이곳저곳 이미지 썸네일 크롤러

구글

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
import urllib.request
from selenium.webdriver.common.by import By
 
 
chromedriver = "크롬 드라이버 경로"     
driver = webdriver.Chrome(chromedriver)
driver.implicitly_wait(1)
 
img_name = "저장할 이미지 이름"     # 저장할 이미지 이름
driver.get("구글 이미지 검색 url")
# 구글 검색 이미지 링크
save_path = "이미지 저장 경로"       # 이미지 저장 위치
 
element = driver.find_element(By.TAG_NAME, "body")
 
temp = 0
while True:
    for _ in range(100):    # 뭔가 중간에 끝나는 것 같으면 100씩 올려봅시다
        element.send_keys(Keys.PAGE_DOWN)
    time.sleep(0.1)
    try:
        driver.find_element(By.XPATH, "/html/body/div[2]/c-wiz/div[3]/div[1]/div/div/div/div[1]/div[2]/div[2]/input").click()
    except:
        break
 
links = []
images = driver.find_elements(By.CSS_SELECTOR, "img.rg_i.Q4LuWd")
for image in images:
    if image.get_attribute("src") != None:
        links.append(image.get_attribute("src"))
 
time.sleep(2)
 
for idx, link in enumerate(links):
    urllib.request.urlretrieve(link, str(save_path) + str(img_name) + str(idx) + ".jpg")
 
driver.close()

 

 

네이버

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import urllib.request
from selenium.webdriver.common.by import By
from keras.utils.image_utils import load_img
import time
 
chromedriver = "크롬 드라이버 경로"     # 크롬 드라이버 위치
img_name = "검색 키워드"     # 검색 키워드
save_path = "이미지 저장 위치"       # 이미지 저장 위치
img_width = 256     # output사이즈(픽셀)
img_height = 256
scroll_num = 30     # 스크롤 횟수
 
 
driver = webdriver.Chrome(chromedriver)
driver.implicitly_wait(1)
driver.get("https://search.naver.com/search.naver?where=image&sm=tab_jum&query=" + img_name)
 
element = driver.find_element(By.TAG_NAME, "body")
 
for _ in range(scroll_num):
    for _ in range(10):
        element.send_keys(Keys.PAGE_DOWN)
    time.sleep(2)
 
links = []
 
images = driver.find_elements(By.CSS_SELECTOR, "img._image._listImage")
for image in images:
    if image.get_attribute("src") != None:
        links.append(image.get_attribute("src"))
driver.close()
 
for idx, link in enumerate(links):
    urllib.request.urlretrieve(link, str(save_path) + str(img_name) + str(idx) + ".jpg")
    img = load_img(str(save_path) + str(img_name) + str(idx) + ".jpg")
    img = img.convert("RGB")
    img = img.resize((img_width, img_height))
    img.save(str(save_path) + str(img_name) + str(idx) + ".jpg")

 

 

핀터레스트

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import urllib.request
from selenium.webdriver.common.by import By
from keras.utils.image_utils import load_img
 
chromedriver = "크롬 드라이버 경로"     # 크롬 드라이버 위치
img_name = "검색 키워드"     # 검색 키워드
save_path = "이미지 저장 경로"       # 이미지 저장 위치
img_width = 256     # output사이즈(픽셀)
img_height = 256
scroll_num = 5    # 스크롤 횟수
 
 
driver = webdriver.Chrome(chromedriver)
driver.implicitly_wait(1)
driver.get("https://www.pinterest.co.kr/search/pins/?q=" + img_name + "&rs=rs&eq=&etslf=1719")
 
element = driver.find_element(By.TAG_NAME, "body")
 
 
for _ in range(scroll_num):
    images = driver.find_elements(By.CSS_SELECTOR, "img.hCL.kVc.L4E.MIw")
    links = []
    for image in images:
        links.append(image.get_attribute("src"))
    for _ in range(5):
        element.send_keys(Keys.PAGE_DOWN)
 
driver.close()
 
for idx, link in enumerate(links):
    urllib.request.urlretrieve(link, str(save_path) + str(img_name) + str(idx) + ".jpg")
    img = load_img(str(save_path) + str(img_name) + str(idx) + ".jpg")
    img = img.convert("RGB")
    img = img.resize((img_width, img_height))
    img.save(str(save_path) + str(img_name) + str(idx) + ".jpg")
 

혹시 몰라서..