requirements.txt 추가 및 lib.py > common.py 수정과 리팩토링

| ----------- | ---------------------- | ------------------------- |
| 예외 처리       | `except:`              | `except Exception:` 으로 제한 |
| 디버깅 출력      | `print()` 섞여 있음        | `debug()` 함수로 통일          |
| 메시지 전송      | 반복적 `MessageSender()`  | 공통화                       |
| 중복 제거       | `작성자/작성일/내용` key 반복 비교 | 튜플 키 비교 유지, 주석 보완         |
| 리뷰 추출 실패 로그 | 단순 출력                  | `place_id` 정보 포함          |
| 메시지 포맷      | biz와 형식 동일             | 동일한 스타일 유지                |

.env_sample

@@ -16,7 +16,7 @@ NAVER_PW=Login_Password
 
 # 메시지 전송 플랫폼 선택
 # mattermost, synology_chat, telegram 중 선택(콤마로 구분) 또는 빈 값(발송 안함)
-MESSAGE_PLATFORM=mattermost,telegram
+MESSAGE_PLATFORMS=mattermost,telegram
 
 # Mattermost 설정
 # MATTERMOST_URL은 마지막에 '/' 없이 입력
@@ -27,7 +27,7 @@ MATTERMOST_CHANNEL_ID=CHANNEL_ID
 MATTERMOST_BOT_TOKEN=BOT_TOKEN
 
 # Synology Chat Webhook URL (사용 시 설정)
-SYNology_CHAT_WEBHOOK_URL=https://synology.chat/webhook/your_webhook_url
+Synology_CHAT_WEBHOOK_URL=https://synology.chat/webhook/your_webhook_url
 
 # Telegram 설정 (사용 시 설정)
 TELEGRAM_BOT_TOKEN=your_bot_token

README.md

@@ -1,7 +1,7 @@
 # 네이버 리뷰 크롤러
 - 네이버 비즈니스, 네이버 map 기준 리뷰를 크롤링해 메시지를 보내줌
 # 폴더 구조
-``` bash
+```bash
 /
 ├── .env_sample                  # 환경변수 샘플 파일 (.env_sample)
 ├── .gitignore                   # Git 무시 파일 목록
@@ -19,3 +19,15 @@
 
