crawlab_feader/FworkSpider/crawl_func/YunSuoAutoJump.py

# -*- coding: utf-8 -*-
"""
Created on 2023-09-12 
---------
@summary: cookies -> security_session_mid_verify
---------
@author: Lzz
"""
import time

import requests
import execjs


def yun_suo_auto_jump_by_js(url):
    ctx = execjs.compile('''
        function YunSuoAutoJump(url) {
            function stringToHex(str) {
                var val = "";
                for (var i = 0; i < str.length; i++) {
                    if (val == "") val = str.charCodeAt(i).toString(16); else val += str.charCodeAt(i).toString(16);
                }
                return val;
            }
            var width = 1536;
            var height = 864;
            var screendate = width + "," + height;
            location = url + "?security_verify_data=" + stringToHex(screendate);
            return location
        }
    ''')
    return ctx.call("YunSuoAutoJump", url)


def string_to_hex(s):
    # 将字符串中的每个字符转换为十六进制，不添加0x前缀
    return ''.join([format(ord(char), 'x') for char in s])


def yun_suo_auto_jump_by_py(url):
    width = 1536
    height = 864
    screen_data = f"{width},{height}"
    # 生成包含安全验证数据的URL
    return f"{url}?security_verify_data={string_to_hex(screen_data)}"


def yun_suo_auto_jump(url, platform='py'):
    if platform == 'js':
        return yun_suo_auto_jump_by_js(url)
    else:
        return yun_suo_auto_jump_by_py(url)


def get_mid_code(url, proxies=None, platform=None):
    headers = {
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Cache-Control": "no-cache",
        "Connection": "keep-alive",
        "Pragma": "no-cache",
        "Upgrade-Insecure-Requests": "1",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36"
    }
    with requests.session() as session:
        session.proxies = proxies
        request_params = dict(headers=headers, timeout=60, verify=False)
        session.get(url, **request_params)
        yz_url = yun_suo_auto_jump(url, platform=platform)

        count, cookies = 0, {}
        while count < 10:
            session.get(yz_url, headers=headers, timeout=60, verify=False)
            cookies = session.cookies.get_dict()
            if cookies.get('security_session_mid_verify'):
                break
            count += 1
            time.sleep(2)
        return cookies