crawler_app.py

from selenium import webdriver
from selenium.webdriver.common.by import By
import time
import urllib.request
import os

def makedirs(path): 
	try: 
		os.makedirs(path) 
	except OSError: 
		if not os.path.isdir(path): 
  			raise

            
print("hello world!")

search=input("What crawled do you want?\t")
number=int(input(f"How many crawled {search}s do you want?\t"))
foldername='./Crawled_image/'+search+'/'
filename=search+'_image'
interval=0.5

chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--no-sandbox')
chrome_options.add_argument("--single-process")
chrome_options.add_argument("--disable-dev-shm-usage")
path='./chromedriver'
driver = webdriver.Chrome(path, chrome_options=chrome_options)

driver.get(f'https://www.google.com/search?q=a+{search}&tbm=isch&tbs=il:ol&rlz=1C1CHZN_koKR1016KR1016&hl=ko&sa=X&ved=0CAAQ1vwEahcKEwjw-_SOuI_7AhUAAAAAHQAAAAAQAg&biw=941&bih=942')
firstImage=driver.find_element(By.CSS_SELECTOR,'#islrg > div.islrc > div:nth-child(2) > a.wXeWr.islib.nfEiy > div.bRMDJf.islir > img')
firstImage.click()

makedirs(foldername)
 
for i in range(number):
    try:
        time.sleep(interval)
        image=driver.find_element(By.CSS_SELECTOR,'#Sva75c > div > div > div.pxAole > div.tvh9oe.BIB1wf > c-wiz > div > div.OUZ5W > div.zjoqD > div.qdnLaf.isv-id.b0vFpe > div > a > img')
        imageSrc=image.get_attribute('src')
        such_filename=f'{filename}_{i+1}.jpg'
        image_path = foldername + such_filename
        #print(image_path)
        urllib.request.urlretrieve(imageSrc,image_path)
        
    except:
        print(such_filename+'\t\t실패')
        
    else:
        print(such_filename+'\t\t저장')
    
    finally:
        nextButton=driver.find_element(By.CSS_SELECTOR,'#Sva75c > div > div > div.pxAole > div.tvh9oe.BIB1wf > c-wiz > div > div.OUZ5W > div.zjoqD > div.mWagE.fDqwl > a:nth-child(4)')
        nextButton.click()



driver.quit()
print("bye world!")