2024.12.07. [파이썬] 네이버 지도 크롤링

https://cafe.naver.com/startcodingofficial/1458

끝이라 생각하고 답글 쓴지.. 2시간 반만에 다시 올립니다!!🫡

 

GUI를 제외하고,
오류도 수두룩하게 많아
가장 많이 생각하고, 고민해야했던 네이버지도 크롤링

작업 시간 : 약 8시간 🤪

search = input('검색어')
count = int(input('몇 개 추출?')) + 1

url = f'https://map.naver.com/p/search/{search}'

driver = webdriver.Chrome()
driver.maximize_window()
driver.get(url)
time.sleep(1)

result = []

try:    # 별점 있을때 !!!
    #  기본 프레임 이동했다가~
    driver.switch_to.default_content()
    time.sleep(1)
    # iframe 변경 (A 라는 영역?)
    driver.switch_to.frame('searchIframe')
    time.sleep(2)

    # 별점 있는지 확인 > 없으면 except로 넘어가기
    driver.find_element(By.CSS_SELECTOR, 'span.h69bs.orXYY')

    # 광고 개수 확인
    ad_count = len(driver.find_elements(By.CSS_SELECTOR, '#_pcmap_list_scroll_container > ul > li.UEzoS.rTjJo.cZnHG'))
    new_count = ad_count + count
    
    for i in range (1, new_count):
        #  기본 프레임 이동했다가~
        driver.switch_to.default_content()
        time.sleep(1)

        # iframe 변경 (A 라는 영역?)
        driver.switch_to.frame('searchIframe')
        time.sleep(2)
        
        try:
            # i 번째 업체명 클릭 및 추출
            element= driver.find_element(By.CSS_SELECTOR, f'#_pcmap_list_scroll_container > ul > li.UEzoS.rTjJo:not(.cZnHG):nth-of-type({i}) > div:nth-of-type(1) > a > div > div')
            element.click()
            driver.execute_script("arguments[0].scrollIntoView();", element) #스크롤
            com = driver.find_element(By.CSS_SELECTOR, f'#_pcmap_list_scroll_container > ul > li:nth-of-type({i}) div.place_bluelink > span:nth-of-type(1)').text
            time.sleep(1)

            #  기본 프레임 이동했다가~
            driver.switch_to.default_content()
            time.sleep(1)

            # iframe 변경 (B 라는 영역?)
            driver.switch_to.frame('entryIframe')
            time.sleep(2)

            # 정보 추출
            try:
                sector = driver.find_element(By.CSS_SELECTOR, '#_title > div > span.lnJFt').text
            except:
                sector = ''
            try:
                addr = driver.find_element(By.CSS_SELECTOR, 'div.place_section_content .LDgIH').text
            except:
                addr = ''
            try :
                phone = driver.find_element(By.CSS_SELECTOR, 'div.place_section_content .xlx7Q').text
            except:
                phone = ''
            try:
                homepage = driver.find_element(By.CSS_SELECTOR, 'div.place_section_content div.jO09N > a').get_attribute('href')
            except:
                homepage =''
        except:
            pass
        finally:
            result.append([com, sector, addr, phone, homepage])
            time.sleep(1)

except:    # 별점 없을때 !!!
    #  기본 프레임 이동했다가~
    driver.switch_to.default_content()
    time.sleep(1)
    # iframe 변경 (A 라는 영역?)
    driver.switch_to.frame('searchIframe')
    time.sleep(2)

    # 5개 설정
    for i in range (1, count):
        #  기본 프레임 이동했다가~
        driver.switch_to.default_content()
        time.sleep(1)

        # iframe 변경 (A 라는 영역?)
        driver.switch_to.frame('searchIframe')
        time.sleep(2)

        # i 번째 업체명 클릭 및 업체명 추출
        element = driver.find_element(By.CSS_SELECTOR, f'#_pcmap_list_scroll_container > ul > li:nth-of-type({i}) .place_bluelink')
        element.click()
        driver.execute_script("arguments[0].scrollIntoView();", element) #스크롤
        com =  driver.find_element(By.CSS_SELECTOR, f'#_pcmap_list_scroll_container > ul > li:nth-of-type({i}) .place_bluelink > span').text
        sector = driver.find_element(By.CSS_SELECTOR, f'#_pcmap_list_scroll_container > ul > li:nth-of-type({i}) div.place_bluelink > span.YzBgS').text

        # 주소 추출
        driver.find_element(By.CSS_SELECTOR, f'#_pcmap_list_scroll_container > ul > li:nth-of-type({i}) span._44_8').click()
        addr = driver.find_element(By.CSS_SELECTOR, f'.zZfO1').text.split('도로명')[1].split('복사')[0]
        driver.find_element(By.CSS_SELECTOR, f'#_pcmap_list_scroll_container > ul > li:nth-of-type({i}) span._44_8').click()
        time.sleep(2)

        #  기본 프레임 이동했다가~
        driver.switch_to.default_content()
        time.sleep(1)

        # 다시 iframe 영역 (B 라는 영역?)
        driver.switch_to.frame('entryIframe')
        time.sleep(1)

        # 업체 정보 추출
        try:
            phone = driver.find_element(By.CSS_SELECTOR, '.O8qbU.nbXkr > div > span.xlx7Q').text
        except :
            try :
                phone = driver.find_element(By.CSS_SELECTOR, 'span.txt_tel').text
            except:
                try :
                    phone = driver.find_element(By.CSS_SELECTOR, 'div.FEtx4c2oAJQ4yTWSktTy > span:nth-of-type(2)').text
                except :
                    phone =''
        try:
            homepage = driver.find_element(By.CSS_SELECTOR, 'div.O8qbU.yIPfO > div > div.jO09N > a').get_attribute('href')
        except:
            homepage = ''
        result.append([com, sector, addr, phone, homepage])
        time.sleep(1)

df = pd.DataFrame(result, columns=['업체명','업종','주소','전화번호','홈페이지'])
df.to_excel(f'{search}.xlsx')