klinik", "panduan-seo-klinik-rumah-sakit", "seo-rumah-sakit", "digital-marketing-rumah-sakit-indikator", "rs-klinik-digital-marketing-2026", "google-business-profile-klinik", "kenapa-rumah-sakit-dan-klinik-wajib-punya-strategi-digital-marketing", "website-rumah-sakit-gagal-pasien", "konten-edukasi-kesehatan-kepercayaan-pasien", ] c = ReplizClient() docs, page = [], 1 while page < 130: for attempt in range(4): try: d = c.get_schedules(page=page, limit=100) break except Exception as e: print("retry page", page, e, flush=True) time.sleep(4) else: break ds = d.get("docs", []) if isinstance(d, dict) else d if not ds: break docs += ds if len(ds) < 100: break page += 1 print("\ntotal jadwal:", len(docs)) json.dump(docs, open("/tmp/hc71_sched.json", "w"), ensure_ascii=False) ACCOUNTS = { ACC.STUDIOSOFT_THREADS: "THREADS", ACC.STUDIOSOFT_LINKEDIN: "LINKEDIN", ACC.STUDIOSOFT_FB: "FACEBOOK", ACC.STUDIOSOFT_IG: "IG", } now = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M") print("now UTC:", now) def hits_for(slug): pat = re.compile(re.escape(slug)) res = {"threads": [], "linkedin": [], "facebook": [], "ig": []} for d in docs: plat = ACCOUNTS.get(d.get("accountId")) if not plat: continue blob = json.dumps({k: d.get(k) for k in ("title", "description", "topic")}, ensure_ascii=False) for m in (d.get("medias") or []): blob += " " + (m.get("url") or "") if pat.search(blob): res[plat.lower()].append((str(d.get("scheduleAt"))[:16], d.get("status"), d.get("type"), (d.get("_id") or d.get("id") or "")[:12])) return res NEW_CANDIDATES = [] for a in arts[:12]: if a["slug"] not in HC_SLUGS and a["slug"] not in NEW_CANDIDATES: NEW_CANDIDATES.append(a["slug"]) summary = {} for slug in HC_SLUGS + NEW_CANDIDATES: h = hits_for(slug) thr, li, fb = sorted(h["threads"]), sorted(h["linkedin"]), sorted(h["facebook"]) fut_thr = [x for x in thr if x[0] >= now and x[1] in ("pending", "scheduled", "draft")] last_thr = [x for x in thr if x[0] < now] fut_fb = [x for x in fb if x[0] >= now and x[1] in ("pending", "scheduled", "draft")] last_fb = [x for x in fb if x[0] < now] succ_fb = [x for x in fb if x[1] == "success"] summary[slug] = {"last_thr": last_thr[-1] if last_thr else None, "fut_thr": fut_thr, "last_fb": last_fb[-1] if last_fb else None, "last_fb_success": succ_fb[-1] if succ_fb else None, "fut_fb": fut_fb, "li_total": len(li), "li_fut": [x for x in li if x[0] >= now]} print("\n" + slug) print(" thr_last:", summary[slug]["last_thr"], "| thr_future:", fut_thr) print(" fb_last :", summary[slug]["last_fb"], "| fb_succ:", summary[slug]["last_fb_success"], "| fb_future:", fut_fb) print(" LI total:", len(li), "future:", len(summary[slug]["li_fut"])) json.dump(summary, open(OUT, "w"), indent=1, ensure_ascii=False) print("\n->", OUT) print("\n=== KANDIDAT THREADS (tanpa jadwal mendatang, urut jejak tertua) ===") belum = [(v["last_thr"][0] if v["last_thr"] else "0000", k) for k, v in summary.items() if k in HC_SLUGS and not v["fut_thr"]] for t, k in sorted(belum): print(" ", t, k) print("\n=== KANDIDAT FB (tanpa jadwal FB mendatang, urut jejak sukses tertua) ===") belum = [(v["last_fb_success"][0] if v["last_fb_success"] else "0000", k) for k, v in summary.items() if k in HC_SLUGS and not v["fut_fb"]] for t, k in sorted(belum): print(" ", t, k) print("\n=== ARTIKEL BARU (non-HC) & jejak LI ===") for slug in NEW_CANDIDATES: s = summary[slug] print(" ", slug, "| LI total:", s["li_total"], "| LI future:", len(s["li_fut"]), "| thr:", s["last_thr"], "| fb:", s["last_fb"])