快手用户公开视频下载代码

最新推荐文章于 2024-09-13 08:48:35 发布

LaySwift

最新推荐文章于 2024-09-13 08:48:35 发布

阅读量4.8k

点赞数

分类专栏： python

本文链接：https://blog.csdn.net/LaySwift/article/details/98479536

版权

python 专栏收录该内容

19 篇文章 1 订阅

订阅专栏

最近刷快手发现有些想缓存的视频下载不了，于是就用了一两天的时间研究了一下快手，可以通过用户的快手ID（用eid也可以）下载用户所有公开的视频（私有视频需要用户的token，不登录拿不到），可能有些用户没有快手ID，只有用户id，所以在文章后面我会放上一段通过用户id查询用户eid的代码。

import os
import re
import json
import requests

# ID：Lijing1997
# ID: h990901h
# ID: 8319075(eid:3xucs5xtvau5jdg)
# ID: Heniao__
USER_IDS = ['Lijing1997']  # 快手ID列表，也可以用eid列表
SAVE_PATH = 'C:\\Users\\Lay\\Desktop'  # feeds下载存储路径


# 请求头
headers = {
    'Proxy-Connection': 'keep-alive',
    'Connection': 'keep-alive',
    'Cache-Control': 'max-age=0',
    'Upgrade-Insecure-Requests': '1',
    'Referer': 'https://live.kuaishou.com',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
}

user_num = 1
for USER_ID in USER_IDS:

    # feeds查询语句
    user_public_feeds_query_string = {"operationName": "RecoFeeds",
                                      "variables": {"principalId": USER_ID, "pcursor": "", "count": 999},
                                      "query": "query RecoFeeds($principalId: String, $pcursor: String, $count: Int) {\n  publicFeeds(principalId: $principalId, pcursor: $pcursor, count: $count) {\n    pcursor\n    list {\n      user {\n        id\n        profile\n        name\n        __typename\n      }\n      photoId\n      caption\n      poster\n      likeCount\n      playUrl\n      imgUrls\n      imgSizes\n      width\n      height\n      expTag\n      __typename\n    }\n    __typename\n  }\n}\n"}

    # 查询用户公开的feeds数据
    r_graphql = requests.post('https://live.kuaishou.com/graphql', headers=headers, json=user_public_feeds_query_string, verify=False)
    user_public_feeds_data = json.loads(r_graphql.content.decode(encoding='utf-8', errors='strict'))['data']
    feeds_path = os.path.join(SAVE_PATH, 'NetFinder')
    print('正在下载:{user_id}......'.format(user_id=USER_ID))
    # 遍历用户feeds列表
    feed_num = 1
    for feed in user_public_feeds_data['publicFeeds']['list']:

        # 去掉caption中的空白符号和不支持的文件符号, [0:99]为win系统文件名长度限制，具体不知，这里取99
        feed['caption'] = re.sub(r'[\/\\\:\*\?\"\<\>\|\s]', ',', feed['caption'])[0:99]

        if feed['caption'] == '...':
            feed['caption'] = '未命名'
        elif '.' in feed['caption']:
            feed['caption'].replace('.', '#')

        # 为每个feed创建一个路径
        feed_path = os.path.join(feeds_path, feed['user']['name']+'({user_id})'.format(user_id=USER_ID), feed['caption'])
        if not os.path.exists(feed_path):
            os.makedirs(feed_path)

        # 下载并写入文件
        if feed['poster']:
            poster_res = requests.get(feed['poster'], headers=headers, verify=False)
            with open(os.path.join(feed_path, '{feed_name}.{suffix}'.format(feed_name=feed['caption'], suffix=feed['poster'].split('.')[-1])), 'wb') as f:
                f.write(poster_res.content)
        if feed['playUrl']:
            video_res = requests.get(feed['playUrl'], headers=headers, verify=False)
            with open(os.path.join(feed_path, '{feed_name}.{suffix}'.format(feed_name=feed['caption'], suffix=feed['playUrl'].split('.')[-1])), 'wb') as f:
                f.write(video_res.content)
        elif feed['imgUrls']:
            i = 1
            for img in feed['imgUrls']:
                img_res = requests.get(img, headers=headers, verify=False)
                try:
                    with open(os.path.join(feed_path, '{num}-{feed_name}.{suffix}'.format(num=str(i), feed_name=feed['caption'], suffix=img.split('.')[-1])), 'wb') as f:
                        f.write(img_res.content)
                except FileNotFoundError:
                    pass
                i += 1
        print('({feed_num}):{feed_name}---下载完毕！'.format(feed_num=feed_num, feed_name=feed['caption']))
        feed_num += 1
    print('({user_num}){user_id}---下载结束！'.format(user_num=user_num, user_id=USER_ID))
    user_num += 1

通过用户id查询用户eid，eid可用于上面的视频下载

headers = {
    'Proxy-Connection': 'keep-alive',
    'Connection': 'keep-alive',
    'Cache-Control': 'max-age=0',
    'Upgrade-Insecure-Requests': '1',
    'Referer': 'https://live.kuaishou.com',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
}
num = 1
authors_info_list = []
key_words = 3848980  # 用户ID（非快手ID）

while True:
    authors_info_query_string = {"operationName":"SearchDetailQuery","variables":{"key":str(key_words),"type":"author","page":num,"lssid":None,"ussid":None},"query":"query SearchDetailQuery($key: String, $type: String, $page: Int, $lssid: String, $ussid: String) {\n  searchDetail(key: $key, type: $type, page: $page, lssid: $lssid, ussid: $ussid) {\n    ... on SearchCategoryList {\n      type\n      list {\n        id\n        categoryId\n        title\n        src\n        roomNumber\n        __typename\n      }\n      __typename\n    }\n    ... on SearchUserList {\n      type\n      ussid\n      list {\n        id\n        name\n        living\n        profile\n        sex\n        description\n        countsInfo {\n          fan\n          follow\n          photo\n          __typename\n        }\n        __typename\n      }\n      __typename\n    }\n    ... on SearchLivestreamList {\n      type\n      lssid\n      list {\n        user {\n          id\n          profile\n          name\n          __typename\n        }\n        watchingCount\n        src\n        title\n        gameId\n        gameName\n        categoryId\n        liveStreamId\n        playUrls {\n          quality\n          url\n          __typename\n        }\n        quality\n        gameInfo {\n          category\n          name\n          pubgSurvival\n          type\n          kingHero\n          __typename\n        }\n        redPack\n        liveGuess\n        expTag\n        __typename\n      }\n      __typename\n    }\n    __typename\n  }\n}\n"}
    r_graphql = requests.post('https://live.kuaishou.com/graphql', headers=headers, json=authors_info_query_string, verify=False)
    try:
        authors_info = json.loads(r_graphql.content.decode(encoding='utf-8', errors='strict'))['data']['searchDetail']
        authors_info_list += authors_info['list']
        print(authors_info['list'])  # 输出中的id为用户eid
        if len(authors_info['list']) < 15:
            print(authors_info_list)
            break
        else:
            num += 1
    except json.decoder.JSONDecodeError:
        pass