firstgarden/fg-auto
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

여러 업체를 불러올 수 있도록 수정, 날싸 범위 설정 기능 추가.

Browse Source
This commit is contained in:
KWON
2025-07-03 11:25:34 +09:00
parent 493178f19f
commit fc3491e62c
2 changed files with 65 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
naver_review/config.sample.py
View File

@ -1,3 +1,5 @@
# config.py
PLACE_ID = "네이버 플레이스 ID" # 네이버 플레이스 ID
MAX_REVIEWS = 30 # 수집할 최대 리뷰 수
PLACE_IDS = ["플레이스 ID 1", "플레이스 ID 2"] # 여러 플레이스 ID 가능
MAX_REVIEWS = 100 # 각 플레이스당 최대 수집 수
START_DATE = "2025-07-01" # 필터링 시작일
END_DATE = "2025-07-03" # 필터링 종료일

85
naver_review/main.py
View File

@ -3,11 +3,11 @@ from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import config # config.py에서 PLACE_ID, MAX_REVIEWS를 불러옴
from datetime import datetime
import config
def setup_driver():
chrome_options = Options()
# 헤드리스 모드 필요하면 아래 주석 해제
chrome_options.add_argument("--headless=new")
chrome_options.add_argument("--no-sandbox")
chrome_options.add_argument("--disable-dev-shm-usage")
@ -15,42 +15,80 @@ def setup_driver():
"--user-agent=Mozilla/5.0 (iPhone; CPU iPhone OS 13_5 like Mac OS X) "
"AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.1.1 Mobile/15E148 Safari/604.1"
)
print("[INFO] Chrome WebDriver 실행 중...")
return webdriver.Chrome(options=chrome_options)
def crawl_naver_place_reviews(place_id, max_reviews=50):
def click_more(driver):
try:
wait = WebDriverWait(driver, 5)
more_btn = wait.until(EC.element_to_be_clickable((
By.XPATH, '//div[contains(@class, "place_section_content")]/following-sibling::div//a[.//span[text()="더보기"]]')))
driver.execute_script("arguments[0].click();", more_btn)
print("[INFO] '더보기' 버튼 클릭됨")
except Exception:
print("[INFO] '더보기' 버튼 없음 또는 클릭 실패")
def parse_date(date_str):
try:
return datetime.strptime(date_str.replace(".", "-"), "%Y-%m-%d")
except Exception:
return None
def is_within_range(date_str, start, end):
d = parse_date(date_str)
if not d:
return False
return start <= d <= end
def get_place_name(driver):
try:
title_div = driver.find_element(By.ID, "_title")
name = title_div.find_element(By.XPATH, './div[1]/span').text.strip()
return name
except Exception as e:
print(f"[WARN] 업체명 추출 실패: {e}")
return "업체명 없음"
def crawl_naver_place_reviews(place_id, max_reviews, start_date, end_date):
url = f"https://m.place.naver.com/place/{place_id}/review/visitor?reviewSort=recent"
driver = setup_driver()
print(f"[INFO] 리뷰 페이지 접속: {url}")
driver.get(url)
wait = WebDriverWait(driver, 10)
wait.until(EC.presence_of_element_located((By.ID, "_review_list")))
place_name = get_place_name(driver)
click_more(driver)
ul = driver.find_element(By.ID, "_review_list")
items = ul.find_elements(By.XPATH, './/li[contains(@class, "place_apply_pui")]')
reviews = []
for item in items:
try:
# 작성자
writer = "익명"
try:
writer = item.find_element(By.XPATH, './div[1]/a[2]/div[1]/span/span').text.strip()
writer = item.find_element(By.XPATH, './div[1]/a[2]/div/span/span').text.strip()
except:
writer = "익명"
pass
# 날짜 (요청하신 정확한 위치)
# 작성일
date = ""
try:
date = item.find_element(By.XPATH, './div[7]/div[2]/div/span[1]/span[2]').text.strip()
date_elem = item.find_element(By.XPATH, './div[7]/div[2]/div/span[1]/span[2]')
date = date_elem.text.strip().replace(" ", "").replace("년", "-").replace("월", "-").replace("일", "")
except:
date = "날짜 없음"
continue
if not is_within_range(date, start_date, end_date):
continue
# 리뷰 본문
text = ""
try:
text = item.find_element(By.XPATH, './div[5]/a').text.strip()
except:
text = ""
continue
if text:
reviews.append({
@ -62,20 +100,19 @@ def crawl_naver_place_reviews(place_id, max_reviews=50):
if len(reviews) >= max_reviews:
break
except Exception as e:
print(f"[WARN] 리뷰 추출 실패: {e}")
print(f"[WARN] 리뷰 파싱 실패: {e}")
driver.quit()
print(f"[DONE] 총 {len(reviews)}개 리뷰 수집 완료")
return reviews
print(f"[DONE] {place_name} ({place_id}) → 총 {len(reviews)}개 리뷰 수집")
return place_name, reviews
if __name__ == "__main__":
result = crawl_naver_place_reviews(config.PLACE_ID, config.MAX_REVIEWS)
start_dt = datetime.strptime(config.START_DATE, "%Y-%m-%d")
end_dt = datetime.strptime(config.END_DATE, "%Y-%m-%d")
print("\n==== [리뷰 목록] ====")
for i, r in enumerate(result, 1):
print(f"{i}. 작성자: {r['writer']}, 날짜: {r['date']}")
print(f" 내용: {r['text']}\n")
for place_id in config.PLACE_IDS:
place_name, result = crawl_naver_place_reviews(place_id, config.MAX_REVIEWS, start_dt, end_dt)
print(f"\n==== [업체명: {place_name}] ====")
for i, r in enumerate(result, 1):
print(f"{i}. 작성자: {r['writer']}, 날짜: {r['date']}")
print(f" 내용: {r['text']}\n")