'''
urllib3批量下载百度图片
'''
import urllib3
import re
start_url = 'http://image.baidu.com/search/index?tn=baiduimage&word=dahuaxiyou'
http = urllib3.PoolManager()
res = http.request('get',start_url).data.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,
}
res = http.request('get',url,headers=headers).data
with open(file_path,'wb') as f:
f.write(res)
for image_url in image_urls:
save_img(image_url)
