RS_zxgk/412-200.py

import requests
import re,json,random,time
from py_mini_racer import MiniRacer
from urllib import parse
from chaojiying import Chaojiying_Client

headers = {
    "Connection": "keep-alive",
    "Pragma": "no-cache",
    "Cache-Control": "no-cache",
    "Upgrade-Insecure-Requests": "1",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36",
    "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=0.9",
    "Referer": "http://zxgk.court.gov.cn/",
    "Accept-Language": "zh-CN,zh;q=0.9"
}



def get_cookie_first(url):
    cookies = {}

    session = requests.session()
    # 第一次访问412
    html = session.get(url, headers=headers)
    print("第一次访问的结果 ===>",html)

    # 拿出content标签
    content = re.findall(r'<meta content="(.*?) r=\"m">', html.text)[0].replace('"', '')
    # 获取JS路径后缀
    win_ts_url = re.findall('" src="(.*?)" r=\'m\'>', html.text)[0]
    # 拼接url
    win_ts_url = parse.urljoin(url, win_ts_url)
    #提取出来js
    InnerJs = requests.get(win_ts_url, headers=headers, verify=False).text
    # 匹配出$_ts
    win_ts = re.findall(r"r='m'>(.*?)</script>", html.text)[1]
    with open('1.js', mode='r', encoding='utf-8') as f:
        code = f.read()
    js_txt = code.replace('window.win_ts', win_ts).replace('window.zhiyuan', InnerJs).replace('window.content',
                                                                                              str(content))
    ctx = MiniRacer()
    ctx.eval(js_txt)
    cookie = re.findall('lqWVdQzgOVyaT=(.*?); p', ctx.call("update_cookie"))[0]
    print("第一次cookie = ", cookie)
    cookies['lqWVdQzgOVyaT'] = cookie
    session.cookies.update(cookies)
    response = session.get(url, headers=headers)
    print("更新412的cookie后请求的结果 ===>",response)
    ##############################################200后的操作########################################
    # 拿出content标签
    second_content = re.findall(r'<meta content="(.*?) r=\"m">', response.text)[0].replace('"', '')
    # 获取JS路径后缀
    obj = re.compile(r'<script type="text/javascript" charset="utf-8" src="(?P<win_ts_url>.*?)" r=\'m\'></script>',
                     re.S)
    second_win_ts_url = ""
    result = obj.finditer(response.text)
    for i in result:
        second_win_ts_url = i.group("win_ts_url")
    # 拼接url
    second_win_ts_url = parse.urljoin(url, second_win_ts_url)
    # 提取出来js
    second_InnerJs = requests.get(second_win_ts_url, headers=headers, verify=False).text
    # 匹配出$_ts
    second_win_ts = re.findall(r"r='m'>(.*?)</script>", response.text)[1]
    with open('2.js', mode='r', encoding='utf-8') as f:
        code = f.read()
    js_txt2 = code.replace('window.win_ts',second_win_ts).replace('window.zhiyuan111',second_InnerJs).replace('window.content',str(second_content)).replace("window.aaaaa",cookie)
    ctx2 = MiniRacer()
    ctx2.eval(js_txt2)

    #200页面生成的cookie
    new_cookie = re.findall('lqWVdQzgOVyaT=(.*?); p', ctx2.call("get_cookie", cookie))[0]  # Search_First_Page
    print("200更新cookie为: ", len(new_cookie), new_cookie)
    session.cookies.set("lqWVdQzgOVyaT", new_cookie)

    while True:
        new_cookie = update_cookie(ctx2,session,new_cookie)
        test_headers = {
            "Connection": "keep-alive",
            "Pragma": "no-cache",
            "Cache-Control": "no-cache",
            "Upgrade-Insecure-Requests": "1",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36",
            "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=0.9",
            "Referer": "http://zxgk.court.gov.cn/",
            "Accept-Language": "zh-CN,zh;q=0.9"
        }
        url = "http://zxgk.court.gov.cn/zhixing/"
        test_response = session.get(url=url,headers=test_headers,verify=False)
        print(test_response)
        if test_response.status_code == 200:
            break
        time.sleep(1)

    captcha_str,captchaId = yzm(session,ctx2,new_cookie)

