Notes

import os
import time
import openpyxl

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.support.ui import WebDriverWait


# =====================================
# 파일명 중복 방지
# =====================================

def get_unique_filename(base_name):

if not os.path.exists(base_name):
return base_name

name, ext = os.path.splitext(base_name)

num = 1

while True:

new_name = f"{name}_{num}{ext}"

if not os.path.exists(new_name):
return new_name

num += 1


# =====================================
# 상세페이지 정보 추출
# =====================================

def extract_ssg_info(driver):

sale_price = ""
coupon_info = ""
main_product = ""
gift_product = ""

try:

driver.switch_to.default_content()

# ==========================
# 판매가
# ==========================

try:

sale_price = driver.find_element(
By.CSS_SELECTOR,
".cdtl_new_price em.ssg_price"
).text.strip()

except:
pass

# ==========================
# 쿠폰
# ==========================

try:

coupon_info = driver.find_element(
By.CSS_SELECTOR,
".cdtl_benefit_coupon p.txt"
).text.strip()

except:
pass

# ==========================
# 상세설명 iframe 진입
# ==========================

try:

iframe = driver.find_element(
By.ID,
"_ifr_html"
)

driver.switch_to.frame(iframe)

except:

return (
sale_price,
coupon_info,
"",
""
)

# ==========================
# descContents 파싱
# ==========================

try:

text = driver.find_element(
By.ID,
"descContents"
).text

except:

try:

text = driver.find_element(
By.TAG_NAME,
"body"
).text

except:

text = ""

lines = []

for line in text.split("n"):

line = line.strip()

if line:
lines.append(line)

# ==========================
# 본품 / 추가증정 파싱
# ==========================

MAIN_START = [
"[본품]"
]

MAIN_EXTRA = [
"[내장]"
]

GIFT_START = [
"[추가증정]",
"[추가구성]",
"[증정]",
"[사은품]",
"[gift]"
]

END_KEYWORDS = [
"[상품상세]",
"[상세정보]",
"[상품정보]",
"상품정보 제공고시",
"※ 제품 이미지는",
"※ 구성품은",
"※ 사은품은",
"교환 및 반품",
"배송안내"
]

main_items = []
gift_items = []

mode = None

for line in lines:

lower_line = line.lower()

# --------------------------
# 본품 시작
# --------------------------

if any(
key.lower() in lower_line
for key in MAIN_START
):

mode = "main"
continue

# --------------------------
# 내장도 본품으로 처리
# --------------------------

if any(
key.lower() in lower_line
for key in MAIN_EXTRA
):

mode = "main"
continue

# --------------------------
# 추가증정 시작
# --------------------------

if any(
key.lower() in lower_line
for key in GIFT_START
):

mode = "gift"
continue

# --------------------------
# 종료 조건
# --------------------------

if any(
key.lower() in lower_line
for key in END_KEYWORDS
):

mode = None
break

# --------------------------
# 수집
# --------------------------

if mode == "main":

if len(line) > 1:
main_items.append(line)

elif mode == "gift":

if len(line) > 1:
gift_items.append(line)

# ==========================
# 중복 제거
# ==========================

main_items = list(
dict.fromkeys(main_items)
)

gift_items = list(
dict.fromkeys(gift_items)
)

# ==========================
# 최종 문자열
# ==========================

main_product = " + ".join(
main_items
)

gift_product = " + ".join(
gift_items
)

driver.switch_to.default_content()

return (
sale_price,
coupon_info,
main_product,
gift_product
)

except Exception as e:

print("상세 추출 실패:", e)

try:
driver.switch_to.default_content()
except:
pass

return (
sale_price,
coupon_info,
"",
""
)

# =====================================
# URL 입력
# =====================================

url = input(
"목록 페이지 URL 입력 : "
).strip()

if not url.startswith("http"):
url = "https://" + url


# =====================================
# 크롬 실행
# =====================================

options = webdriver.ChromeOptions()

options.add_argument(
"--disable-blink-features=AutomationControlled"
)

options.add_experimental_option(
"excludeSwitches",
["enable-automation"]
)

options.add_experimental_option(
"useAutomationExtension",
False
)

driver = webdriver.Chrome(
service=Service("chromedriver.exe"),
options=options
)

driver.get(url)

print()
print("=" * 60)
print("정렬 / 필터 설정 후 엔터")
print("=" * 60)

input()

time.sleep(2)


