Python 采集筷实现视频批量保存

前言

嗨喽~大家好呀，这里是魔王呐 ❤ ~!

刷到的视频怕它下架？我们来采集保存一下它

知识点:

动态数据抓包
requests发送请求
json数据解析

开发环境:

python 3.8 运行代码
pycharm 2022.3 辅助敲代码
requests pip install requests

代码展示

需要源码 . 素材 . 点击领取即可

导入模块

import re

import requests     # 发送请求

伪装

headers = {
    'Cookie': 'kpf=PC_WEB; clientid=3; did=web_4bf90ac4df8aaef2d99527f1da1063fd; userId=3075864129; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqAB9tSqSgbeN3Qhc4H_V6Awn1-yfEnaceVEJQUhtxgCBBHHQl_DyWKPYDO3XIdjFQTHwSSFOPZL6FPTk7LSW1dfp7qvBSeP4ANjPT1evIoq9ODcPJyb6YgEIdsV-Dzm_Sq73yQg6jYhvuRNJGwAM_GfAfUKWiG4RDdGDpHd1uCAJd0qM2xZwqzr11JlIz3yRFeNFNfO2zINkJAktY8lUyQwuRoS9XMBYg26NCtIxdOwhbHEY-u6IiBNGgmRMQXPmCodWM1RM7oFpjHSgD61betJSR00w0VYtSgFMAE; kuaishou.server.web_ph=69e54c87baac46f523262858017c7988cf22; kpn=KUAISHOU_VISION',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36'
}

请求链接

url = 'https://www.****.com/graphql'

pcursor = ""
while True:
    # 请求体
    json = {
        'operationName': "visionProfilePhotoList",
        'query': "fragment photoContent on PhotoEntity {\n  id\n  duration\n  caption\n  originCaption\n  likeCount\n  viewCount\n  realLikeCount\n  coverUrl\n  photoUrl\n  photoH265Url\n  manifest\n  manifestH265\n  videoResource\n  coverUrls {\n    url\n    __typename\n  }\n  timestamp\n  expTag\n  animatedCoverUrl\n  distance\n  videoRatio\n  liked\n  stereoType\n  profileUserTopPhoto\n  musicBlocked\n  __typename\n}\n\nfragment feedContent on Feed {\n  type\n  author {\n    id\n    name\n    headerUrl\n    following\n    headerUrls {\n      url\n      __typename\n    }\n    __typename\n  }\n  photo {\n    ...photoContent\n    __typename\n  }\n  canAddComment\n  llsid\n  status\n  currentPcursor\n  tags {\n    type\n    name\n    __typename\n  }\n  __typename\n}\n\nquery visionProfilePhotoList($pcursor: String, $userId: String, $page: String, $webPageArea: String) {\n  visionProfilePhotoList(pcursor: $pcursor, userId: $userId, page: $page, webPageArea: $webPageArea) {\n    result\n    llsid\n    webPageArea\n    feeds {\n      ...feedContent\n      __typename\n    }\n    hostName\n    pcursor\n    __typename\n  }\n}\n",
        'variables': {'userId': "3xjfq9eesf4kxwg", 'pcursor': pcursor, 'page': "profile"}
    }

发送请求

    response = requests.post(url=url, headers=headers, json=json)

获取数据

    json_data = response.json()

解析数据

键: 值通过:前面的内容取:后面的内容

    feeds = json_data['data']['visionProfilePhotoList']['feeds']
    pcursor = json_data['data']['visionProfilePhotoList']['pcursor']
    for feed in feeds:
        photoUrl = feed['photo']['photoUrl']
        caption = feed['photo']['caption']
        caption = re.sub('[\\\/:*?"<>|]', '', caption)
        print(caption, photoUrl)

保存数据

        video_data = requests.get(photoUrl).content
        with open(rf"C:\Users\Administrator\Desktop\video\{caption}.mp4", mode='wb') as f:
            f.write(video_data)
    if pcursor == "no_more":
        break