python爬取快手小姐姐视频
流程分析
一、导入需要的三方库
import re #正则表表达式文字匹配 import requests #指定url，获取网页数据 import json #转化json格式
import os #创建文件
二、确定目标地址
快手的目标地址需要在https://www.kuaishou.com网站截取请求，需要在控制台network截取，找到真正的地址https://www.kuaishou.com/graphql
url = https://www.kuaishou.com/graphql #目标网站url
三、确定数据位置
通过在network中搜索网页中显示的特定数据来确定data数据包，可以发现数据在data中。
四、伪装请求头、复制data数据
在控制台找到headers，复制里面的信息并手动转换成键值对的形式
在负载中找到以下信息，并封装到data里用于post请求
data = { #封装data数据 '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':MTRfNTU2NDg2NDBfMTY1MTE0Njk1MTk5OV_mhaLmkYdfNjA0NQ} } data = json.dumps(data) #将字典数据data转换成需要的json headers = { #伪装请求头，模拟浏览器访问 'accept': */*, 'Accept-Encoding' : gzip,deflate,br, 'Accept-Language': zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6, 'Connection': keep-alive, 'Content-Length': 1279, 'content-type': application/json, 'Cookie': clientid=3; did=web_3a9d9e97c96c8d33eddd663ef9362703; client_key=65890b29; kpf=PC_WEB; kpn=KUAISHOU_VISION; userId=55648640; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqABVSIs0T2ccYTa7qgMDgpAdRiErWNJyU1r87iKEYuIWEo_oJSNGq4aTBB5sq0bA7iLeCMOoX0grrEbBkpPmehOVWEs_tC-cDytf6dxSLnrE9-tRQaVcHziopazhh5rroA2XZmHEjHAe6z9-AHD0ZTxV9nJPHeI0-k0wfn9DHvDcj8ZUgQexbGwXDeH2wBV_WSuzutsd3d5oLNmN-90a33TXhoS6uws2LN-siMyPVYdMaXTUH7FIiBd27-7kiEEP6BHgx67BTXhdNPtfA88SZZL4Q_uQ09AuCgFMAE; kuaishou.server.web_ph=b0d04539ad2d77e13d866a70f9e56371c4a6, '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, Microsoft Edge;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(Linux;Android6.0;Nexus5 Build / MRA58N) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 99.0.4844.51Mobile Safari / 537.36 }
五、发出请求
向网站发起请求，需要用到第三方requests库，进行访问。
response = requests.post(url=url,headers=headers,data=data) #向目标网站发出请求
六、数据解析
通过re库和xpath进行数据解析，解析到需要的数据封装到列表中。
json_data = response.json() #转换json数据 #print(json_data) feed_list = json_data['data']['visionSearchPhoto']['feeds'] #在标签中找出每一项的列表 #print(feed_list) for feeds in feed_list: #循环每一项 title = feeds['photo']['caption'] #在网页中找出标题 new_title = re.sub(r'[\/:*?<>\n]','_',title) #去除标题中的特殊字符 photoUrl = feeds['photo']['photoUrl'] #找到视频的url地址 mp4_data = requests.get(photoUrl).content #转换视频二进制形式
七、保存数据
创建文件夹，并将数据保存到文件夹中。需要用到os库。
def mkdir(path): #创建文件夹 # 引入模块 import os #引入第三方库 # 去除首位空格 path = path.strip() # 去除尾部 \ 符号 path = path.rstrip(\\) # 判断路径是否存在 # 存在 True # 不存在 False isExists = os.path.exists(path) # 判断结果 if not isExists: # 如果不存在则创建目录 # 创建目录操作函数 os.makedirs(path) print(path + ' 创建成功') return True else: # 如果目录存在则不创建，并提示目录已存在 print(path + ' 目录已存在') return False
with open(keyword+'/'+ new_title +'.mp4',mode=wb) as f: #设定保存数据路径 f.write(mp4_data) #保存数据 print(保存成功！,new_title)
完整源代码
