自从快手出了网页版，使用Python爬起来爽多了，再也不用fiddler抓包了。
import json
import re
import os
import requests
import urllib.request
from multiprocessing import Pool
requestUrl = 'https://video.kuaishou.com/graphql'
folder_path = 'D:\kuaishou'
userId=''
cookie = ''
pcursor = ''
def post(userId,Cookie,pcursor):
data = {"operationName":"visionProfilePhotoList","variables":{"userId":userId,"pcursor":pcursor,"page":"profile"},"query":"query 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 type\n author {\n id\n name\n following\n headerUrl\n headerUrls {\n cdn\n url\n __typename\n }\n __typename\n }\n tags {\n type\n name\n __typename\n }\n photo {\n id\n duration\n caption\n likeCount\n realLikeCount\n coverUrl\n coverUrls {\n cdn\n url\n __typename\n }\n photoUrls {\n cdn\n url\n __typename\n }\n photoUrl\n liked\n timestamp\n expTag\n animatedCoverUrl\n stereoType\n videoRatio\n __typename\n }\n canAddComment\n currentPcursor\n llsid\n status\n __typename\n }\n hostName\n pcursor\n __typename\n }\n}\n"}
failed = {'msg': 'failed...'}
headers = {
'Host':'video.kuaishou.com',
'Connection':'keep-alive',
'Content-Length':'1261',
'accept':'*/*',
'User-Agent':'Mozilla/5.0(WindowsNT10.0;Win64;x64)AppleWebKit/537.36(KHTML,likeGecko)Chrome/89.0.4389.114Safari/537.36Edg/89.0.774.68',
'content-type':'application/json',
'Origin':'https://video.kuaishou.com',
'Sec-Fetch-Site':'same-origin',
'Sec-Fetch-Mode':'cors',
'Sec-Fetch-Dest':'empty',
'Referer':'https://video.kuaishou.com/profile/' + userId,
'Accept-Language':'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
'Cookie':Cookie,
}
r = requests.post(requestUrl, data=json.dumps(data), headers=headers)
r.encoding = 'UTF-8'
html = r.text
return html
def down(feeds):
for feed in feeds:
#print(feed['photo']['caption'])
#print(feed['photo']['photoUrl'])
author = feed['author']['name']
filename = feed['photo']['caption']
if not os.path.exists(folder_path + '/' + author + '/'):
os.makedirs(path)
filepath = folder_path + '/' + author + '/' + filename + '.mp4'
filepath.replace("~", "")
if not os.path.exists(filepath):
urllib.request.urlretrieve(feed['photo']['photoUrl'], filename=filepath)
print(filepath + ",下载完成")
else:
print(filepath + ",已存在，跳过")
if __name__ == "__main__":
p = Pool(10)
while True:
result = post(userId,cookie,pcursor)
data = json.loads(result)
pcursor = data['data']['visionProfilePhotoList']['pcursor']
feeds = data['data']['visionProfilePhotoList']['feeds']
for feed in feeds:
print(feed['photo']['caption'])
p.apply_async(down, args=(feeds,))
#down(feeds)
if pcursor is '':
break
print('Waiting for all subprocesses done...')
p.close()
p.join()
print('All subprocesses done.')