python采集快手视频及评论数据并作自动点赞操作~

python芊 2022-07-19 发布于湖南

展开全文

前言

嗨喽，大家好呀~这里是爱看美女的茜茜呐

今天我们要采集的网站呢，它是一款国民级短视频App。

在它那里,了解真实的世界,认识有趣的人,也可以记录真实而有趣的自己。 🛫

现在，话不多说，让我们开始叭 ⛱

本篇代码提供者：青灯教育-巳月

知识点:

动态数据抓包
requests发送请求
json数据解析

准备工作

python 3.8 运行代码
pycharm 2021.2 辅助敲代码
requests 第三方模块

代码实现:

发送请求
获取数据
解析数据
保存数据

代码

采集视频

导入模块

import requests         # 导入请求模块
import re

加入伪装

# 服务器 识别 你是不是一个正常用户
headers = {
    'content-type': 'application/json',
    'Cookie': 'kpf=PC_WEB; kpn=KUAISHOU_VISION; clientid=3; did=web_d3f9d8c2cbebafd126b80eb0b1c13360; client_key=65890b29; userId=270932146; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqABH5pXBjDW6tX4vO3hi0mofxvSjVsHg6LatW99bMWA3KrRx_WY1RxCgq6BtAVnGDjqgm8RsWPrOJHukiYbXTmH_oFeSlNsOVIz4Ymg2x_wybN0bT-G-soz4woc62rMc5g-QkghtJkGFnl2dLiX7vfScrR1k2eequu1Sb75AelVzJHMI-6112E_BA8UXRmBpDcA7fzWbzJnEH0p7I6OiAJn1BoSf061Kc3w5Nem7YdpVBmH39ceIiBdj1aQWaSUYM-4rqViwshbJuwtgX0NJfI_52HdjZ6_MygFMAE; kuaishou.server.web_ph=8c6a5419c9f21478baa04f79fbf6c7283c13',
    'Host': 'www.kuaishou.com',
    'Origin': 'https://www.kuaishou.com',
    'Referer': 'https://www.kuaishou.com/search/video?searchKey=%E8%BE%A3%E5%A6%B9',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36',
}
for page in range(1, 11):
    json = {
        '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': "辣妹", 'pcursor': str(page), 'page': "search", 'searchSessionId': "MTRfMjcwOTMyMTQ2XzE2NTc3MTQ0MDUwMTZf6L6j5aa5Xzk1NDU"}
    }
    # x = 1, y = 2, z = 3

发送请求

    url = 'https://www.kuaishou.com/graphql'
    response = requests.post(url=url, headers=headers, json=json)

<Response [200]>: 请求成功

python 里面字典可以转变为 json类型字符串

前后端数据交互

.json()取出来的就是字典格式

获取数据

    json_data = response.json()

解析数据

源码、解答、教程加Q裙：832157862
    feeds = json_data['data']['visionSearchPhoto']['feeds']    for i in range(len(feeds)):        # 字典 列表
        caption = feeds[i]['photo']['caption']
        photoUrl = feeds[i]['photo']['photoUrl']        # 正则替换 可以替换掉 字符串里面的字符
        caption = re.sub('[\\/:*?"<>|\\n]', '', caption)
        print(caption, photoUrl)

保存数据

        video_data = requests.get(photoUrl).content
        open(f'video/{caption}.mp4', mode='wb').write(video_data)

