#!/usr/bin/env python3 """Пробуем достать данные устройств с yealink.com и support.yealink.com.""" import json import re import subprocess import sys UA = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/120 Safari/537.36" def fetch(url): return subprocess.run(["curl", "-sL", "-m", "45", "-A", UA, url], capture_output=True, text=True, timeout=90).stdout def nuxt_text(html): m = re.search(r']*id="__NUXT_DATA__"[^>]*>(.*?)', html, re.S) if not m: return "" try: data = json.loads(m.group(1).strip()) except Exception: return "" texts = [] def walk(o): if isinstance(o, str): if o.strip().startswith('{"type":"doc"'): try: d = json.loads(o) def t(n): if isinstance(n, dict): if n.get("type") == "text": texts.append(n.get("text", "")) for c in n.get("content") or []: t(c) t(d) except Exception: pass elif isinstance(o, list): for v in o: walk(v) elif isinstance(o, dict): for v in o.values(): walk(v) walk(data) return "\n".join(texts) def raw_text(html): html = re.sub(r"", " ", html, flags=re.S | re.I) html = re.sub(r"", " ", html, flags=re.S | re.I) txt = re.sub(r"<[^>]+>", "\n", html) txt = re.sub(r" ?", " ", txt) txt = re.sub(r"\n{2,}", "\n", txt) return txt KEYS = ("power", "poe", "vch", "pickup", "consumption", "watt", "Вт", "interface", "port", "microphone", "cable") def scan(text, name): print("\n=== %s ===" % name) lines = [ln.strip() for ln in text.splitlines() if ln.strip()] hits = [ln for ln in lines if any(k.lower() in ln.lower() for k in KEYS)] for ln in hits[:14]: print(" ", ln[:150]) if not hits: print(" (нет совпадений)") if __name__ == "__main__": urls = sys.argv[1:] for u in urls: html = fetch(u) name = u.split("/")[-2] if u.endswith("/") else u.rsplit("/", 1)[-1] print("\n" + "#" * 70) print("URL:", u, "| размер:", len(html)) t = nuxt_text(html) if t: scan(t, "NUXT: " + name[:40]) if len(t) < 200: scan(raw_text(html), "HTML: " + name[:40])