python 爬虫快手

最新推荐文章于 2024-07-17 14:52:49 发布

鲁班工作室

最新推荐文章于 2024-07-17 14:52:49 发布

阅读量2.4k

点赞数 1

分类专栏： python

本文链接：https://blog.csdn.net/qq_40658762/article/details/99303092

版权

python 专栏收录该内容

7 篇文章 0 订阅

订阅专栏

爬虫日常

快手
源码使用常见错误
- 1.提示模块requests不存在

快手

1.爬个人列表下的所有作品

# 作者：robin_aerfa
# QQ:1514149460
# wx:Stbz528403
import json  # 导入模块 json
import requests  # 导入模块 requests


def sub_data(ginseng_id, ginseng_pcursor=''):  # 定义函数组合请求数据
    local_post_data = {"operationName": "publicFeedsQuery",
                       "variables": {"principalId": ginseng_id, "pcursor": ginseng_pcursor, "count": 24},
                       "query": "query publicFeedsQuery($principalId: String, $pcursor: String, $count: Int) {\n  publicFeeds(principalId: $principalId, pcursor: $pcursor, count: $count) {\n    pcursor\n    live {\n      user {\n        id\n        kwaiId\n        eid\n        profile\n        name\n        living\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      followed\n      type\n      living\n      redPack\n      liveGuess\n      anchorPointed\n      latestViewed\n      expTag\n      __typename\n    }\n    list {\n      photoId\n      caption\n      thumbnailUrl\n      poster\n      viewCount\n      likeCount\n      commentCount\n      timestamp\n      workType\n      type\n      useVideoPlayer\n      imgUrls\n      imgSizes\n      magicFace\n      musicName\n      location\n      liked\n      onlyFollowerCanComment\n      relativeHeight\n      width\n      height\n      user {\n        id\n        eid\n        name\n        profile\n        __typename\n      }\n      expTag\n      __typename\n    }\n    __typename\n  }\n}\n"}
    local_post_data = str(local_post_data).replace("'", '"').replace(', ', ',').replace(' ', '', 5)
    return local_post_data


def sub_head(ginseng_id):  # 定义函数组合请求头
    local_headers = {
        "Host": "live.kuaishou.com",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:68.0) Gecko/20100101 Firefox/68.0",
        "Accept": "*/*",
        "Accept-Language": "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
        "Accept-Encoding": "gzip, deflate, br",
        "Referer": "https://live.kuaishou.com/profile/" + ginseng_id,
        "content-type": "application/json",
        "Cookie": "clientid=3; did=web_79aee2e860f5438d897ddb18f84c1365; client_key=65890b29; didv=1565316325000; kuaishou.live.bfb1s=3e261140b0cf7444a0ba411c6f227d88",
    }
    return local_headers


def data_analysis(ginseng_data):  # 解析返回json为 dcti
    local_json_data = json.loads(ginseng_data)['data']['publicFeeds']['list']
    works_list = []
    works = {}
    for lin_data in local_json_data:
        works = {
            '作品ID:': lin_data['photoId'],
            '标题:': lin_data['caption'],
        }
        works_list.append(works)
    return works_list


if __name__ == '__main__':
    url = 'https://live.kuaishou.com/graphql'
    local_id = 'CFNF88888888'
    local_pcursor = ''
    local_works = []

    # 下面代码进行爬取数据
    state = True
    while state:
        json_data = requests.post(url, headers=sub_head('local_id'), data=sub_data(local_id, local_pcursor))
        json_data.encoding = 'UTF-8-SIG'  # 乱码解决办法
        local_works += data_analysis(json_data.text)

        local_pcursor = json.loads(json_data.text)['data']['publicFeeds']['pcursor']
        # print(local_pcursor)
        if local_pcursor == 'no_more':  # 数据爬取完后，结束循环。
            state = False
    with open('个人列表作品.txt', 'w', encoding='utf8') as fileobject:  # 保存数据
        for d_key in local_works:
            # print(d_key)
            fileobject.write(str(d_key) + "\n")
        fileobject.close()
    print(len(local_works))

