快⼿视频批量采集php,【原创开源】快⼿爬⾍，根据eid批量爬取⽤户的所有图集和视频【已失。。。
[Python] 纯⽂本查看 复制代码# -*-coding:utf-8 -*-
import requests
import time
import os
import json
import threading
import re
cookies = ""
def downVideo(video,d_url,v_name):
if not ists(video):
r = (d_url)
r.raise_for_status()
with open(video, "wb") as f:
f.t)
print(" 视频 " + v_name + " 下载成功 √")
# else:
# print(" 视频 " + v_name + " 已存在 √")
def downPic(j,pic,d_url,p_name):
if not ists(pic):
r = (d_url)
r.raise_for_status()
with open(pic, "wb") as f:
f.t)
print(" " + str(j + 1) + "/ 图⽚ " + p_name + " 下载成功 √")
# else:
# print(" " + str(j + 1) + "/ 图⽚ " + p_name + " 已存在 √")
def getCookies():
# url = 'c.m.chenzhongtech/rest/lapi/getcoo?_='+str(int(round(time.time() * 1000)))
url = 'live.kuaishou/u/3xnvh7hzw7ib9ec/3xqbgg5rrpui69c'
headers_web = {
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',图片爬虫app
'Connection': 'keep-alive',
'Host': 'live.kuaishou',
# 'Origin': 'v.kuaishou',
# 'Referer': 'v.kuaishou/fw/photo/3xqbgg5rrpui69c',
'Sec-Fetch-Dest': 'document',
'Sec-Fetch-Mode': 'navigate',
'Sec-Fetch-Site': 'none',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36',
# 'Cookie':'did=web_c78c7a3f39befb6076e5891268254f0f'
}
rs = (url=url, headers=headers_web, allow_redirects=False)
# resJson = json.t.decode(encoding='utf-8'))
global cookies
# cookies = resJson['cookies'][0].split(';')[0]
cookies = 'did='+rs.cookies._cookies['.kuaishou']['/']['did'].value
def getVideo(data):
url = 'v.kuaishou/rest/kd/feed/profile'
headers_web = {
'accept': '*/*',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
'Connection': 'keep-alive',
'Content-Type': 'application/json',
'Host': 'v.kuaishou',
'Origin': 'v.kuaishou',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'same-origin',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36',
#Cookie 根据⾃⼰的电脑修改
#'Cookie': 'did=web_6ab2aa48ebfa49c18e497b1efb80429f'
}
headers_web["Cookie"] = cookies
rs = requests.post(url=url, headers=headers_web, json=data)
v_json = json.t.decode(encoding='utf-8'))
if (str(v_json["result"])=="2"):
print("服务器返回操作太快，可能触发反爬机制")
return
feeds = v_json["feeds"]
for i in range(len(feeds)):
feed = feeds[i]
caption = str(feed["caption"]).replace("\n","").replace("\u200b","").replace("\"","").replace("\\","")[0:100] f_time = time.strftime('%Y-%m-%d %H%M%S', time.localtime(feed['timestamp'] / 1000))
name = re.sub(r'[\\/:*?"<>|\r\n]+', "", feed['userName'])
dir = "data/" + name + "(" + feed['userEid'] + ")/"
if not ists(dir):
os.makedirs(dir)
if(str(feed['singlePicture']) == "False"):
d_url = feed['mainMvUrls'][0]['url']
v_name = f_time + "_" + caption + ".mp4"
video = dir + v_name
t_downVideo = threading.Thread(target=downVideo, args=(video,d_url,v_name,))
t_downVideo.start()
else:
try:
imgList = feed['ext_params']['atlas']['list']
cdn = feed['ext_params']['atlas']['cdn'][0]
except:
imgList = []
imgList.append(str(feed['coverUrls'][0]['url']).replace("",""))
cdn = ""
for j in range(len(imgList)):
p_name = f_time + "_" + caption + "_" + str(j + 1) + ".jpg"
pic = dir + p_name
d_url = "" + cdn + imgList[j].replace("webp","jpg")
t_downPic = threading.Thread(target=downPic, args=(j,pic,d_url,p_name,))
t_downPic.start()
pcursor = v_json["pcursor"]
if(str(pcursor) != "no_more"):
data = {"eid":v_json['feeds'][0]['userEid'],"count":30,"pcursor":pcursor} getVideo(data)
if not ists("/data"):
os.makedirs("/data")
getCookies()
eidList = ["3xnvh7hzw7ib9ec","3xi4m53fqfftq94"]
for eid in eidList:
data = {"eid":eid,"count":30,"pcursor":"0"}
getVideo(data)
print("收⼯")

版权声明：本站内容均来自互联网，仅供演示用，请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系QQ:729038198，我们将在24小时内删除。