urllib批量下载百度图片

版权声明：只要点赞，这篇文章就是你的。 https://blog.csdn.net/weixin_36691991/article/details/89048506

'''
urllib批量下载百度图片
'''
import urllib.request
import re
start_url = 'http://image.baidu.com/search/index?tn=baiduimage&word=dahuaxiyou'
res = urllib.request.urlopen(start_url).read().decode()
image_urls = re.findall(r'"thumbURL":"(.*?)"',res,re.S)
def save_img(url):
    file_path = url.split('/')[-1]
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36",
        "Referer":start_url,
    }
    rep = urllib.request.Request(url,headers=headers)
    res = urllib.request.urlopen(rep).read()
    with open(file_path,'wb') as f:
        f.write(res)
for image_url in image_urls:
    save_img(image_url)