 
 ```
+
+# 빌드(Windows 11 기준)
+```bash
+pyinstaller --onefile `
+  --add-data ".env;.env" `
+  --add-data "conf;conf" `
+  --add-data "lib;lib" `
+  --add-data "data;data" `
+  run.py
+```
+- 환경 변수를 포함하여 빌드하므로 `.env` 파일을 사전에 생성해 두어야 함
+- 동작 확인을 위해 `--noconsloe` 옵션 제거

conf/config.py

@@ -1,4 +1,25 @@
 import os
+import sys
+import time
+from dotenv import load_dotenv
+
+# 프로젝트 루트 기준으로 .env 위치 지정
+BASE_DIR = getattr(sys, '_MEIPASS', os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+ENV_PATH = os.path.join(BASE_DIR, '.env')
+load_dotenv(dotenv_path=ENV_PATH)
+
+# ✅ 타임존 설정
+TZ = os.getenv("TZ", "Asia/Seoul")
+os.environ["TZ"] = TZ
+try:
+    time.tzset()
+except AttributeError:
+    pass
+
+try:
+    time.tzset()
+except AttributeError:
+    pass
 
 def parse_bool(value):
     if isinstance(value, bool):
@@ -17,14 +38,14 @@ MAX_REVIEWS = int(os.getenv("MAX_REVIEWS", "100"))
 NAVER_ID = os.getenv("NAVER_ID", "")
 NAVER_PW = os.getenv("NAVER_PW", "")
 
-MESSAGE_PLATFORMS = parse_list(os.getenv("MESSAGE_PLATFORM", ""))
+MESSAGE_PLATFORMS = parse_list(os.getenv("MESSAGE_PLATFORMS", ""))
 
 MATTERMOST_URL = os.getenv("MATTERMOST_URL", "")
 MATTERMOST_WEBHOOK_URL = os.getenv("MATTERMOST_WEBHOOK_URL", "")
 MATTERMOST_CHANNEL_ID = os.getenv("MATTERMOST_CHANNEL_ID", "")
 MATTERMOST_BOT_TOKEN = os.getenv("MATTERMOST_BOT_TOKEN", "")
 
-SYNology_CHAT_WEBHOOK_URL = os.getenv("SYNology_CHAT_WEBHOOK_URL", "")
+Synology_CHAT_WEBHOOK_URL = os.getenv("Synology_CHAT_WEBHOOK_URL", "")
 
 TELEGRAM_BOT_TOKEN = os.getenv("TELEGRAM_BOT_TOKEN", "")
 TELEGRAM_CHAT_ID = os.getenv("TELEGRAM_CHAT_ID", "")

lib/biz_crawler.py

@@ -1,3 +1,4 @@
+# biz_crawler.py
 import os, sys
 import time
 from datetime import datetime
@@ -13,7 +14,7 @@ from conf.config import (
     MESSAGE_PLATFORMS, MATTERMOST_URL, MATTERMOST_BOT_TOKEN, MATTERMOST_CHANNEL_ID
 )
 from lib.send_message import MessageSender
-from lib.lib import (
+from lib.common import (
     create_mobile_driver,
     save_cookies,
     load_cookies,
@@ -22,6 +23,10 @@ from lib.lib import (
     clean_html_text
 )
 
+def debug(msg):
+    if DEBUG:
+        print(f"[DEBUG] {msg}")
+
 class NaverReviewCollector:
     def __init__(self, headless=HEADLESS):
         self.headless = headless
@@ -41,7 +46,7 @@ class NaverReviewCollector:
         try:
             modal = wait.until(EC.presence_of_element_located((By.ID, "modal-root")))
             modal.find_element(By.XPATH, './/button').click()
-        except:
+        except Exception:
             pass
 
         try:
@@ -49,7 +54,6 @@ class NaverReviewCollector:
             self.driver.find_element(By.ID, 'pw').send_keys(NAVER_PW)
             self.driver.find_element(By.XPATH, '//button[@type="submit"]').click()
         except Exception:
-            self.driver.quit()
             return False
 
         time.sleep(3)
@@ -70,9 +74,32 @@ class NaverReviewCollector:
                 EC.presence_of_element_located((By.XPATH, '//*[starts-with(@class, "Header_btn_select_")]'))
             )
             return el.text.strip()
-        except:
+        except Exception:
             return "알수없음"
 
+    def extract_written_date(self, spans, li):
+        labels = [s.text.strip() for s in spans]
+        try:
+            if "작성일" in labels:
+                idx = labels.index("작성일")
+                return spans[idx + 1].find_element(By.TAG_NAME, "time").text.strip()
+            elif "예약자" in labels:
+                return li.find_element(By.XPATH, ".//div[3]/div[1]/span[2]/time").text.strip()
+        except Exception:
+            return None
+
+    def extract_review_text(self, li):
+        for i in range(4, 7):
+            try:
+                el = li.find_element(By.XPATH, f"./div[{i}]/a")
+                if el:
+                    text = el.text.strip()
+                    return clean_html_text(el.get_attribute("innerHTML")) if text else "내용 없음"
+            except Exception:
+                continue
+        return "내용 없음"
+
+
     def extract_reviews(self):
         reviews = []
         try:
@@ -81,48 +108,34 @@ class NaverReviewCollector:
             )
             lis = self.driver.find_elements(By.XPATH, "//ul[starts-with(@class, 'Review_columns_list')]/li")
             for li in lis:
-                if "Review_banner__" in li.get_attribute("class"):
-                    continue
-
                 try:
+                    if "Review_banner__" in li.get_attribute("class"):
+                        continue
+
                     author = li.find_element(By.XPATH, ".//div[1]/a[2]/div/span/span").text.strip()
                     visit_text = li.find_element(By.XPATH, ".//div[2]/div[1]/span[2]/time").text.strip()
