requests爬取梨视频并保存到本地最简单的方法

import requests
from lxml import etree
import re
import os
from urllib.request import urlretrieve

url='https://www.pearvideo.com/category_9'
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'}

res = requests.get(url,headers=headers)
html_doc = res.content.decode('utf-8')

tree = etree.HTML(html_doc)


movie = tree.xpath('//*[@id="categoryList"]/li/div/a/@href')
movie_1 = tree.xpath('//*[@id="categoryList"]/li/div/a/div[2]/text()')

for movie_url,movie_text in zip(movie,movie_1):
    #拼接url
    movie_url = 'https://www.pearvideo.com/'+movie_url
    #获取每个url的网页text
    movie_id_string = requests.get(movie_url,headers=headers).text

    #获取视频里层播放mp4的url地址 []
    movie_mp4_url = re.findall('sdflvUrl="",hdUrl="",sdUrl="",ldUrl="",srcUrl="(.*?)",vdoUrl=srcUrl',movie_id_string)

    #url在[]列表里 没有遍历出来 所以用索引下标[0]

    #第一种保存方法
    mp4 = requests.get(movie_mp4_url[0]).content

    with open('./movie/%s.mp4'%movie_text,'wb') as f:
        f.write(mp4)
        print("正在下载视频：%s"%movie_text)


    # #第二种保存方法
    # path='movie'
    # #判断有没有这个路径，没有则创建
    # if path not in os.listdir():
    #     os.mkdir(path)
    # #路径+文件格式+文件名字
    # filepath = path + '/%s.mp4'%movie_text[0]
    # #下载：url地址，文件路径。
    # urlretrieve(movie_mp4_url[0],filepath)