短视频爬虫

import requests
import json


def short_video():
    #  1.构造start_url
    start_url = "https://www.ku6.com/video/feed?pageNo=0&pageSize=40&subjectId=76"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
                      "(KHTML, like Gecko) Chrome/77.0.3865.75 Safari/537.36",
        "referer": "https://www.ku6.com/detail/76",
    }
    # 2.发送请求，获取响应
    response = requests.get(start_url, headers=headers)
    # print(response.text)
    res_data = response.text

    #  3.解析数据
    json_data = json.loads(res_data)
    # print(json_data)
    #  4.保存数据
    data_list = json_data["data"]
    # print(data_list)

    for data_dic in data_list:
        # print(data_dic)
        video_name = data_dic["title"] + ".mp4"
        video_url = data_dic["playUrl"]
        print(video_name, video_url)
        # # print("正在下载：", video_name)
        video_data = requests.get(video_url, headers=headers).content
        # print(video_data)

        with open(video_name, "wb")as f:
            f.write(video_data)
            # print("下载完成：", video_name)


if __name__ == '__main__':
    short_video()