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

relese

Browse Source
This commit is contained in:
KWON
2025-07-03 11:42:21 +09:00
parent fc3491e62c
commit 57ad944ccb
1 changed files with 109 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

166
naver_review/main.py
View File

@ -4,115 +4,167 @@ from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from datetime import datetime
import config
import time
import config # 사용자 설정 파일
# ───────────────────────────────────────────────────────
# ✅ WebDriver 설정 (모바일 User-Agent 포함, 헤드리스 옵션 가능)
# ───────────────────────────────────────────────────────
def setup_driver():
chrome_options = Options()
chrome_options.add_argument("--headless=new")
chrome_options.add_argument("--headless=new") # 필요 시 주석 해제
chrome_options.add_argument("--no-sandbox")
chrome_options.add_argument("--disable-dev-shm-usage")
chrome_options.add_argument(
"--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 click_more(driver):
# ───────────────────────────────────────────────────────
# ✅ 날짜 문자열 파싱 함수 (예: '2025년 6월 8일 일요일')
# ───────────────────────────────────────────────────────
def parse_korean_date(date_str):
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:
# '2025년 6월 8일 일요일' → '2025년 6월 8일'
date_clean = " ".join(date_str.strip().split(" ")[:3])
return datetime.strptime(date_clean, "%Y년 %m월 %d일").date()
except Exception as e:
print(f"[WARN] 날짜 파싱 실패: {date_str} ({e})")
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):
# ───────────────────────────────────────────────────────
# ✅ "더보기" 버튼 클릭 함수 (한 번만 클릭)
# ───────────────────────────────────────────────────────
def click_more(driver):
try:
title_div = driver.find_element(By.ID, "_title")
name = title_div.find_element(By.XPATH, './div[1]/span').text.strip()
container = driver.find_element(By.CLASS_NAME, "place_section_content")
more_div = container.find_element(By.XPATH, "./following-sibling::div[1]")
more_btn = more_div.find_element(By.TAG_NAME, "a")
driver.execute_script("arguments[0].click();", more_btn)
print("[INFO] 더보기 클릭")
time.sleep(2)
return True
except:
print("[INFO] 더보기 없음")
return False
# ───────────────────────────────────────────────────────
# ✅ 업체명 추출 함수 (페이지 상단의 "_title" ID 활용)
# ───────────────────────────────────────────────────────
def extract_shop_name(driver):
try:
main = driver.find_element(By.CSS_SELECTOR, 'div[role="main"]')
title = main.find_element(By.ID, "_title")
name = title.find_element(By.TAG_NAME, "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()
driver.get(url)
# ───────────────────────────────────────────────────────
# ✅ 리뷰 추출 함수: 작성자 / 날짜 / 본문
# ───────────────────────────────────────────────────────
def extract_reviews(driver):
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
# ① 작성자: ./div[1]/a[2]/div/span/span
writer = "익명"
try:
writer = item.find_element(By.XPATH, './div[1]/a[2]/div/span/span').text.strip()
writer = item.find_element(By.XPATH, "./div[1]/a[2]/div/span/span").text.strip()
except:
pass
# 작성일
date = ""
# ② 날짜: ./div[7]/div[2]/div/span[1]/span[2]
date = "날짜 없음"
date_obj = None
try:
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", "")
date_text = item.find_element(By.XPATH, "./div[7]/div[2]/div/span[1]/span[2]").text.strip()
date = date_text
date_obj = parse_korean_date(date_text)
except:
continue
pass
if not is_within_range(date, start_date, end_date):
continue
# 리뷰 본문
# ③ 본문: ./div[5]/a
text = ""
try:
text = item.find_element(By.XPATH, './div[5]/a').text.strip()
text = item.find_element(By.XPATH, "./div[5]/a").text.strip()
except:
continue
pass
if text:
reviews.append({
"writer": writer,
"date": date,
"date_obj": date_obj,
"text": text
})
if len(reviews) >= max_reviews:
break
except Exception as e:
print(f"[WARN] 리뷰 파싱 실패: {e}")
print(f"[WARN] 리뷰 추출 실패: {e}")
return reviews
# ───────────────────────────────────────────────────────
# ✅ 특정 기간 내 리뷰 수집 함수 (날짜 필터 + 더보기 반복)
# ───────────────────────────────────────────────────────
def crawl_reviews_within_range(place_id, 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)
shop_name = extract_shop_name(driver)
all_reviews = []
seen = set()
while True:
new_reviews = extract_reviews(driver)
if not new_reviews:
break
filtered = []
for r in new_reviews:
if r["date_obj"] is None:
continue
if start_date <= r["date_obj"] <= end_date:
key = (r["writer"], r["date_obj"], r["text"])
if key not in seen:
seen.add(key)
filtered.append(r)
if not filtered:
print("[INFO] 범위 내 리뷰 없음 → 수집 종료")
break
all_reviews.extend(filtered)
# 더 클릭할 필요가 없으면 종료
if not click_more(driver):
break
driver.quit()
print(f"[DONE] {place_name} ({place_id}) → 총 {len(reviews)}개 리뷰 수집")
return place_name, reviews
print(f"[DONE] [{shop_name}] {len(all_reviews)}개 리뷰 수집 완료")
return shop_name, all_reviews
# ───────────────────────────────────────────────────────
# ✅ 메인 실행부
# ───────────────────────────────────────────────────────
if __name__ == "__main__":
start_dt = datetime.strptime(config.START_DATE, "%Y-%m-%d")
end_dt = datetime.strptime(config.END_DATE, "%Y-%m-%d")
start_date = datetime.strptime(config.START_DATE, "%Y-%m-%d").date()
end_date = datetime.strptime(config.END_DATE, "%Y-%m-%d").date()
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):
shop, reviews = crawl_reviews_within_range(place_id, start_date, end_date)
print(f"\n==== {shop} ({place_id}) 리뷰 목록 ====")
for i, r in enumerate(reviews, 1):
print(f"{i}. 작성자: {r['writer']}, 날짜: {r['date']}")
print(f" 내용: {r['text']}\n")