RS_zxgk/zhixing/zhixing.py

import json
import time

import ddddocr
from RS import Get_Cookie
from Captcha import Init_Captcha
import re

class Get_Info:
    def __init__(self):
        self.Get_Cookie = Get_Cookie()
        self.session, self.ctx200 = self.Get_Cookie.main()
        self.updateCookie = self.Get_Cookie.update_cookie
        self.initURL = "http://zxgk.court.gov.cn/zhixing"
        self.ListURL = "http://zxgk.court.gov.cn/zhixing/searchBzxr.do"
        self.pCode = None
        self.ocr = ddddocr.DdddOcr()
        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.id = []
        self.file = open("detail.txt","w",encoding="utf-8")
        self.obj_id = re.compile(r'"id":(?P<id>.*?),"jsonObject"',re.S)

    def init_page(self):
        init_page_response = self.session.get(url=self.initURL,headers=self.headers)
        print("init_page_response ===>",init_page_response)
        if init_page_response.status_code == 412:
            print("cookie失效,重新获取ts")
            exit(0)
        # print("init_page_response.text ===>",init_page_response.text)
        self.updateCookie()

    def init_captcha(self):
        self.CaptchaURL, self.captchaId, self.MyRandom = Init_Captcha().main()
        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)
        print("请求验证码的响应结果 ===>",CaptchaResponse)
        if CaptchaResponse.status_code == 412:
            print("cookie失效,重新获取ts")
            exit(0)
        with open("captcha.jpg", 'wb') as f:
            f.write(CaptchaResponse.content)
        with open("captcha.jpg", 'rb') as f:
            image = f.read()
        self.pCode = self.ocr.classification(image)
        print("验证码的结果 ===>",self.pCode)
        self.updateCookie()

    def check_Captcha(self):
        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)
        self.updateCookie()
        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:
                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):
        List_data = {
            "pName": pName,
            "pCardNum": "",
            "selectCourtId": "0",
            "pCode": self.pCode,
            "captchaId": self.captchaId,
            "searchCourtName": "全国法院（包含地方各级法院）",
            "selectCourtArrange": "1",
            "currentPage": currentPage
        }
        listURL = self.ctx200.call("get_list","POST","searchBzxr.do")
        listURL = "http://zxgk.court.gov.cn" + listURL
        print("列表页的URL ===>",listURL)
        list_response = self.session.post(url=listURL, headers=self.headers, data=List_data)
        self.updateCookie()
        if list_response.status_code == 412:
            print("cookie失效,重新获取ts")
            exit(0)
        print("列表页的响应 ===>",list_response)
        print(list_response.text)
        try:
            result = self.obj_id.finditer(list_response.text)
            for i in result:
                self.id.append(i.group("id"))
            print("当前列表页的ID存储完毕")
            return True
        except:
            print("需要更新一下验证码")
            self.check_yzm()
            return False

    def Get_Detail(self, i):
        #self.pCode = ""
        currentTime = str(time.time() * 1000)
        DetailURL = "newdetail?id=" + str(self.id[i]) + "&j_captcha=" + self.pCode + "&captchaId=" + self.captchaId
        currentURL = self.ctx200.call("get_bzxr_hz","GET",DetailURL,self.captchaId,self.pCode,currentTime,str(self.id[i]))
        currentURL = "http://zxgk.court.gov.cn" + currentURL
        print("currentURL ===>", currentURL)
        detail_response = self.session.get(url=currentURL,headers=self.headers)
        self.updateCookie()
        if detail_response.status_code == 412:
            print("cookie失效,重新获取ts")
            exit(0)
        id = json.loads(detail_response.text).get("id")
        if id != None:
            self.file.write(detail_response.content.decode())
            self.file.write("\n")
            print(f"写入id为 {i} 的内容")
            print(detail_response.text)
            return True
        return False
    def main(self):
        self.init_page()
        self.check_yzm()
        index = 1
        while True:
            if self.Get_List("张三",index):
                index += 1
                if len(self.id) == 0:
                    break
                for i in range(0,len(self.id)):
                    if self.Get_Detail(i) == False:
                        print("获取id=" + str(i) + "的详情的时候出了问题")
                self.id = []
            if index == len(self.id) + 1:
                break

        self.file.close()

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