import requests
import re
from bs4 import BeautifulSoup
import random
# 生成随机数
# for i in range(5):
# print(random.randrange(100000000))
headers = {
'content-type': 'application/json;charset=UTF-8',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36'
}
# 构建获取图片函数
def get_url(get_url_list):
response = requests.get(get_url_list, headers=headers)
response.encoding = 'utf-8'
html = response.text
soup = BeautifulSoup(html, 'html.parser')
img = soup.select('img')
re_img_url_list = re.findall('https.*?.jpg', str(img))
# print(re_img_list)
return re_img_url_list
# 构建下载函数
def download_img(url, file_name):
res = requests.get(url)
img = open('file/' + file_name, 'wb')
img.write(res.content)
img.close()
# """
for j in range(10):
urls = get_url('https://www.keaitupian.cn/meinv/list_4_' + str(j + 1) + '.html')
print('正在下载第' + str(j + 1) + '页图片...')
for i in urls:
# 图片名称
name = i.split('/')[-1]
download_img(i, name)
print('第' + str(j + 1) + '页图片下载完成')
print('下载完成！')
# """
下载图片：
标签：批量,img,get,python,list,url,print,re,配图 From： https://www.cnblogs.com/zhaoyiguang/p/16791612.html