Created
August 6, 2022 08:49
-
-
Save taoka-toshiaki/1cd532737236695640ea4660a6539e30 to your computer and use it in GitHub Desktop.
bingサイトで画像ダウンロードするために作られたものです。
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from functools import cache | |
import time | |
import requests | |
import os | |
from selenium import webdriver | |
from selenium.webdriver.support import expected_conditions as EC | |
from selenium.webdriver.support.wait import WebDriverWait | |
from selenium.webdriver.common.by import By | |
from webdriver_manager.chrome import ChromeDriverManager | |
from selenium.webdriver.chrome.options import Options | |
options = Options() | |
# download_path = 'C:\python\images\face' | |
# options.add_experimental_option("prefs", {"download.default_directory": download_path}) | |
# driver = webdriver.Chrome(ChromeDriverManager().install(), options=options) | |
driver = webdriver.Chrome(ChromeDriverManager().install()) | |
driver.get("https://www.bing.com/images/search?q=顔&form=HDRSC2&first=1&tsc=ImageHoverTitle") | |
driver.set_window_size(945, 1012) | |
time.sleep(3) | |
sl = 700 | |
for i in range(30): | |
driver.execute_script("window.scrollTo(0," + str(sl) + ")") | |
time.sleep(3) | |
sl = sl + 700 | |
img = [] | |
for x in range(10): | |
for y in range(100): | |
try: | |
txt = driver.find_element(By.XPATH,"//*[@id=\"mmComponent_images_2\"]/ul[" + str(int(y +1 )) +"]/li[" + str(int(x +1 )) +"]/div/div[1]/a").get_attribute("m") | |
hoge = str(txt).split(",") | |
#print(hoge) | |
img.append([s for s in hoge if "murl" in s]) | |
except: | |
print("errors not image") | |
driver.quit() | |
file_dir = "C:\\python\\images\\face\\" | |
for imgdata in img: | |
url = str(imgdata).split(":")[1] + ":" + str(imgdata).split(":")[2] | |
url = url.replace('"',"").replace("']","") | |
print(url) | |
try: | |
urlData = requests.get(url).content | |
with open(os.path.join(file_dir,os.path.basename(url)),'wb') as f: | |
f.write(urlData) | |
except: | |
print("errors not Download") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment