存储媒体文件到本地

# -*- encoding=UTF-8 -*-
'''
author:vfast
name:spider
data:2021/6/24
'''

import urllib
from lxml import etree
import requests


def Schedule(blocknum, blocksize, totalsize):
    '''
    :param blocknum:已经下载的数据块
    :param blocksize: 数据块的大小
    :param totalsize: 远程文件的大小
    :return:
    '''
    per = 100.0 * blocknum * blocksize / totalsize
    if per > 100:
        per = 100
    print '当前下载进度:%d' % per


user_agent = 'Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0'
headers = {'User-Agent': user_agent}
r = requests.get('http://www.ivsky.com/tupian/ziranfengguang/', headers=headers)

html = etree.HTML(r.text)
img_urls = html.xpath('.//img/@src')
i = 0
for img_url in img_urls:
    urllib.urlretrieve(img_url, 'img' + str(i) + '.jpg', Schedule)
    i += 1

来源：Python爬虫开发与项目实战