前言 😋
嗨喽，大家好呀~这里是爱看美女的茜茜呐
技术赋能，用科技提升每个人独特的幸福感。
在快上，用户可以用照片和短视频记录自己的生活点滴，也可以通过直播与粉丝实时互动。
快的内容覆盖生活的方方面面，用户遍布全国各地。
在这里，人们能找到自己喜欢的内容，找到自己感兴趣的人，看到更真实有趣的世界，也可以让世界发现真实有趣的自己。
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 2021.2 辅助敲代码
requests 第三方模块 发送请求 Python工具 访问网站
代码实现:
发送请求
获取数据
解析数据
保存数据
采集视频代码
导入模块
import requests # 第三方模块 发送请求
import re
伪装
headers = {
'content-type': 'application/json',
'Cookie': 'kpf=PC_WEB; kpn=KUAISHOU_VISION; clientid=3; did=web_d3f9d8c2cbebafd126b80eb0b1c13360; client_key=65890b29; didv=1658130458000; userId=270932146; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqABymzXlGDinYWz3v5NKZWKq6Ld14uOvyRNPT3Gi7uJwI8CE4aatjowKRbPtRt5YIE3s2otZdFEzL7kvW1PQuijqUT_qUe4-u0FlfN1S49mhR4QRc9YKQNObXAPYzZRWIRcrSvdohIwUW8TBTSWLUtMlMh2He2FyvNMR-JfhUHaK-YSkwqXKUj-N-zlHTCPp0z0y6cSgrR9RIdlXqIJFifSbxoSsguEA2pmac6i3oLJsA9rNwKEIiB86mXKYIgbGBbtkVuyoy8TCIwZ2uckiTnfAGZiyV9imCgFMAE; kuaishou.server.web_ph=7353170c91b8f7f05c250730c2faea5355e1',
'Host': 'www.kuaishou.com',
'Origin': 'https://www.kuaishou.com',
'Referer': 'https://www.kuaishou.com/search/video?searchKey=%E6%B3%B3%E8%A3%85%E5%B0%8F%E5%A7%90%E5%A7%90',
'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):
# post请求里面才会有
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': "泳装小姐姐", 'pcursor': str(page), 'page': "search", 'searchSessionId': "MTRfMjcwOTMyMTQ2XzE2NTg5MjM5NDExODBf5rOz6KOF5bCP5aeQ5aeQXzE4NzQ"}
}
url = 'https://www.kuaishou.com/graphql'
1. 发送请求
response = requests.post(url=url, headers=headers, json=json)
<Response [200]>: 请求成功
<Response [400]>: 没有在服务器里面找到你想要的资源
给不给你数据 是两回事
2. 获取数据
.text: 字符串
.json(): 字典类型数据
json_data = response.json()
3. 解析数据
xpath
css 只能取网页源代码里面数据的
re 如果当 xpath 和 css 和 json 都不可以用的时候 都可以取 (复杂)
json 只能取 {"":""} ["", ""]
feeds = json_data['data']['visionSearchPhoto']['feeds']
for i in range(0, len(feeds)):
photoUrl = feeds[i]['photo']['photoUrl']
caption = feeds[i]['photo']['caption']
print(caption, photoUrl)
caption = re.sub('[\\/:*?"<>|\\n]', '', caption)
4. 保存视频
一般情况下, 大部分网站 视频链接 图片链接 音频链接 都可以直接用get
.content: 获取视频二进制数据
video_data = requests.get(photoUrl).content
with open(f'video/{caption}.mp4', mode='wb') as f:
f.write(video_data)
自动评论, 自动点赞
import requests
class KuaiShou():
def __init__(self):
self.headers = {
'content-type': 'application/json',
'Cookie': 'kpf=PC_WEB; kpn=KUAISHOU_VISION; clientid=3; did=web_d3f9d8c2cbebafd126b80eb0b1c13360; client_key=65890b29; didv=1658130458000; userId=270932146; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqABymzXlGDinYWz3v5NKZWKq6Ld14uOvyRNPT3Gi7uJwI8CE4aatjowKRbPtRt5YIE3s2otZdFEzL7kvW1PQuijqUT_qUe4-u0FlfN1S49mhR4QRc9YKQNObXAPYzZRWIRcrSvdohIwUW8TBTSWLUtMlMh2He2FyvNMR-JfhUHaK-YSkwqXKUj-N-zlHTCPp0z0y6cSgrR9RIdlXqIJFifSbxoSsguEA2pmac6i3oLJsA9rNwKEIiB86mXKYIgbGBbtkVuyoy8TCIwZ2uckiTnfAGZiyV9imCgFMAE; kuaishou.server.web_ph=7353170c91b8f7f05c250730c2faea5355e1',
'Host': 'www.kuaishou.com',
'Origin': 'https://www.kuaishou.com',
'Referer': 'https://www.kuaishou.com/search/video?searchKey=%E6%B3%B3%E8%A3%85%E5%B0%8F%E5%A7%90%E5%A7%90',
'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'
}
self.url = 'https://www.kuaishou.com/graphql'
def getSearch(self, keyword, page):
"""
源码、解答、教程加Q裙：261823976
获取搜索视频
:param keyword: 关键字
:param page: 页码
:return: json_data
"""
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: $webPageArea) {\n result\n llsid\n webPageArea\n feeds {\n ...feedContent\n __typename\n }\n searchSessionId\n pcursor\n aladdinBanner {\n imgUrl\n link\n __typename\n }\n __typename\n }\n}\n",
'variables': {'keyword': keyword, 'pcursor': str(page), 'page': "search",
'searchSessionId': "MTRfMjcwOTMyMTQ2XzE2NTg5MjM5NDExODBf5rOz6KOF5bCP5aeQ5aeQXzE4NzQ"}
}
json_data = requests.post(url=self.url, headers=self.headers, json=json).json()
return json_data
def isLike(self, photoAuthorId, photoId):
"""
点赞操作
:param photoAuthorId: 作品的作者id