-                    visit_date = datetime.strptime(visit_text.split("(")[0].replace(". ", "-").replace(".", ""), "%Y-%m-%d").strftime("%Y-%m-%d")
+                    visit_date = datetime.strptime(
+                        visit_text.split("(")[0].replace(". ", "-").replace(".", ""), "%Y-%m-%d"
+                    ).strftime("%Y-%m-%d")
 
                     spans = li.find_elements(By.XPATH, ".//div[2]/div[2]/span")
-                    labels = [s.text.strip() for s in spans]
-                    written_text = None
-
-                    if "작성일" in labels:
-                        idx = labels.index("작성일")
-                        written_text = spans[idx + 1].find_element(By.TAG_NAME, "time").text.strip()
-                    elif "예약자" in labels:
-                        try:
-                            written_text = li.find_element(By.XPATH, ".//div[3]/div[1]/span[2]/time").text.strip()
-                        except:
-                            continue
-
+                    written_text = self.extract_written_date(spans, li)
                     if not written_text:
                         continue
 
-                    written_date = datetime.strptime(written_text.split("(")[0].replace(". ", "-").replace(".", ""), "%Y-%m-%d").date()
+                    try:
+                        written_date = datetime.strptime(
+                            written_text.split("(")[0].replace(". ", "-").replace(".", ""), "%Y-%m-%d"
+                        ).date()
+                    except ValueError:
+                        continue
+
                     if not (self.start_date <= written_date <= self.end_date):
                         continue
 
-                    content_el = None
-                    for i in range(4, 7):
-                        try:
-                            el = li.find_element(By.XPATH, f"./div[{i}]/a")
-                            if el and el.text.strip():
-                                content_el = el
-                                break
-                        except:
-                            continue
-                    if content_el is None:
-                        continue
-
-                    html = content_el.get_attribute("innerHTML")
-                    text = clean_html_text(html)
+                    text = self.extract_review_text(li)
+                    #if not text:
+                    #    continue
 
                     reviews.append({
                         "작성자": author,
@@ -130,10 +143,9 @@ class NaverReviewCollector:
                         "작성일": written_date,
                         "내용": text
                     })
-
-                except:
+                except Exception:
                     continue
-        except:
+        except Exception:
             pass
         return reviews
 
@@ -163,9 +175,10 @@ class NaverReviewCollector:
             lines.append("---")
 
         message = "\n".join(lines)
+
         if not MESSAGE_PLATFORMS:
             print("[WARN] 메시지 전송 플랫폼이 지정되지 않음. 미전송")
-            print(f"[DEBUG] {message}")
+            debug(message)
             return
 
         sender = MessageSender(
@@ -175,38 +188,40 @@ class NaverReviewCollector:
         )
 
         if DEBUG:
-            print(f"[DEBUG] message platform : {MESSAGE_PLATFORMS}")
-            print("[DEBUG] 디버그 모드 메시지 미전송")
-            print(f"[DEBUG] {message}")
+            debug(f"메시지 플랫폼: {MESSAGE_PLATFORMS}")
+            debug("디버그 모드: 메시지 전송 생략")
+            debug(message)
         else:
             sender.send(message, platforms=MESSAGE_PLATFORMS, use_webhook=False)
 
     def run(self):
-        self.create_driver()
-        self.driver.get("https://naver.com")
-        time.sleep(1)
+        while True:
+            self.create_driver()
+            self.driver.get("https://naver.com")
+            time.sleep(1)
 
-        if os.path.exists(COOKIE_FILE):
-            try:
-                load_cookies(self.driver, COOKIE_FILE)
-                self.driver.get("https://naver.com")
-                time.sleep(1)
-            except:
-                os.remove(COOKIE_FILE)
+            if os.path.exists(COOKIE_FILE):
+                try:
+                    load_cookies(self.driver, COOKIE_FILE)
+                    self.driver.get("https://naver.com")
+                    time.sleep(1)
+                except Exception:
+                    os.remove(COOKIE_FILE)
+                    self.driver.quit()
+                    self.headless = False
+                    continue
+            else:
+                if self.headless:
+                    self.driver.quit()
+                    self.headless = False
+                    continue
+                if not self.perform_login():
+                    self.driver.quit()