1.爬个人列表下的所有作品 (2019/8/4更新)

2019/8/4更新增加读入ID
根据需求增加读入文件ID，批量爬取。

# 作者：robin_aerfa
# QQ:1514149460
# wx:Stbz528403
import json  # 导入模块 json
import requests  # 导入模块 requests


def sub_data(ginseng_id, ginseng_pcursor=''):  # 定义函数组合请求数据
    local_post_data = {"operationName": "publicFeedsQuery",
                       "variables": {"principalId": ginseng_id, "pcursor": ginseng_pcursor, "count": 24},
                       "query": "query publicFeedsQuery($principalId: String, $pcursor: String, $count: Int) {\n  publicFeeds(principalId: $principalId, pcursor: $pcursor, count: $count) {\n    pcursor\n    live {\n      user {\n        id\n        kwaiId\n        eid\n        profile\n        name\n        living\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      followed\n      type\n      living\n      redPack\n      liveGuess\n      anchorPointed\n      latestViewed\n      expTag\n      __typename\n    }\n    list {\n      photoId\n      caption\n      thumbnailUrl\n      poster\n      viewCount\n      likeCount\n      commentCount\n      timestamp\n      workType\n      type\n      useVideoPlayer\n      imgUrls\n      imgSizes\n      magicFace\n      musicName\n      location\n      liked\n      onlyFollowerCanComment\n      relativeHeight\n      width\n      height\n      user {\n        id\n        eid\n        name\n        profile\n        __typename\n      }\n      expTag\n      __typename\n    }\n    __typename\n  }\n}\n"}
    local_post_data = str(local_post_data).replace("'", '"').replace(', ', ',').replace(' ', '', 5)
    return local_post_data


def sub_head(ginseng_id):  # 定义函数组合请求头
    local_headers = {
        "Host": "live.kuaishou.com",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:68.0) Gecko/20100101 Firefox/68.0",
        "Accept": "*/*",
        "Accept-Language": "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
        "Accept-Encoding": "gzip, deflate, br",
        "Referer": "https://live.kuaishou.com/profile/" + ginseng_id,
        "content-type": "application/json",
        "Cookie": "clientid=3; did=web_79aee2e860f5438d897ddb18f84c1365; client_key=65890b29; didv=1565316325000; kuaishou.live.bfb1s=3e261140b0cf7444a0ba411c6f227d88",
    }
    return local_headers


def data_analysis(ginseng_data):  # 解析返回json为 dcti
    local_json_data = json.loads(ginseng_data)['data']['publicFeeds']['list']
    works_list = []
    works = {}
    for lin_data in local_json_data:
        works = {
            '作品ID:': lin_data['photoId'],
            '标题:': lin_data['caption'],
        }
        works_list.append(works)
    return works_list


if __name__ == '__main__':
    url = 'https://live.kuaishou.com/graphql'

    print("例如：C:1.TXT文件或者运行目录下 1.txt")
    file_path = input("请输入ID文件路径：")
    with open(file_path.replace('\\', '/')) as file_object:  # 打开文件
        local_data = file_object.read()  # 读入内容
        file_object.close()  # 关闭文件

    for file in file_path.split():
        # local_id = input("请输入用户ID:")
        # local_id = 'CFNF88888888'
        local_id = file
        local_pcursor = ''
        local_works = []
        local_headers = sub_head(local_id)
        local_data = sub_data(local_id, local_pcursor)

        # 下面代码进行爬取数据
        state = True
        while state:
            json_data = requests.post(url, headers=local_headers, data=local_data)
            json_data.encoding = 'UTF-8-SIG'  # 乱码解决办法
            local_works += data_analysis(json_data.text)

            local_pcursor = json.loads(json_data.text)['data']['publicFeeds']['pcursor']
            # print(local_pcursor)
            if local_pcursor == 'no_more':  # 数据爬取完后，结束循环。
                state = False

        with open('个人列表作品.txt', 'a', encoding='utf8') as fileobject:  # 保存数据 a附加插入模式
            for d_key in local_works:
                # print(d_key)
                fileobject.write(str(d_key) + "\n")
            fileobject.close()
        print(len(local_works))

    input("按任意字符退出~！")

