# -*- coding: utf-8 -*- import os import sys import re 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 NaverSchoolTabLogger: 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 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 handle_response(self, response): try: url = str(response.url) if not self.is_json_response(response): return lowered = url.lower() if f"/api/articles/{self.article_no}" in lowered: self.article_data = response.json() print("[ARTICLE API CAPTURED]", url) watch = [ "school", "schools", "education", "edu", "complex", "facility", "around", "article", ] if any(x in lowered for x in watch): print("[API]", url) except Exception: pass def dump(self, label): out_dir = os.path.join(ROOT_DIR, "storage", "debug") os.makedirs(out_dir, exist_ok=True) label = re.sub(r"[^0-9A-Za-z_]+", "_", str(label or "dump")) path = os.path.join(out_dir, f"school_tab_{self.article_no}_{label}.txt") try: text = self.page.locator("body").inner_text(timeout=5000) except Exception as e: print("[DUMP FAIL]", label, str(e)[:200]) return "" with open(path, "w", encoding="utf-8") as f: f.write(text) print("[DUMP SAVED]", path) self.print_useful_lines(text) return text def print_useful_lines(self, text): keywords = [ "초등학교", "중학교", "고등학교", "학군", "학교", "교육", "관리비", "공용관리비", "난방비", "취득세", "보유세", "재산세", "중개보수", "교통", "공원", "편의시설", ] lines = [] for line in str(text or "").splitlines(): line = line.strip() if not line: continue if any(k in line for k in keywords): lines.append(line) print("=" * 80) print("[USEFUL LINES]", len(lines)) for line in lines[:160]: print(line) print("=" * 80) def print_clickable_candidates(self): print("=" * 80) print("[CLICKABLE CANDIDATES]") selectors = [ "a", "button", "[role='tab']", ".tab", ".tab_item", ".complex_tab", ".detail_tab", "li", ] for selector in selectors: try: items = self.page.locator(selector) count = min(items.count(), 120) for i in range(count): try: text = items.nth(i).inner_text(timeout=500).strip() if any(k in text for k in ["학군", "학교", "교육", "주변", "시설", "관리비"]): print(f"[{selector} #{i}]", repr(text[:120])) except Exception: pass except Exception: pass print("=" * 80) def click_by_text_variants(self): targets = [ ("school_info", "학군정보"), ("school", "학군"), ("school_word", "학교"), ("education", "교육"), ("around", "주변"), ("facility", "주변시설"), ("maintenance", "관리비"), ] for label, text in targets: print("=" * 80) print("[TARGET CLICK]", label, text) selectors = [ f"text={text}", f"a:has-text('{text}')", f"button:has-text('{text}')", f"li:has-text('{text}')", f"span:has-text('{text}')", f"div:has-text('{text}')", f"[role='tab']:has-text('{text}')", ] for selector in selectors: try: loc = self.page.locator(selector) count = loc.count() if count <= 0: continue print("[TRY]", selector, "count=", count) # first visible-like candidate 우선 clicked = False for i in range(min(count, 8)): try: box = loc.nth(i).bounding_box(timeout=1000) if not box: continue if box["width"] <= 0 or box["height"] <= 0: continue print("[CLICK BOX]", selector, i, box) loc.nth(i).click(force=True, timeout=3000) clicked = True break except Exception as e: print("[BOX CLICK FAIL]", selector, i, str(e)[:120]) if not clicked: loc.first.click(force=True, timeout=3000) self.page.wait_for_timeout(3500) self.dump(label) break except Exception as e: print("[CLICK FAIL]", selector, str(e)[:160]) def try_url_hashes(self): # 네이버 내부 라우팅이 탭 클릭 대신 hash/query를 볼 가능성 대비 hashes = [ "school", "education", "facility", "around", "maintenance", ] current = self.page.url for h in hashes: try: print("[HASH TRY]", h) self.page.goto(current + "#" + h, wait_until="commit", timeout=15000) self.page.wait_for_timeout(3000) self.dump("hash_" + h) except Exception as e: print("[HASH FAIL]", h, str(e)[:160]) def extract_candidates(self): try: text = self.page.locator("body").inner_text(timeout=5000) except Exception: text = "" patterns = [ (r"([가-힣A-Za-z0-9]{2,30}초등학교)", "초등학교"), (r"([가-힣A-Za-z0-9]{2,30}중학교)", "중학교"), (r"([가-힣A-Za-z0-9]{2,30}고등학교)", "고등학교"), ] seen = set() result = [] for pattern, school_type in patterns: for name in re.findall(pattern, text): if name in seen: continue seen.add(name) result.append((name, school_type)) print("=" * 80) print("[SCHOOL NAME CANDIDATES]", len(result)) for name, school_type in result: print(name, school_type) 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(8000) self.dump("initial") self.print_clickable_candidates() self.click_by_text_variants() self.try_url_hashes() self.extract_candidates() 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") args = parser.parse_args() logger = NaverSchoolTabLogger( article_no=args.article_no, headless=args.headless, ) logger.run() if __name__ == "__main__": main()