RS_zxgk/shixin/RS.py

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

# 用来获取cookie
class Get_Cookie():
    def __init__(self):
        self.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"
        }
        self.session = requests.session()
        self.initURL = "http://zxgk.court.gov.cn/"
        self.ctx200 = MiniRacer()

    def first_cookie(self):
        url = self.initURL
        response = self.session.get(url, headers=self.headers)
        if response.status_code == 412:
            print("第一次RS的cookie刷新", response)
        else:
            print("第一次RS的cookie刷新 出错")
            exit()
        # 拿出content标签
        content = re.findall(r'<meta content="(.*?) r=\"m">', response.text)[0].replace('"', '')

        # 获取JS路径后缀
        win_ts_url = re.findall('" src="(.*?)" r=\'m\'>', response.text)[0]

        # 匹配出$_ts
        win_ts = re.findall(r"r='m'>(.*?)</script>", response.text)[1]

        # 拼接url
        win_ts_url = parse.urljoin(self.initURL, win_ts_url)
        print("RS 412的JS的URL ===>", win_ts_url)
        # 提取出来js
        first_InnerJs = self.session.get(win_ts_url, headers=self.headers, verify=False).text

        with open('1.js', mode='r', encoding='utf-8') as f:
            code = f.read()
        JSText = code.replace('win_ts', win_ts).replace('first_InnerJs', first_InnerJs).replace('window.content',
                                                                                                str(content))
        ctx = MiniRacer()
        ctx.eval(JSText)

        FirstCookie = re.findall('lqWVdQzgOVyaT=(.*?); path=/;', ctx.call("get_cookie"))[0]
        print("FirstCookie ===>", FirstCookie)
        self.CurrentCookie = FirstCookie
        cookies = {"lqWVdQzgOVyaT": self.CurrentCookie}
        self.session.cookies.update(cookies)
        print("RS的第一次cookie更新完毕")

    def second_cookie(self):
        # 验证第一次的cookie是否有效
        url = self.initURL
        response = self.session.get(url, headers=self.headers)
        if response.status_code == 200:
            print("获得了第一次的200")
        else:
            print(self.session.cookies)
            print("第一次的200获取失败,退出程序 ===>",response)
            exit()
        print(response)
        # print(response.text)
        # 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JS的URL
        second_win_ts_url = parse.urljoin(self.initURL, second_win_ts_url)
        print("RS 200的JS的URL ===>", second_win_ts_url)
        # 提取JS
        second_InnerJs = self.session.get(second_win_ts_url, headers=self.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()
        JSText2 = code.replace('second_win_ts', second_win_ts).replace('second_InnerJs', second_InnerJs).replace(
            'window.content', str(second_content)).replace("CurrentCookie", self.CurrentCookie)
        self.ctx200.eval(JSText2)
        self.CurrentCookie = re.findall('lqWVdQzgOVyaT=(.*?); path=/;', self.ctx200.call("get_cookie"))[0]
        print("self.CurrentCookie ===>", self.CurrentCookie)
        cookies = {"lqWVdQzgOVyaT": self.CurrentCookie}
        self.session.cookies.update(cookies)
        print("RS的第二次cookie更新完毕(200页面的cookie)")

    def update_cookie(self):
        self.CurrentCookie = re.findall('lqWVdQzgOVyaT=(.*?); path=/;', self.ctx200.call("get_cookie",self.CurrentCookie))[0]
        print("self.CurrentCookie ===>", self.CurrentCookie)
        cookies = {"lqWVdQzgOVyaT": self.CurrentCookie}
        self.session.cookies.update(cookies)
        print("============================更新cookie完毕============================")

    def test_cookie(self):
        URL = "http://zxgk.court.gov.cn/zhixing/"
        test_response = self.session.get(url=URL,headers=self.headers)
        print(test_response)
        # print(test_response.text)
    def main(self):
        self.first_cookie()
        self.second_cookie()
        #self.update_cookie()
        # self.test_cookie()
        return self.session, self.ctx200

if __name__ == '__main__':
    Get_Cookie().main()