用selenium爬取百度图片_selenium src怎么下载图片

用selenium爬取百度图片

因为百度图片是瀑布流， 所以我选择了用selenium模拟鼠标点击来下载图片

from selenium import webdriver
import bs4
import time
import urllib.request
import re

name = input('请输入你要搜索的名字：')
number = int(input('请输入你要保存的文件数量：'))

driver = webdriver.Chrome()
driver.get('http://image.baidu.com/')   #打开百度图片
time.sleep(2)
driver.find_element_by_id('kw').send_keys(name)    #搜索林依晨
driver.find_element_by_class_name('s_search').click()

m = 0
    
for i in range(5):   #划5下
    js = "window.scrollTo(0,document.body.scrollHeight)"    
    driver.execute_script(js)   #滚到最底部    
    time.sleep(1)



soup = bs4.BeautifulSoup(driver.page_source, 'lxml')
imgsrc = soup.body.find_all('img', class_="main_img img-hover")

for img in imgsrc:

    images = img.attrs['src']
    urllib.request.urlretrieve(images, r'E:\python\爬的图片\%d.jpg' % m)
    m += 1
    time.sleep(1)
    
    if m > number:
        break

print('finish...')
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38