# =====================================
# 상품 수집 (범용 버전)
# =====================================

products = []

print()
print("=" * 50)
print("상품명 CSS 선택자 입력")
print("예시")
print(".css-1r5pe50")
print(".mnsditem_goods_tit")
print(".ssgitem_tit_name")
print("=" * 50)

product_selector = input(
"상품명 선택자 : "
).strip()

if not product_selector:
product_selector = ".css-1r5pe50"

links = driver.find_elements(
By.TAG_NAME,
"a"
)

for link in links:

try:

href = link.get_attribute(
"href"
)

if not href:
continue

if href.startswith(
"javascript"
):
continue

names = link.find_elements(
By.CSS_SELECTOR,
product_selector
)

if not names:
continue

product_name = (
names[0]
.text
.strip()
)

if not product_name:
continue

products.append(
(
href,
product_name
)
)

except:
pass

# =====================================
# 추가 수집 (상품명 자체가 a 밖에 있는 경우)
# =====================================

try:

name_elements = driver.find_elements(
By.CSS_SELECTOR,
product_selector
)

for elem in name_elements:

try:

product_name = (
elem.text
.strip()
)

if not product_name:
continue

parent = elem

href = ""

for _ in range(10):

try:

href = parent.get_attribute(
"href"
)

if href:
break

except:
pass

try:

parent = parent.find_element(
By.XPATH,
".."
)

except:
break

if not href:
continue

if href.startswith(
"javascript"
):
continue

products.append(
(
href,
product_name
)
)

except:
pass

except:
pass

# =====================================
# 중복 제거
# =====================================

seen = set()

unique_products = []

for href, name in products:

key = (
href.strip(),
name.strip()
)

if key in seen:
continue

seen.add(key)

unique_products.append(
(
href,
name
)
)

print()
print(
f"총 {len(unique_products)}개 발견"
)
print()
# =====================================
# 상세 수집
# =====================================

results = []

for idx, (
product_url,
product_name
) in enumerate(
unique_products,
start=1
):

try:

print(
f"[{idx}/{len(unique_products)}] "
f"{product_name}"
)

driver.execute_script(
"window.open(arguments[0]);",
product_url
)

driver.switch_to.window(
driver.window_handles[-1]
)

# 봇 방지용
time.sleep(5)

WebDriverWait(
driver,
20
).until(
lambda d:
d.execute_script(
"return document.readyState"
) == "complete"
)

sale_price = ""
coupon_info = ""
main_product = ""
gift_product = ""

for _ in range(10):

(
sale_price,
coupon_info,
main_product,
gift_product
) = extract_ssg_info(
driver
)

if (
sale_price
or coupon_info
or main_product
or gift_product
):
break

time.sleep(1)

print("판매가 :", sale_price)

if coupon_info:
print("쿠폰 :", coupon_info[:60])

if main_product:
print("본품 :", main_product[:60])

if gift_product:
print("추가증정 :", gift_product[:60])

results.append(
[
product_url,
product_name,
sale_price,
coupon_info,
main_product,
gift_product
]
)

driver.close()

driver.switch_to.window(
driver.window_handles[0]
)

except Exception as e:

print(
"오류:",
e
)

try:
driver.close()
except:
pass

try:
driver.switch_to.window(
driver.window_handles[0]
)
except:
pass


# =====================================
# 엑셀 저장
# =====================================

wb = openpyxl.Workbook()

ws = wb.active

ws.title = "Products"

headers = [
"URL",
"상품명",
"판매가",
"쿠폰정보",
"본품",
"추가증정"
]

for col, header in enumerate(
headers,
start=1
):

ws.cell(
row=1,
column=col,
value=header
)

for row, item in enumerate(
results,
start=2
):

for col, value in enumerate(
item,
start=1
):

ws.cell(
row=row,
column=col,
value=value
)

ws.column_dimensions["A"].width = 90
ws.column_dimensions["B"].width = 50
ws.column_dimensions["C"].width = 15
ws.column_dimensions["D"].width = 80
ws.column_dimensions["E"].width = 80
ws.column_dimensions["F"].width = 120

filename = get_unique_filename(
"products.xlsx"
)

wb.save(filename)

print()
print("=" * 60)
print("저장 완료")
print(filename)
print("=" * 60)

driver.quit()

input(
"n엔터 누르면 종료..."
)