+                    return
                 self.driver.quit()
-                NaverReviewCollector(headless=False).run()
-                return
-        else:
-            if self.headless:
-                self.driver.quit()
-                NaverReviewCollector(headless=False).run()
-                return
-            if not self.perform_login():
-                self.driver.quit()
-                return
-            self.driver.quit()
-            NaverReviewCollector(headless=self.headless).run()
-            return
+                continue
+
+            break  # 쿠키 로딩 또는 로그인 성공 시 루프 종료
 
         for biz_id in BIZ_ID:
             place_name = self.access_review_page(biz_id)
@@ -215,8 +230,8 @@ class NaverReviewCollector:
                 print("[WARN] 세션 만료 또는 쿠키 무효. 로그인 재진행")
                 os.remove(COOKIE_FILE)
                 self.driver.quit()
-                NaverReviewCollector(headless=False).run()
-                return
+                self.headless = False
+                return self.run()
 
             try:
                 reviews = self.extract_reviews()
@@ -228,13 +243,14 @@ class NaverReviewCollector:
                 self.reviews_by_place[place_name] = []
 
         self.driver.quit()
-
+        
         if not self.reviews_by_place:
             sender = MessageSender(
                 mattermost_url=MATTERMOST_URL,
-                mattermost_bot_token=MATTERMOST_BOT_TOKEN,
+                mattermost_token=MATTERMOST_BOT_TOKEN,
                 mattermost_channel_id=MATTERMOST_CHANNEL_ID,
             )
+            
             send_failure_message(sender, MESSAGE_PLATFORMS)
         else:
             self.send_to_message()

lib/common.py

@@ -1,12 +1,11 @@
 # lib/lib.py
 
-import os
-import sys
+import os, sys
 import time
 import pickle
 import re
-from datetime import datetime, timedelta
 import undetected_chromedriver as uc
+from datetime import datetime, timedelta
 from selenium.webdriver.common.by import By
 
 # 공통 설정 경로 추가 (필요 시)

lib/naver_review_crawler.py

@@ -1,3 +1,4 @@
+# naver_review_crawler.py
 import os, sys
 from datetime import datetime
 from selenium.webdriver.common.by import By
@@ -7,11 +8,11 @@ from selenium.webdriver.support import expected_conditions as EC
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
 
 from conf.config import (
-    PLACE_IDS, START_DATE, END_DATE, DEBUG, 
+    PLACE_IDS, START_DATE, END_DATE, DEBUG,
     MESSAGE_PLATFORMS, MATTERMOST_URL, MATTERMOST_BOT_TOKEN, MATTERMOST_CHANNEL_ID
-    )
+)
 from lib.send_message import MessageSender
-from lib.lib import (
+from lib.common import (
     create_mobile_driver,
     get_start_end_dates,
     parse_korean_date,
@@ -21,7 +22,13 @@ from lib.lib import (
     send_failure_message
 )
 
-class NaverReviewMapCollector:
+
+def debug(msg):
+    if DEBUG:
+        print(f"[DEBUG] {msg}")
+
+
+class NaverMapReviewCollector:
     def __init__(self):
         self.driver = None
         self.total_reviews = 0
@@ -30,40 +37,46 @@ class NaverReviewMapCollector:
 
     def extract_reviews(self):
         reviews = []
-        WebDriverWait(self.driver, 10).until(
-            EC.presence_of_element_located((By.ID, "_review_list"))
-        )
-        ul = self.driver.find_element(By.ID, "_review_list")
-        items = ul.find_elements(By.XPATH, './/li[contains(@class, "place_apply_pui")]')
-        for item in items:
-            try:
-                writer = "익명"
-                try:
-                    writer = item.find_element(By.XPATH, "./div[1]/a[2]/div/span/span").text.strip()
-                except:
-                    pass
+        try:
+            WebDriverWait(self.driver, 10).until(
+                EC.presence_of_element_located((By.ID, "_review_list"))
+            )
+            ul = self.driver.find_element(By.ID, "_review_list")
+            items = ul.find_elements(By.XPATH, './/li[contains(@class, "place_apply_pui")]')
 
-                date_obj = None
+            for item in items:
                 try:
-                    date_text = item.find_element(By.XPATH, "./div[7]/div[2]/div/span[1]/span[2]").text.strip()
-                    date_obj = parse_korean_date(date_text)
-                except:
-                    continue
+                    writer = "익명"
+                    try:
+                        writer = item.find_element(By.XPATH, "./div[1]/a[2]/div/span/span").text.strip()
+                    except Exception:
+                        pass
 
-                text = ""
-                try:
-                    text = item.find_element(By.XPATH, "./div[5]/a").get_attribute("innerHTML")
-                except:
-                    continue
+                    try:
