Python爱奇艺个人中心数据js逆向

最新推荐文章于 2024-03-29 21:13:06 发布

原创最新推荐文章于 2024-03-29 21:13:06 发布 · 1.1k 阅读

9 ·

CC 4.0 BY-SA版权

文章标签：

#python #js

爬虫档案袋专栏收录该内容

13 篇文章

订阅专栏

本文介绍如何使用Python解析爱奇艺个人中心数据，通过分析不同类别（专辑、视频、动态）的API接口，揭示其统一的加密函数L()并展示如何获取sign参数进行数据采集。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

爱奇艺个人中心数据采集

声明：本文只作学习研究，禁止用于非法用途，否则后果自负，如有侵权，请告知删除，谢谢！
目标网址链接->>> 点击跳转.
图片原因反馈很多次版权问题了，我打码了这样可以吗。
在这里插入图片描述

已覆盖动态/视频/专辑
在这里插入图片描述
分析视频/专辑/动态接口发现API都不同，但加密sign都是同一套加密函数。其中不同类别的加密通过 L()(i) 中的i的不同会得到不同的结果

    if typ==1:
        # 专辑
        st = "GETiqiyihao.iqiyi.com/iqiyihao/entity/get_album_collection_videos.action?agenttype=118&agentversion=10.7.5&albumPage={page}&albumSize=6&authcookie={authcookie}&dfp={dfp}&fuid={uid}&m_device_id=cv2irlndqb0opl8fgsydst7q&timestamp={time_stamp}&videoSize=4NZrFGv72GYppTUxO"
    elif typ==2:
        # 视频
        st = "GETiqiyihao.iqiyi.com/iqiyihao/entity/get_videos.action?agenttype=118&agentversion=10.7.5&authcookie={authcookie}&dfp={dfp}&fuid={uid}&m_device_id=cv2irlndqb0opl8fgsydst7q&page={page}&size=28&timestamp={time_stamp}NZrFGv72GYppTUxO"
    elif typ==3:
        # 动态
        st = "GETiqiyihao.iqiyi.com/iqiyihao/entity/get_dynamic_ids.action?agenttype=118&agentversion=10.7.5&authcookie={authcookie}&dfp={dfp}&fuid={uid}&m_device_id=cv2irlndqb0opl8fgsydst7q&page={page}&timestamp={time_stamp}NZrFGv72GYppTUxO"