:param photoId: 作品id
:return:
"""
json = {
'operationName': "visionVideoLike",
'query': "mutation visionVideoLike($photoId: String, $photoAuthorId: String, $cancel: Int, $expTag: String) {\n visionVideoLike(photoId: $photoId, photoAuthorId: $photoAuthorId, cancel: $cancel, expTag: $expTag) {\n result\n __typename\n }\n}\n",
'variables': {
'cancel': 0,
'expTag': "1_a/2001481596260506114_xpcwebsearchxxnull0",
'photoAuthorId': photoAuthorId,
'photoId': photoId
}
}
json_data = requests.post(url=self.url, headers=self.headers, json=json).json()
return json_data
def postComment(self, content, photoAuthorId, photoId):
"""
发布评论
:param content: 评论内容
:param photoAuthorId: 作品的作者id
:param photoId: 作者id
:return:
"""
json = {
'operationName': "visionAddComment",
'query': "mutation visionAddComment($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: $expTag) {\n result\n commentId\n content\n timestamp\n status\n __typename\n }\n}\n",
'variables': {
'content': content,
'expTag': "1_a/2001481596260506114_xpcwebsearchxxnull0",
'photoAuthorId': photoAuthorId,
'photoId': photoId
}
}
json_data = requests.post(url=self.url, headers=self.headers, json=json).json()
return json_data
def getComment(self, photoId, pcursor):
"""
获取评论
:param photoId: 作品id
:param pcursor: 页码
:return: 评论内容
"""
json = {
'operationName': "commentListQuery",
'query': "query commentListQuery($photoId: String, $pcursor: String) {\n visionCommentList(photoId: $photoId, pcursor: $pcursor) {\n commentCount\n pcursor\n rootComments {\n commentId\n authorId\n authorName\n content\n headurl\n timestamp\n likedCount\n realLikedCount\n liked\n status\n subCommentCount\n subCommentsPcursor\n subComments {\n commentId\n authorId\n authorName\n content\n headurl\n timestamp\n likedCount\n realLikedCount\n liked\n status\n replyToUserName\n replyTo\n __typename\n }\n __typename\n }\n __typename\n }\n}\n",
'variables': {'photoId': photoId, 'pcursor': str(pcursor)}
}
json_data = requests.post(url=self.url, headers=self.headers, json=json).json()
return json_data
def getUserInfo(self, userId):
"""
获取用户信息
:param userId: 用户id
:return:
"""
json = {
'operationName': "visionProfile",
'query': "query visionProfile($userId: String) {\n visionProfile(userId: $userId) {\n result\n hostName\n userProfile {\n ownerCount {\n fan\n photo\n follow\n photo_public\n __typename\n }\n profile {\n gender\n user_name\n user_id\n headurl\n user_text\n user_profile_bg_url\n __typename\n }\n isFollowing\n __typename\n }\n __typename\n }\n}\n",
'variables': {'userId': userId}
}
json_data = requests.post(url=self.url, headers=self.headers, json=json).json()
return json_data
def getUserPhoto(self, userId, pcursor):
"""
获取用户作品
:param userId: 用户id
:param pcursor: 页码参数
:return:
"""
json = {
'operationName': "visionProfilePhotoList",
'query': "fragment photoContent on PhotoEntity {\n id\n duration\n caption\n likeCount\n viewCount\n realLikeCount\n coverUrl\n photoUrl\n photoH265Url\n manifest\n manifestH265\n videoResource\n coverUrls {\n url\n __typename\n }\n timestamp\n expTag\n animatedCoverUrl\n distance\n videoRatio\n liked\n stereoType\n profileUserTopPhoto\n __typename\n}\n\nfragment feedContent on Feed {\n type\n author {\n id\n name\n headerUrl\n following\n headerUrls {\n url\n __typename\n }\n __typename\n }\n photo {\n ...photoContent\n __typename\n }\n canAddComment\n llsid\n status\n currentPcursor\n __typename\n}\n\nquery visionProfilePhotoList($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': userId, 'pcursor': pcursor, 'page': "profile"}
}
json_data = requests.post(url=self.url, headers=self.headers, json=json).json()
return json_data
if __name__ == '__main__':
kuaishou = KuaiShou()
尾语 💝
感谢你观看我的文章呐~本次航班到这里就结束啦 🛬
希望本篇文章有对你带来帮助 🎉，有学习到一点知识~
躲起来的星星🍥也在努力发光，你也要努力加油（让我们一起努力叭）。
最后，博主要一下你们的三连呀（点赞、评论、收藏），不要钱的还是可以搞一搞的嘛~
不知道评论啥的，即使扣个6666也是对博主的鼓舞吖 💞 感谢 💐