采集评论

源码、解答、教程加Q裙：832157862
import requests

headers = {
    'content-type': 'application/json',
    'Cookie': 'kpf=PC_WEB; kpn=KUAISHOU_VISION; clientid=3; did=web_d3f9d8c2cbebafd126b80eb0b1c13360; client_key=65890b29; userId=270932146; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqABoMUaybC2UKr2MOuXtaCMlS0my2AJe2dE2crt0WKNd6n2_hWQlTHuEfB_l5yq5WEV-kbR4SSKebmVxd__N3y98rvOpZtEtTssidKptKitcRQA3_VuIfXKYDrOvmsKrLDo0l8u5-GXzDzbLrjLm2E14U65DCDSweVNdOqSCgDQh9gjxOCKWMG4sCZO-rhYHYi1pN4c-kn1SZcgSh8ItP6WOxoS8JByODRPv5hk-B95zTquvFHcIiD38YeNZzgktz_RU3mo3dDlFag5UaRViIBk-xbucAuJDSgFMAE; kuaishou.server.web_ph=21ef9689a064ff74dfbc5e3f00c440696d0d',
    'Host': 'www.kuaishou.com',
    'Origin': 'https://www.kuaishou.com',
    'Referer': 'https://www.kuaishou.com/short-video/3xk7fvrbbqektni?authorId=3xeb7adrir6iny9&streamSource=search&area=searchxxnull&searchKey=%E8%BE%A3%E5%A6%B9&currentPcursor=1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36',
}
json = {
    'operationName': "visionAddComment",
    'query': "mutation visionAddComment($photoId: String, $photoAuthorId: String, $content: String, $replyToCommentId: ID, $replyTo: ID, $expTag: String) {\n  visionAddComment(photoId: $photoId, photoAuthorId: $photoAuthorId, content: $content, replyToCommentId: $replyToCommentId, replyTo: $replyTo, expTag: $expTag) {\n    result\n    commentId\n    content\n    timestamp\n    status\n    __typename\n  }\n}\n",
    'variables': {
        'content': "不好",
        'expTag': "1_i/2005259440785868865_xpcwebsearchxxnull0",
        'photoAuthorId': "3xeb7adrir6iny9",
        'photoId': "3xk7fvrbbqektni"
    }
}
url = 'https://www.kuaishou.com/graphql'
response = requests.post(url=url, headers=headers, json=json)

实现自动点赞

# 网页里面的所有操作 点赞 发布评论 访问网站 下单 预约...
# 发送请求
# 分析数据来源
# https://www.kuaishou.com/graphql
# json 请求体 有区别
import requests
源码、解答、教程加Q裙：832157862
headers = {
    'content-type': 'application/json',
    'Cookie': 'kpf=PC_WEB; kpn=KUAISHOU_VISION; clientid=3; did=web_d3f9d8c2cbebafd126b80eb0b1c13360; client_key=65890b29; userId=270932146; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqAB8HEt1O6Ahi5XgrkkTFeYhp0xHyR0XW_-_xE7ccfDb3W_gPVA53sBXEk0qMFYounhic9pa97jqNrN12ll8dFi0aTKu-esFbPDlxwZrJMaugua7_C-TU4MiQs9boYD4uXCs2qiDmeCxyfpi2sxN-htiwYZJcyomKDMitAApaX6-HwgCqJ3LXlTnwg9hC9K3sQK4c3wjmKJKV9ABJILoQQdVxoSg3ZkWJHNsQvvc8vsvUksYr6BIiDWS1rGE8d_0kelcNUomvyiQjxk2bKONmeM5GDJSz0f4SgFMAE; kuaishou.server.web_ph=61e920d14e1e0abfae19521be99015ba22df',
    'Host': 'www.kuaishou.com',
    'Origin': 'https://www.kuaishou.com',
    'Referer': 'https://www.kuaishou.com/short-video/3xk7fvrbbqektni?authorId=3xeb7adrir6iny9&streamSource=search&area=searchxxnull&searchKey=%E8%BE%A3%E5%A6%B9&currentPcursor=1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36',
}
json = {
    'operationName': "visionVideoLike",
    'query': "mutation visionVideoLike($photoId: String, $photoAuthorId: String, $cancel: Int, $expTag: String) {\n  visionVideoLike(photoId: $photoId, photoAuthorId: $photoAuthorId, cancel: $cancel, expTag: $expTag) {\n    result\n    __typename\n  }\n}\n",
    'variables': {
        'cancel': 0,
        'expTag': "1_i/2001449839044035650_xpcwebsearchxxnull0",
        'photoAuthorId': "3xeb7adrir6iny9",
        'photoId': "3xk7fvrbbqektni"
    }
}
url = 'https://www.kuaishou.com/graphql'
response = requests.post(url=url, headers=headers, json=json)