2.爬作品所有评论

# 作者：robin_aerfa
# QQ:1514149460
# wx:Stbz528403

import json
import requests


def sub_data(ginseng_id, ginseng_pcursor=''):
    local_post_data = {"operationName": "publicFeedsQuery",
                       "variables": {"principalId": ginseng_id, "pcursor": ginseng_pcursor, "count": 24},
                       "query": "query publicFeedsQuery($principalId: String, $pcursor: String, $count: Int) {\n  publicFeeds(principalId: $principalId, pcursor: $pcursor, count: $count) {\n    pcursor\n    live {\n      user {\n        id\n        kwaiId\n        eid\n        profile\n        name\n        living\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      followed\n      type\n      living\n      redPack\n      liveGuess\n      anchorPointed\n      latestViewed\n      expTag\n      __typename\n    }\n    list {\n      photoId\n      caption\n      thumbnailUrl\n      poster\n      viewCount\n      likeCount\n      commentCount\n      timestamp\n      workType\n      type\n      useVideoPlayer\n      imgUrls\n      imgSizes\n      magicFace\n      musicName\n      location\n      liked\n      onlyFollowerCanComment\n      relativeHeight\n      width\n      height\n      user {\n        id\n        eid\n        name\n        profile\n        __typename\n      }\n      expTag\n      __typename\n    }\n    __typename\n  }\n}\n"}
    local_post_data = str(local_post_data).replace("'", '"').replace(', ', ',').replace(' ', '', 5)
    return local_post_data


def sub_head(ginseng_id):
    local_headers = {
        "Host": "live.kuaishou.com",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:68.0) Gecko/20100101 Firefox/68.0",
        "Accept": "*/*",
        "Accept-Language": "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
        "Accept-Encoding": "gzip, deflate, br",
        "Referer": "https://live.kuaishou.com/profile/" + ginseng_id,
        "content-type": "application/json",
        "Cookie": "clientid=3; did=web_79aee2e860f5438d897ddb18f84c1365; client_key=65890b29; didv=1565316325000; kuaishou.live.bfb1s=3e261140b0cf7444a0ba411c6f227d88",
    }
    return local_headers


def data_analysis(ginseng_data):
    local_json_data = json.loads(ginseng_data)['data']['publicFeeds']['list']
    works_list = []
    works = {}
    for lin_data in local_json_data:
        works = {
            '作品ID:': lin_data['photoId'],
            '标题:': lin_data['caption'],
        }
        works_list.append(works)
    return works_list


if __name__ == '__main__':
    url = 'https://live.kuaishou.com/graphql'
    local_id = 'CFNF88888888'
    local_pcursor = ''
    local_works = []
    # no_more
    state = True
    while state:
        json_data = requests.post(url, headers=sub_head('local_id'), data=sub_data(local_id, local_pcursor))
        json_data.encoding = 'UTF-8-SIG'  # 乱码解决办法
        local_works += data_analysis(json_data.text)

        local_pcursor = json.loads(json_data.text)['data']['publicFeeds']['pcursor']
        # print(local_pcursor)
        if local_pcursor == 'no_more':
            state = False
    with open('个人列表作品.txt', 'a', encoding='utf8') as fileobject:
        for d_key in local_works:
            # print(d_key)
            fileobject.write(str(d_key) + "\n")
        fileobject.close()
    print(len(local_works))

源码使用常见错误

1.提示模块requests不存在

# 因为暂时没有虚拟机，无法上图。有虚拟机再上图更新。~
# CMD界面执行
pip install requests 
# 模块安装完毕即可

鲁班工作室

关注

1
点赞
踩
17

收藏

觉得还不错? 一键收藏
2
评论
复制链接

分享到 QQ

分享到新浪微博

扫一扫

专栏目录