python新人再战江湖————爬虫第二弹（爬取短视频）

import requests
from lxml import etree
import  os
import time
import random

def get_html(url):
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.5918.400 LBBROWSER/10.1.3090.400'}

    try:
        html = requests.get(url, headers = headers)
        html.encoding = html.apparent_encoding
        if html.status_code == 200:
            print('获取源代码成功')
            # print(html.text)
    except Exception as e:
        print('获取源代码失败:%s'%e)
    return html.text

def parse_html(html):
    html = etree.HTML(html)
    lis = html.xpath('//div[@class="j-r-list"]/ul/li')   # 每个li 标签代表一个段子
    videourls = []
    names = []
    for li in lis:
        title = li.xpath(".//div[@class='j-r-list-c-desc']/a/text()")[0]
        videourl = li.xpath(".//li[@title='下载视频']/a/@href")[0]
        videourls.append(videourl)
        names.append(title)
    return( videourls, names)

def downloadvideo(url, name):
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.5918.400 LBBROWSER/10.1.3090.400'}

    if '百思不得姐video' in os.listdir(r'E:\pycharm项目\爬虫初战'):     #  此处一定要是绝对路径，否则会形成文件夹嵌套
        pass
    else:
        os.mkdir(r'E:\pycharm项目\爬虫初战\百思不得姐video')
    os.chdir(r'E:\pycharm项目\爬虫初战\百思不得姐video')

    video = requests.get(url, headers = headers).content    #  .content 很重要，视频和音频、图片都这么保存  都是以二进制形式保存的
    with open(name + '.mp4', 'wb')as f:
        print('正在下载%s'%url)
        f.write(video)

if __name__ == "__main__":
    page = int(input('你要下载几页：'))
    for i in range(page):
        url = 'http://www.budejie.com/video/' + str(i + 1)     #  range 从零开始，且前闭后开。所以要加1

        html = get_html(url)
        videourls = parse_html(html)[0]
        names = parse_html(html)[1]

    for i in range(20):
        time.sleep(random.randint(1, 4)+ random.random())           #   使得请求时间变得随机
        downloadvideo(videourls[i], names[i])

对于爬虫的掌握还不太好，没有太深入，对于大型网站的反扒措施束手无策。
望各位大神指点迷津。