微信视频号python爬虫

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import requests
import json
import time
import re
import os

def get_video_url(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'
    }
    response = requests.get(url,headers=headers)
    response.encoding = 'utf-8'
    html = response.text
    #获取视频id
    vid = re.findall('vid: "(.*?)",',html,re.S)[0]
    #拼接视频播放页面url
    video_url = 'https://h5vv.video.qq.com/getinfo?vids={}&platform=101001&charge=0&otype=json'.format(vid)
    #请求视频播放页面
    response = requests.get(video_url,headers=headers)
    response.encoding = 'utf-8'
    #获取视频真实url
    j_data = json.loads(response.text[response.text.find('{'):response.text.rfind('}') + 1])
    video_urls = j_data['vl']['vi'][0]['ul']['ui'][0]['url']
    return video_urls

def download_video(url,name):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'
    }
    response = requests.get(url,headers=headers)
    #获取文件大小
    size = int(response.headers['Content-Length'])
    #设置文件大小
    count = 0
    #设置下载路径
    path = 'D:/video/'
    #设置文件名
    file_name = name + '.mp4'
    #拼接文件路径
    file_path = path + file_name
    #判断文件路径是否存在
    if not os.path.exists(path):
        os.makedirs(path)
    #判断文件是否存在
    if not os.path.exists(file_path):
        #文件不存在，开始下载
        with open(file_path,'wb') as f:
            f.write(response.content)
            f.flush()
        print('文件下载成功')
    else:
        #文件存在，提示用户
        print('文件已存在')

if __name__ == '__main__':
    #设置视频链接
    url = 'https://v.qq.com/x/page/j3030h2k5j5.html'
    #获取视频真实url
    video_url = get_video_url(url)
    #设置视频名称
    name = '微信视频号'
    #开始下载视频
    download_video(video_url,name)