# -*- coding = utf-8 -*- # @Time : 2022/4/28 10:48 # @Author :王敬博 # @File : 快手小姐姐.py # @Software: PyCharm import re #正则表表达式文字匹配 import requests #指定url，获取网页数据 import json #转化json格式 def mkdir(path): #创建文件夹 # 引入模块 import os #引入第三方库 # 去除首位空格 path = path.strip() # 去除尾部 \ 符号 path = path.rstrip(\\) # 判断路径是否存在 # 存在 True # 不存在 False isExists = os.path.exists(path) # 判断结果 if not isExists: # 如果不存在则创建目录 # 创建目录操作函数 os.makedirs(path) print(path + ' 创建成功') return True else: # 如果目录存在则不创建，并提示目录已存在 print(path + ' 目录已存在') return False url = https://www.kuaishou.com/graphql #目标网站url keyword = input(请输入想要搜索的关键词) #搜索关键字 mkpath = d:\\pywork\\demo02\\+keyword #创建的文件路径 mkdir(mkpath) #调用函数，创建文件夹 for page in range(1,5): #爬取4页 print(==================第%d页=================%page) #打印爬取的页数 data = { #封装data数据 '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':MTRfNTU2NDg2NDBfMTY1MTE0Njk1MTk5OV_mhaLmkYdfNjA0NQ} } data = json.dumps(data) #将字典数据data转换成需要的json headers = { #伪装请求头，模拟浏览器访问 'accept': */*, 'Accept-Encoding' : gzip,deflate,br, 'Accept-Language': zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6, 'Connection': keep-alive, 'Content-Length': 1279, 'content-type': application/json, 'Cookie': clientid=3; did=web_3a9d9e97c96c8d33eddd663ef9362703; client_key=65890b29; kpf=PC_WEB; kpn=KUAISHOU_VISION; userId=55648640; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqABVSIs0T2ccYTa7qgMDgpAdRiErWNJyU1r87iKEYuIWEo_oJSNGq4aTBB5sq0bA7iLeCMOoX0grrEbBkpPmehOVWEs_tC-cDytf6dxSLnrE9-tRQaVcHziopazhh5rroA2XZmHEjHAe6z9-AHD0ZTxV9nJPHeI0-k0wfn9DHvDcj8ZUgQexbGwXDeH2wBV_WSuzutsd3d5oLNmN-90a33TXhoS6uws2LN-siMyPVYdMaXTUH7FIiBd27-7kiEEP6BHgx67BTXhdNPtfA88SZZL4Q_uQ09AuCgFMAE; kuaishou.server.web_ph=b0d04539ad2d77e13d866a70f9e56371c4a6, '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, Microsoft Edge;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(Linux;Android6.0;Nexus5 Build / MRA58N) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 99.0.4844.51Mobile Safari / 537.36 } response = requests.post(url=url,headers=headers,data=data) #向目标网站发出请求 json_data = response.json() #转换json数据 #print(json_data) feed_list = json_data['data']['visionSearchPhoto']['feeds'] #在标签中找出每一项的列表 #print(feed_list) for feeds in feed_list: #循环每一项 title = feeds['photo']['caption'] #在网页中找出标题 new_title = re.sub(r'[\/:*?<>\n]','_',title) #去除标题中的特殊字符 photoUrl = feeds['photo']['photoUrl'] #找到视频的url地址 mp4_data = requests.get(photoUrl).content #转换视频二进制形式 with open(keyword+'/'+ new_title +'.mp4',mode=wb) as f: #设定保存数据路径 f.write(mp4_data) #保存数据 print(保存成功！,new_title) 效果展示
总结
这次爬取的流程以及源代码是从bili的课程中学到的，大概用了3个小时左右，个人感觉第一次爬取动态网页还是找到数据是比较难的。通过这次实践我终于体会到了程序员的快乐(谁不喜欢看小姐姐呢)，嘿嘿嘿!
如果有问题可以私聊我，如果对你有帮助的话，记得个赞哦！