爬虫- 爬取快手视频-批量爬取 | 视频解密AES-128

 爬取快手视频代码:

 

import requests
import json
import re


# 输入你想要的搜索关键词
key = input('输入你搜索的关键词:')
# range(0, 3) -> 0 1 2 抓取, 3表示结束不抓取
for pcursor in range(0, 3):

    headers = {
        'accept': '*/*',
        'Accept-Encoding': 'gzip, deflate, br',
        'Accept-Language': 'zh-CN,zh;q=0.9',
        'Connection': 'keep-alive',
        'Content-Length': '1279',
        'content-type': 'application/json',
        'Cookie': 'kpf=PC_WEB; kpn=KUAISHOU_VISION; clientid=3; did=web_e8ca87384bb99320873d4f0cdb8b4a0b',
        'Host': 'www.kuaishou.com',
        'Origin': 'https://www.kuaishou.com',
        'Referer': 'https://www.kuaishou.com/search/video?searchKey=%E6%85%A2%E6%91%87',
        'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="100", "Google Chrome";v="100"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': 'Windows',
        'Sec-Fetch-Dest': 'empty',
        'Sec-Fetch-Mode': 'cors',
        'Sec-Fetch-Site': 'same-origin',
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36'

    }

    url = 'https://www.kuaishou.com/graphql'
    data = {
        "operationName": "visionSearchPhoto",
        "query": "fragment photoContent on PhotoEntity {\n  id\n  duration\n  caption\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  __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  __typename\n}\n\nquery visionSearchPhoto($keyword: String, $pcursor: String, $searchSessionId: String, $page: String, $webPageArea: String) {\n  visionSearchPhoto(keyword: $keyword, pcursor: $pcursor, searchSessionId: $searchSessionId, page: $page, webPageArea: $webPageArea) {\n    result\n    llsid\n    webPageArea\n    feeds {\n      ...feedContent\n      __typename\n    }\n    searchSessionId\n    pcursor\n    aladdinBanner {\n      imgUrl\n      link\n      __typename\n    }\n    __typename\n  }\n}\n",
        'variables': {'keyword': key, 'pcursor': f"{pcursor}", 'page': "search",'searchSessionId': "MTRfMF8xNjUxNjY0MzM5NjI5X-aFouaRh184ODUz"}

    }


    # 将字典类型  转化   json字符串
    data = json.dumps(data)

    resp = requests.post(url=url, headers=headers, data=data)
    # 拿到页面数据 字典格式
    json_data = resp.json()

    #在字段中获取 值

    lists = json_data["data"]["visionSearchPhoto"]["feeds"]

    for list in lists:
        # list 是个字典  获取视频的标题
        title = list['photo']['caption']

        # 去掉标题里面特殊字符 , 预防title 里面有特殊字符不能被系统识别
        new_title = re.sub(r'[/\:*?"|\n]', '_', title)


        # 获取视频的地址
        info_url = list['photo']['photoUrl']

        # 保存视频
        resp = requests.get(info_url).content

        with open('v/' + new_title + '.mp4', mode='wb') as f:
            f.write(resp)

        print('下载完成' + new_title)

 

2. AES -128 解密 

　　2.1 需要安装包 

　　

pip install pycryptodome