RS_zxgk/测试/shixin/shixin.py

import json
import time
from urllib import parse
import ddddocr
import requests
from rs_zxgk.shixin.RS import Get_Cookie
from rs_zxgk.shixin.Captcha import Init_Captcha
import re


class Get_Info:
    def __init__(self):
        self.Get_Cookie = Get_Cookie()
        self.session, self.ctx200, self.proxy = self.Get_Cookie.main()
        self.updateCookie = self.Get_Cookie.update_cookie
        self.initURL = "http://zxgk.court.gov.cn/shixin"
        self.CaptchaCheckURL = "http://zxgk.court.gov.cn/shixin/checkyzm.do"
        self.ListURL = "http://zxgk.court.gov.cn/zhixing/searchBzxr.do"
        self.DetailURL = "http://zxgk.court.gov.cn/zhixing/newdetail"
        self.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"
        }
        self.pCode = None
        self.ocr = ddddocr.DdddOcr()
        self.totalPage = 0
        self.Id_CaseCode = {}
        self.names = ["小明", "小白", "张三", "王五", "张伟"]
        self.file = open("test.txt", mode="w", encoding="utf-8")

    def init_page(self):
        self.updateCookie()
        init_page_response = self.session.get(url=self.initURL, headers=self.headers, proxies=self.proxy)
        #print("init_page_response ===>", init_page_response)
        if init_page_response.status_code == 412:
            print("cookie失效,重新获取ts")
            return
        self.updateCookie()

    def init_captcha(self):
        self.CaptchaURL, self.captchaId, self.MyRandom = Init_Captcha().main()
        # print("获取验证码的URL ===>",self.CaptchaURL)
        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"
        }
        CaptchaResponse = self.session.get(url=self.CaptchaURL, headers=Captcha_headers, proxies=self.proxy)
        if CaptchaResponse.status_code == 412:
            print("cookie失效,重新获取ts")
            return
        # print("请求验证码的响应结果 ===>",CaptchaResponse)
        with open("captcha.jpg", 'wb') as f:
            f.write(CaptchaResponse.content)
        self.pCode = self.ocr.classification(CaptchaResponse.content)
        # print("验证码的结果 ===>",self.pCode)
        self.updateCookie()

    def check_Captcha(self):
        self.updateCookie()
        url = "checkyzm.do?captchaId=" + self.captchaId + "&pCode=" + self.pCode + ""
        checkURL = self.ctx200.call("check_yzm", "GET", url, self.captchaId, self.pCode)
        checkURL = "http://zxgk.court.gov.cn" + checkURL
        #  print("验证码验证的URL ===>",checkURL)
        response = self.session.get(url=checkURL, headers=self.headers, proxies=self.proxy)
        if response.status_code == 412:
            print("cookie失效,重新获取ts")
            exit(0)
        if response.text.split("\n")[0] == "1":
            return True
        return False

    def check_yzm(self):
        while True:
            self.init_captcha()
            ret = self.check_Captcha()
            self.updateCookie()
            if ret == True:
                break
            else:
                print("验证失败,正在进行重新请求验证码并验证")
        #print("验证码的验证通过")

    def get_list(self, pname, currentPage):
        # print("执行了get_list")
        url = "http://zxgk.court.gov.cn"
        url = url + self.ctx200.call("get_list", "POST", "searchSX.do")
        #print("请求列表页的URL ===>", url)
        data = {
            "pName": pname,
            "pCardNum": "",
            "pProvince": "0",
            "pCode": self.pCode,
            "captchaId": self.captchaId,
            "currentPage": str(currentPage)
        }
        response = self.session.post(url=url, headers=self.headers, data=data, proxies=self.proxy)
        #print("response =>", response.text)
        if response.status_code == 412:
            print("cookie失效,重新获取ts")
            return
        try:
            result = json.loads(response.text)[0].get("result")
            self.totalPage = json.loads(response.text)[0].get("totalPage")
            for ret in result:
                self.Id_CaseCode[ret["id"]] = ret["caseCode"]
            #print("self.Id_CaseCode ===>", self.Id_CaseCode)
            self.updateCookie()
            return True
        except:
            # print(response.content.decode())
            # print("出现了error,进行刷新验证码操作")
            self.check_yzm()
            return False

    def get_detail(self):
        for id in self.Id_CaseCode:
            #("当前的id对应的caseCode ===>", self.Id_CaseCode[id])
            caseCode = parse.quote(self.Id_CaseCode[id])
            checkURL = "disDetailNew?id=" + str(
                id) + "&caseCode=" + caseCode + "&pCode=" + self.pCode + "&captchaId=" + self.captchaId
            ret = self.ctx200.call("get_detail", "GET", checkURL, self.captchaId, self.pCode, str(id), caseCode)
            ret = "http://zxgk.court.gov.cn" + ret
            #print("当前请求的详情页 ===>", ret)
            response = self.session.get(url=ret, headers=self.headers, proxies=self.proxy)
            if response.status_code == 412:
                #print("cookie失效,重新获取ts")
                exit(0)
            id = json.loads(response.text).get("id")
            #print("id =>", id)
            if id == None:
                #print(response.content.decode())
                #print("进行刷新验证码操作")
                self.init_captcha()
                self.check_Captcha()
            print("resp.text =>", response.text)
            self.file.write(response.text)
            self.file.write("\n")
            self.updateCookie()
        self.Id_CaseCode = {}

    def test(self):
        pass

    def main(self):
        self.init_page()
        self.check_yzm()
        for name in self.names:
            index = 1
            self.file.write(f"关键字 =======> {name}")
            self.file.write("\n")
            while True:
                time.sleep(0.5)
                if self.get_list(name, index):
                    self.get_detail()
                    if index == self.totalPage:
                        break
                    index += 1
            #print("index =>", index)
            #print(f"关键字为 {name} 搜索完毕")
            self.totalPage = 0
        self.file.close()


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