虎牙视频

# @Author: 昊阳
# _*_ coding : utf-8 _*_
# @Time:2022/10/22 0022 13:19
# @File : video_all
# @Project : MyCase

import requests
import  re
import  pprint
def create(num):
    for page in range(1, num+1):
        print(f'--------------正在获取第{page}页的视频---------------')
        url = f'https://v.huya.com/g/all?set_id=51&order=hot&page={page}'
        headres = {
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36'
        }
        response = requests.get(url=url, headers=headres).text
        # 正则中只需要数字就用\d+就行了
        # 视频id
        vid = re.findall('"vid":(\d+),"liveId"', response)
    # 视频地址
    for i in vid:
        video_url = f'https://liveapi.huya.com/moment/getMomentContent?videoId={i}&_=1666417414509'
        # 新的视频地址
        response_1 = requests.get(url=video_url, headers=headres).json()
        # pprint.pprint(response_1)
        # 视频名
        title = response_1['data']['moment']['title']
        # 视频地址
        video_url = response_1['data']['moment']['videoInfo']['definitions'][0]['url']
        print(title,video_url)
        # 保存数据
        video_content = requests.get(url=video_url, headers=headres).content  # 获取二进制数据内容
        with open("video\\" + title + '.mp4', mode='wb') as f:
            f.write(video_content)
        # print(video_content)
if __name__ =='__main__':
    num = input("请输入想要爬取几页的视频")
    create(int(num))