    while True:
        new_cookie = update_cookie(ctx2, session, new_cookie)
        result = get_sxmd(session,captcha_str,captchaId,ctx2)
        if result == True:
            break

def update_cookie(ctx2,session,cookie):
    new_cookie = re.findall('lqWVdQzgOVyaT=(.*?); p', ctx2.call("update_cookie", cookie))[0]
    print("更新cookie为: ", len(new_cookie), new_cookie)
    session.cookies.set("lqWVdQzgOVyaT", new_cookie)
    return new_cookie


def get_captchaId():
    chars = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A',
             'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M',
             'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y',
             'Z', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k',
             'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w',
             'x', 'y', 'z']
    nums = ""
    for i in range(32):
        ids = int(random.random() * 61)
        nums += chars[ids]
    return nums


def yzm(session,ctx2,new_cookie):
    captcha_headers = {
        "Connection": "keep-alive",
        "Pragma": "no-cache",
        "Cache-Control": "no-cache",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36",
        "Accept": "image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8",
        "Referer": "http://zxgk.court.gov.cn/zhixing/",
        "Accept-Language": "zh-CN,zh;q=0.9"
    }
    captchaId = get_captchaId()
    print("captchaId ===>",captchaId)
    params = {
        "captchaId": captchaId,
        "random": str(random.random())
    }
    try:
        captcha_str = ""
        response_captcha = session.get("http://zxgk.court.gov.cn/zhixing/captcha.do",headers=captcha_headers,params=params)
        print("验证码的响应 ===>",response_captcha)
        with open("captcha.jpg","wb") as f:
            f.write(response_captcha.content)
        if response_captcha.status_code == 200:
            chaojiying = Chaojiying_Client('15985724690', 'a520520a', '923160')
            captcha_str = chaojiying.PostPic(response_captcha.content, 1005).get('pic_str')
            print("验证码的结果 ===>",captcha_str)
            #激活操作
            yzm_url = f"checkyzm.do?captchaId={captchaId}&pCode={captcha_str}"
            yzm_url = ctx2.call("get_bzxr_hz","GET",yzm_url,captchaId,captcha_str,str(int(time.time() * 1000)))
            print("yzm_url ===>",yzm_url)
            new_cookie = update_cookie(ctx2,session,new_cookie)
            session.cookies.set("lqWVdQzgOVyaT", new_cookie)
            yzm_url = "http://zxgk.court.gov.cn" + yzm_url
            print("验证码的验证的url ===>",yzm_url)
            yzm_response = session.get(url=yzm_url,headers=headers,verify=False)
            print("验证码的验证 ===>",yzm_response.text)
    except:
        print("验证码error")
    return captcha_str, captchaId

def get_sxmd(session,captcha_str,captchaId,ctx2):
    headers = {
        "Connection": "keep-alive",
        "Pragma": "no-cache",
        "Cache-Control": "no-cache",
        "Accept": "application/json, text/javascript, */*; q=0.01",
        "X-Requested-With": "XMLHttpRequest",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36",
        "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
        "Origin": "http://zxgk.court.gov.cn",
        "Referer": "http://zxgk.court.gov.cn/zhixing/",
        "Accept-Language": "zh-CN,zh;q=0.9"
    }

    url = "http://zxgk.court.gov.cn/zhixing/searchBzxr.do"

    data = {
        "pName": "张三",
        "pCardNum": "",
        "selectCourtId": "0",
        "pCode": captcha_str,
        "captchaId": captchaId,
        "searchCourtName": "全国法院（包含地方各级法院）",
        "selectCourtArrange": "1",
        "currentPage": "1"
    }
    response = session.post(url=url, headers=headers, data=data, verify=False)

    print(response.text)
    print(response)

    currentTime = str(int(time.time() * 1000))
    url = f"newdetail?id=1582536987&j_captcha={captcha_str}&captchaId={captchaId}&_={currentTime}"
    new_url = ctx2.call("get_bzxr_hz", "GET", url, captchaId, captcha_str, currentTime)
    new_url = "http://zxgk.court.gov.cn" + new_url
    print(new_url)
    response = session.get(new_url, headers=headers, verify=False)
    print("response.text =====>",response.text)
    print(response)
    exit()


get_cookie_first("http://zxgk.court.gov.cn/")