+                        date_text = item.find_element(By.XPATH, "./div[7]/div[2]/div/span[1]/span[2]").text.strip()
+                        date_obj = parse_korean_date(date_text)
+                    except Exception:
+                        continue
+
+                    if not (self.start_date <= date_obj <= self.end_date):
+                        continue
+
+                    try:
+                        text_html = item.find_element(By.XPATH, "./div[5]/a").get_attribute("innerHTML")
+                        content = clean_html_text(text_html)
+                    except Exception:
+                        continue
 
-                if date_obj and (self.start_date <= date_obj <= self.end_date):
                     reviews.append({
                         "작성자": writer,
                         "작성일": date_obj,
-                        "내용": clean_html_text(text)
+                        "내용": content
                     })
-            except Exception as e:
-                print(f"[WARN] 리뷰 추출 실패: {e}")
+
+                except Exception as e:
+                    debug(f"[WARN] 리뷰 항목 처리 중 오류: {e}")
+        except Exception as e:
+            debug(f"[ERROR] 리뷰 리스트 접근 실패: {e}")
         return reviews
 
     def send_to_message(self):
@@ -91,9 +104,10 @@ class NaverReviewMapCollector:
             lines.append("---")
 
         message = "\n".join(lines)
+
         if not MESSAGE_PLATFORMS:
-            print("[WARN] 메시지 전송 플랫폼 없음")
-            print(f"[DEBUG] {message}")
+            print("[WARN] 메시지 전송 플랫폼이 지정되지 않음")
+            debug(message)
             return
 
         sender = MessageSender(
@@ -103,8 +117,8 @@ class NaverReviewMapCollector:
         )
 
         if DEBUG:
-            print("[DEBUG] 디버그 모드로 메시지 미전송")
-            print(message)
+            debug("디버그 모드로 메시지 전송 생략")
+            debug(message)
         else:
             sender.send(message, platforms=MESSAGE_PLATFORMS, use_webhook=False)
 
@@ -114,10 +128,15 @@ class NaverReviewMapCollector:
         for place_id in PLACE_IDS:
             url = f"https://m.place.naver.com/place/{place_id}/review/visitor?reviewSort=recent"
             print(f"[INFO] 접근: {url}")
-            self.driver.get(url)
-            shop_name = extract_shop_name(self.driver)
+            try:
+                self.driver.get(url)
+                shop_name = extract_shop_name(self.driver)
+            except Exception as e:
+                print(f"[ERROR] {place_id} 매장 접근 오류: {e}")
+                continue
+
             all_reviews = []
-            seen = set()
+            seen = set()  # (작성자, 작성일, 내용) 기준으로 중복 제거
 
             while True:
                 new_reviews = self.extract_reviews()
@@ -135,6 +154,7 @@ class NaverReviewMapCollector:
                     break
 
                 all_reviews.extend(filtered)
+
                 if not click_more(self.driver):
                     break
 
@@ -154,6 +174,7 @@ class NaverReviewMapCollector:
         else:
             self.send_to_message()
 
+
 if __name__ == "__main__":
-    collector = NaverReviewMapCollector()
+    collector = NaverMapReviewCollector()
     collector.run()

lib/send_message.py

@@ -1,3 +1,4 @@
+# send_message.py
 import requests
 
 class MessageSender:

naver_review_bot.bat

@@ -0,0 +1,2 @@
+@echo off
+python C:\DEV\python\fg-auto\naver_review\run.py

requirements.txt

@@ -0,0 +1,4 @@
+selenium
+requests
+undetected_chromedriver
+dotenv

run.py

@@ -1,28 +1,27 @@
-import os
-import sys
-from dotenv import load_dotenv
-
-
-# 환경 변수 로드
-load_dotenv()
-
+# run.py
+import os, sys
 # 프로젝트 루트 기준 경로 추가
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), 'lib')))
 
-# 실행 모드 확인
-mode = os.getenv("MODE", "").strip().lower()
+from conf import config
 
-if mode == "biz":
-    from lib.biz_crawler import NaverReviewCollector
-    print("[INFO] 비즈니스 리뷰 수집기 실행")
-    collector = NaverReviewCollector()
-    collector.run()
+def main():
+    mode = os.getenv("MODE", "").strip().lower()
 
-elif mode == "map":
-    from lib.naver_review_crawler import NaverMapReviewCollector
-    print("[INFO] 지도 리뷰 수집기 실행")
-    collector = NaverMapReviewCollector()
-    collector.run()
+    if mode == "biz":
+        from lib.biz_crawler import NaverReviewCollector
+        print("[INFO] 비즈니스 리뷰 수집기 실행")
+        collector = NaverReviewCollector()
+        collector.run()
 
-else:
-    print("[ERROR] .env 파일에서 MODE 값을 설정해주세요. (biz 또는 map)")
+    elif mode == "map":
+        from lib.naver_review_crawler import NaverMapReviewCollector
+        print("[INFO] 지도 리뷰 수집기 실행")
+        collector = NaverMapReviewCollector()
+        collector.run()
+
+    else:
+        print(f"[ERROR] .env 파일에서 MODE 값을 설정해주세요. (biz 또는 map) 현재값: '{mode}'")
+
+if __name__ == "__main__":
+    main()