爬虫selenium下载搜索百度图片_selenium 安装 爬百度图片 mac

# -- coding: utf-8 --
import re
import time
 
import requests
from selenium import webdriver
import os
 
if not os.path.exists('imgs'):
    os.mkdir('imgs')
 
bd_browser = webdriver.Chrome('chromedriver.exe')
bd_browser.maximize_window()
with open('stealth.min.js', 'r', encoding='utf-8')as f:
    js_code = f.read()
 
 
bd_browser.get('https://image.baidu.com/')
input_jd = bd_browser.find_element_by_id('kw')
input_jd.send_keys(input("请输入要搜索图片的名字："))
 
cick_job = bd_browser.find_element_by_class_name('s_newBtn')
cick_job.click()
bd_browser.implicitly_wait(20)
def drop_down():
    for i in range(100):
        time.sleep(0.3)
        bd_browser.execute_script('window.scrollBy(0,300)', '')
        bd_browser.implicitly_wait(50)
 
def Download():
    lis = bd_browser.find_elements_by_class_name('main_img')
    titles = bd_browser.find_elements_by_class_name('imgitem-title')
    names = []
    urls = []
    for name in titles:
        name = name.get_attribute('title')
        name2 = name.replace(" ", "").replace("|", "").replace("?", "").replace(":", "").replace("/", "").replace(">", "").replace(".", "").replace(",", "").replace("_", "")
        name3 = re.sub('"', "", name2)
        names.append(name3)
 
    for url in lis:
        url = url.get_attribute('src')
        urls.append(url)
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36",
    }
 
 
    result = dict(zip(names, urls))
    for k, v in result.items():
        img = requests.get(v, headers=headers).content
        try:
            with open('imgs/'+k+".png", 'wb') as f:
                f.write(img)
        except:
            print(k+"不符合古命名规则")
 
if __name__ == '__main__':
    drop_down()
    Download()