# -*- coding: utf-8 -*- import os import sys import json from playwright.sync_api import sync_playwright CURRENT_DIR = os.path.dirname(os.path.abspath(__file__)) ROOT_DIR = os.path.dirname(CURRENT_DIR) if ROOT_DIR not in sys.path: sys.path.append(ROOT_DIR) USER_AGENT = ( "Mozilla/5.0 (Windows NT 10.0; Win64; x64) " "AppleWebKit/537.36 (KHTML, like Gecko) " "Chrome/136.0.0.0 Safari/537.36" ) class NaverSchoolApiLogger: def __init__(self, article_no, headless=False): self.article_no = str(article_no or "").strip() self.headless = headless self.playwright = None self.browser = None self.context = None self.page = None self.article_data = None self.detected = [] self.school_hits = [] def start(self): print("=" * 80) print("[BROWSER START]") self.playwright = sync_playwright().start() self.browser = self.playwright.chromium.launch( headless=self.headless, args=[ "--disable-blink-features=AutomationControlled", "--no-sandbox", ], ) self.context = self.browser.new_context( locale="ko-KR", viewport={"width": 1365, "height": 900}, user_agent=USER_AGENT, ) self.page = self.context.new_page() self.page.on("response", self.handle_response) print("[BROWSER READY]") def close(self): print("[BROWSER CLOSED]") try: if self.browser: self.browser.close() except Exception: pass try: if self.playwright: self.playwright.stop() except Exception: pass def build_url(self): return "https://new.land.naver.com/complexes?articleNo=" + self.article_no def is_json_response(self, response): try: content_type = response.headers.get("content-type", "") return "json" in content_type.lower() except Exception: return False def has_school_keyword(self, data): text = json.dumps(data, ensure_ascii=False).lower() keywords = [ "school", "education", "edu", "academy", "poi", "facility", "초등학교", "중학교", "고등학교", "학교", "학군", "교육", ] return any(k.lower() in text for k in keywords) def handle_response(self, response): try: url = str(response.url) lowered = url.lower() if not self.is_json_response(response): return watch_keywords = [ "article", "complex", "hscp", "school", "education", "edu", "poi", "facility", "around", "near", "map", "place", "infra", "developmentplan", ] if not any(k in lowered for k in watch_keywords): return data = response.json() print("[API DETECTED]", url) if f"/api/articles/{self.article_no}" in lowered: self.article_data = data print("[ARTICLE API CAPTURED]") if self.has_school_keyword(data): preview = json.dumps(data, ensure_ascii=False)[:700] print("[SCHOOL/EDU KEYWORD FOUND]", url) print("[PREVIEW]", preview) self.school_hits.append({ "url": url, "preview": preview, }) keys = list(data.keys()) if isinstance(data, dict) else [] self.detected.append({ "url": url, "keys": keys, }) except Exception: pass def get_article_meta(self): if not self.article_data: print("[ARTICLE META] not captured") return {} detail = self.article_data.get("articleDetail") or {} meta = { "article_no": detail.get("articleNo") or self.article_no, "article_name": detail.get("articleName"), "hscp_no": detail.get("hscpNo"), "complex_no": detail.get("complexNo"), "latitude": detail.get("latitude"), "longitude": detail.get("longitude"), "cortar_no": detail.get("cortarNo"), "realtor_id": detail.get("realtorId"), } print("=" * 80) print("[ARTICLE META]") for key, value in meta.items(): print(f"{key}: {value}") print("=" * 80) return meta def try_click_candidates(self): candidates = [ "text=학군", "text=학교", "text=주변", "text=주변시설", "text=생활", "text=단지정보", "text=시설", "text=교육", "text=교통", "button:has-text('학군')", "button:has-text('학교')", "button:has-text('주변')", "button:has-text('주변시설')", "a:has-text('학군')", "a:has-text('학교')", "a:has-text('주변')", "a:has-text('주변시설')", ] print("=" * 