과제 여러개 파일 수집 (2024-05-22)

!pip install chromedriver_autoinstaller
import time
from selenium import webdriver
from selenium.webdriver.common.keys import By
from selenium.webdriver.common.keys import Keys
from urllib.request import Request, urlopen


def crawl_and_save_image(keyword, pages):
    image_urls = []
	
    // 다음페이지 설정
    for i in range(1, pages+1):
        url = f'https://pixabay.com/ko/images/search/{keyword}/?pagi={i}'
        driver.get(url)
        time.sleep(2)

        for _ in range(20):
            driver.execute_script("window.scrollBy({ top: window.innerHeight, behavior: 'smooth' })")
            time.sleep(1)

        image_area_xpath = '/html/body/div[1]/div[1]/div/div[2]/div[3]'
        image_area = driver.find_element(By.XPATH, image_area_xpath)
        image_elements = image_area.find_elements(By.TAG_NAME, 'img')

        for image_element in image_elements:
            image_url = image_element.get_attribute('src')
            print(image_url)
            image_urls.append(image_url)
	
    // keyword명으로 파일이 없다면 생성
    if not os.path.exists(keyword):
        os.mkdir(keyword)

    for i in range(len(image_urls)):
        image_url = image_urls[i]
        url = parse.urlparse(image_url)
        filename = image_url.split('/')[-1]
        image_byte = Request(image_url, headers= {'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'})
        f = open(f'{keyword}/{filename}', 'wb')
        f.write(urlopen(image_byte).read())
        f.close()
        
        
// 함수 실행
driver = webdriver.Chrome()
crawl_and_save_image('고양이',2)