python爬虫小程序,爬取百度图片

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/xcd1997/article/details/82526990

from selenium import webdriver
import requests
from selenium.webdriver import  ActionChains
import time
def get_img(url,finame):#保存图片
    # url = 'https://ss2.bdstatic.com/70cFvnSh_Q1YnxGkpoWK1HF6hhy/it/u=271066229,2382325557&fm=27&gp=0.jpg'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36'
    }
    data = requests.get(url, headers=headers)

    with open(finame, 'wb') as f:
        f.write(data.content)

def skip(d):#跳转到打开界面
    d.switch_to.window(d.window_handles[-1])
    return d

def prepare(url):#准备事项
    d = webdriver.Chrome()
    d.implicitly_wait(10)
    d.get(url)
    return d
def run():
    url = 'https://www.baidu.com'

    d = prepare(url)

    text = d.find_element_by_xpath('//*[@id="kw"]')

    buten1 = d.find_element_by_xpath('//*[@id="su"]')

    text.send_keys('刘诗诗龙葵图片')

    buten1.click()

    d = skip(d)

    data = d.find_element_by_xpath('//*[@id="1"]/h3/a')

    ActionChains(d).move_to_element(data).click().perform()

    d=skip(d)

    fs = d.find_element_by_xpath('//*[@id="imgid"]/div/ul/li[1]/div/a/img')

    ActionChains(d).move_to_element(fs).click().perform()

    d = skip(d)
    for i in range(20):
        img_url = d.find_element_by_xpath('//*[@id="currentImg"]').get_attribute('src')
        get_img(img_url,'D:\\龙葵\\'+str(i)+'.jpg')
        last = d.find_element_by_xpath('//*[@id="container"]/span[2]/span')
        time.sleep(1)
        last.click()

    time.sleep(3)
    d.close()

    d.quit()

if __name__ == '__main__':
    run()