80) print("[CLICK CANDIDATES START]") for selector in candidates: try: locator = self.page.locator(selector) count = locator.count() if count <= 0: continue print("[CLICK TRY]", selector, "count=", count) locator.first.click(force=True, timeout=2500) self.page.wait_for_timeout(2500) except Exception as e: print("[CLICK FAIL]", selector, str(e)[:160]) print("[CLICK CANDIDATES END]") print("=" * 80) def try_direct_api_candidates(self, meta): hscp_no = meta.get("hscp_no") lat = meta.get("latitude") lon = meta.get("longitude") cortar_no = meta.get("cortar_no") candidates = [] if hscp_no: candidates += [ f"https://new.land.naver.com/api/complexes/{hscp_no}", f"https://new.land.naver.com/api/complexes/{hscp_no}/overview", f"https://new.land.naver.com/api/complexes/{hscp_no}/schools", f"https://new.land.naver.com/api/complexes/{hscp_no}/school", f"https://new.land.naver.com/api/complexes/{hscp_no}/facilities", f"https://new.land.naver.com/api/complexes/{hscp_no}/around", ] if lat and lon: candidates += [ f"https://new.land.naver.com/api/poi?lat={lat}&lon={lon}", f"https://new.land.naver.com/api/poi/school?lat={lat}&lon={lon}", f"https://new.land.naver.com/api/schools?lat={lat}&lon={lon}", f"https://new.land.naver.com/api/school?lat={lat}&lon={lon}", f"https://new.land.naver.com/api/facility?lat={lat}&lon={lon}", f"https://new.land.naver.com/api/facilities?lat={lat}&lon={lon}", ] if cortar_no: candidates += [ f"https://new.land.naver.com/api/regions/schools?cortarNo={cortar_no}", f"https://new.land.naver.com/api/schools?cortarNo={cortar_no}", ] print("=" * 80) print("[DIRECT API CANDIDATES START]") for url in candidates: try: result = self.page.evaluate( """ async (url) => { const res = await fetch(url, { method: 'GET', credentials: 'include', headers: { 'accept': 'application/json, text/plain, */*' } }); const text = await res.text(); return { url, status: res.status, contentType: res.headers.get('content-type') || '', text: text.slice(0, 1000) }; } """, url, ) print("[DIRECT API]", result.get("status"), url) text = result.get("text") or "" if any(k in text.lower() for k in [ "school", "education", "초등학교", "중학교", "고등학교", "학교", ]): print("[DIRECT SCHOOL HIT]", url) print(text[:1000]) except Exception as e: print("[DIRECT API FAIL]", url, str(e)[:160]) print("[DIRECT API CANDIDATES END]") print("=" * 80) def print_summary(self): print("=" * 80) print("[SUMMARY]") print("[DETECTED API COUNT]", len(self.detected)) print("[SCHOOL HIT COUNT]", len(self.school_hits)) if self.school_hits: print("-" * 80) print("[SCHOOL HITS]") for idx, item in enumerate(self.school_hits, 1): print(f"[{idx}] {item['url']}") print(item["preview"][:700]) print("-" * 80) print("=" * 80) def run(self): if not self.article_no: raise ValueError("article_no is required") self.start() try: url = self.build_url() print("[OPEN]", url) self.page.goto( url, wait_until="commit", timeout=30000, ) self.page.wait_for_timeout(7000) meta = self.get_article_meta() self.try_click_candidates() self.page.wait_for_timeout(5000) meta = self.get_article_meta() self.try_direct_api_candidates(meta) self.print_summary() finally: self.close() def main(): import argparse parser = argparse.ArgumentParser() parser.add_argument( "--article-no", type=str, default="2627920510", ) parser.add_argument( "--headless", action="store_true", help="headless mode", ) args = parser.parse_args() logger = NaverSchoolApiLogger( article_no=args.article_no, headless=args.headless, ) logger.run() if __name__ == "__main__": main()