关于函数 L() 就是md5，
tip：对于加密函数可以在页面上直接尝试加密1或者a 得到的结果就可知道是哪种加密md5(1)/bs64(1) 等等。

复制直接调用

# -*- coding:utf-8 -*-
# 享受雷霆感受雨露
# author xyy,time:2021/6/16

import re
import time
import requests
from hashlib import md5
headers = {
        'Connection': 'keep-alive',
        'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="90", "Google Chrome";v="90"',
        'sec-ch-ua-mobile': '?0',
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36',
        'Accept': '*/*',
        'Sec-Fetch-Site': 'same-site',
        'Sec-Fetch-Mode': 'no-cors',
        'Sec-Fetch-Dest': 'script',
        'Referer': 'https://www.iqiyi.com/',
        'Accept-Language': 'zh-CN,zh;q=0.9',
    }
# Md5 加密函数 32 返回32位的加密结果
def md5_use(text: str) -> str:
    result = md5(bytes(text, encoding="utf-8")).hexdigest()
    return result
# 获取加密参数 sign
def get_sign(page_num,uid,authcookie,dfp,typ=1,time_stamp=""):
    """:key
    typ 1 专辑
    typ 2 视频
    typ 3 动态
    """
    st = ""
    if typ==1:
        # 专辑
        st = "GETiqiyihao.iqiyi.com/iqiyihao/entity/get_album_collection_videos.action?agenttype=118&agentversion=10.7.5&albumPage={page}&albumSize=6&authcookie={authcookie}&dfp={dfp}&fuid={uid}&m_device_id=cv2irlndqb0opl8fgsydst7q&timestamp={time_stamp}&videoSize=4NZrFGv72GYppTUxO"
    elif typ==2:
        # 视频
        st = "GETiqiyihao.iqiyi.com/iqiyihao/entity/get_videos.action?agenttype=118&agentversion=10.7.5&authcookie={authcookie}&dfp={dfp}&fuid={uid}&m_device_id=cv2irlndqb0opl8fgsydst7q&page={page}&size=28&timestamp={time_stamp}NZrFGv72GYppTUxO"
    elif typ==3:
        # 动态
        st = "GETiqiyihao.iqiyi.com/iqiyihao/entity/get_dynamic_ids.action?agenttype=118&agentversion=10.7.5&authcookie={authcookie}&dfp={dfp}&fuid={uid}&m_device_id=cv2irlndqb0opl8fgsydst7q&page={page}&timestamp={time_stamp}NZrFGv72GYppTUxO"
    md5_str =   st.format(page=page_num,uid=uid,authcookie=authcookie,dfp=dfp,time_stamp=time_stamp)
    return md5_use(md5_str)
# 获取主页下分类内容
def get_page(page,uid,typ,jsonp_name):
    authcookie, dfp = "",""
    time_stamp = int(round(time.time() * 1000))
    if typ==3: # 需要获取动态的时候有问题 需要请求两次获取 因为他的翻页在上一页的请求中
        if page>1:
            page = "".join(re.findall(r'"page":"(.*?)"',get_page_typ3(page,uid,typ).text))
        else:
            page = "df_0_0:dv_0_0"
    sign = get_sign(page, uid, authcookie, dfp, typ, str(time_stamp))
    url = ""
    if typ==1:
        url = "https://iqiyihao.iqiyi.com/iqiyihao/entity/get_album_collection_videos.action?agenttype=118&agentversion=10.7.5&albumPage={albumPage}&albumSize=6&authcookie={authcookie}&dfp={dfp}&fuid={uid}&m_device_id=cv2irlndqb0opl8fgsydst7q&sign={sign}&timestamp={time_stamp}&videoSize=4&callback={jsonp_name}"
    elif typ==2:
        url = "https://iqiyihao.iqiyi.com/iqiyihao/entity/get_videos.action?agenttype=118&agentversion=10.7.5&authcookie={authcookie}&dfp={dfp}&fuid={uid}&m_device_id=cv2irlndqb0opl8fgsydst7q&page={page}&sign={sign}&size=28&timestamp={time_stamp}&callback={jsonp_name}"
    elif typ==3:
        url = "https://iqiyihao.iqiyi.com/iqiyihao/entity/get_dynamic_ids.action?agenttype=118&agentversion=10.7.5&authcookie={authcookie}&dfp={dfp}&fuid={uid}&m_device_id=cv2irlndqb0opl8fgsydst7q&page={page}&sign={sign}&timestamp={time_stamp}&callback={jsonp_name}"
    url = url.format(sign=sign,page=page,uid=uid,authcookie=authcookie,dfp=dfp,time_stamp=time_stamp,albumPage=page,jsonp_name=jsonp_name)
    payload = {}

    response = requests.request("GET", url, headers=headers, data=payload,proxies={})

    # print(response.text)
    return response
# 专门为了动态而活
def get_page_typ3(page,uid,typ,jsonp_name):
    authcookie, dfp = "",""
    time_stamp = int(round(time.time() * 1000))
    page = "df_0_0:dv_{}_0".format((page-1)*10)
    sign = get_sign(page, uid, authcookie, dfp, typ, str(time_stamp))
    url = "https://iqiyihao.iqiyi.com/iqiyihao/entity/get_dynamic_ids.action?agenttype=118&agentversion=10.7.5&authcookie={authcookie}&dfp={dfp}&fuid={uid}&m_device_id=cv2irlndqb0opl8fgsydst7q&page={page}&sign={sign}&timestamp={time_stamp}&callback=jsonp_1626005050286_49428"
    url = url.format(sign=sign,page=page,uid=uid,authcookie=authcookie,dfp=dfp,time_stamp=time_stamp)
    payload = {}
    response = requests.request("GET", url, headers=headers, data=payload,proxies={})
    return response

if __name__ == '__main__':
    # authcookie = "03N92J6K4m1gm33np09kuv0spG4YDgjbqwJOzcM1LzeARuMm1zMlbdeOnWK9fwpEB7isq77" # 我的世界木鱼
    # dfp = "a1e60ddab2a6f442d59979b3740faf0082372e3edd26de1171fddf0c2a25f553e8" # 我的世界木鱼
    """:key
    typ 1 专辑
    typ 2 视频
    typ 3 动态
    typ 待添加
    """
    jsonp_name = "xyy" # 默认xyy
    page = 1
    # uid = 1201201320 # 我的世界木鱼
    uid = 1015560516  # 爱小艺KG
    typ = 2
    info = get_page(page,uid,typ,jsonp_name) # 不知道的名字 有视频 / 动态
    print(info.text)