RS_zxgk/zhongben/zhongben.py

import json
import re
import sys
import time

import ddddocr
import requests

from RS import Get_Cookie
from Captcha import Init_Captcha


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/zhongben/"
        self.DetailURL = "http://zxgk.court.gov.cn/zhongben/searchZbDetail"
        self.ocr = ddddocr.DdddOcr()
        self.headers = {
            "Connection": "keep-alive",
            "Pragma": "no-cache",
            "Cache-Control": "no-cache",
            "Accept": "*/*",
            "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/zhongben/",
            "Accept-Language": "zh-CN,zh;q=0.9"
        }
        self.id = []
        self.file = open("detail.txt",mode="w",encoding="utf-8")
        self.names = ["张三", "李四", "王五"]
        self.totalPage = 2

    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)
        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/zhongben/",
            "Accept-Language": "zh-CN,zh;q=0.9"
        }
        print("self.CaptchaURL ===>",self.CaptchaURL)
        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("验证验证码的URL ===>",checkURL)
        response = self.session.get(url=checkURL, headers=self.headers)
        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
        else:
            print("验证码验证失败,退出程序")
            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, name, currentPage):
        List_data = {
            "pName": name,
            "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","search.do")
        self.ListURL = "http://zxgk.court.gov.cn" + ListURL
        print("获取列表页的URL ===>",self.ListURL)
        list_response = self.session.post(url=self.ListURL, headers=self.headers, data=List_data)
        if list_response.status_code == 412:
            print("cookie失效,重新获取ts")
            exit(0)
        self.updateCookie()
        try:
            self.id = re.findall(r'"id":(.*?),"', list_response.text)
            print("获取id列表完成")
            self.totalPage = int(re.findall(r'"totalPage":(.*?),"',list_response.text)[0])
            return True
        except:
            print("获取self.id失败 重新刷新验证码",list_response.text)
            self.check_yzm()
            return False

    def get_detail(self, id):
        #self.captchaId = ""
        searchURL = "searchZbDetail?id=" + id + "&j_captcha=" + self.pCode + "&captchaId=" + self.captchaId
        DetailURL = self.ctx200.call("get_detail","GET",searchURL,self.captchaId,self.pCode,id)
        self.DetailURL = "http://zxgk.court.gov.cn" + DetailURL
        print("获取详情的URL ===>",self.DetailURL)
        response = self.session.get(url=self.DetailURL,headers=self.headers)
        if response.status_code == 412:
            print("cookie失效,重新获取ts")
            exit(0)
        print("详情页 ===>",response.text)
        try:
            id = json.loads(response.text).get("id")
            print("详情id =>",id)
            self.file.write(response.text)
            self.file.write("\n")
            #返回True表示当前的详情写入正确(有数据)
            self.updateCookie()
            return True
        except:
            print("验证码出现错误")
            self.check_yzm()
            return False

    def main(self):
        self.init_page()
        self.check_yzm()
        for name in self.names:
            self.file.write(f"关键字 =======> {name}")
            self.file.write("\n")
            # 表示某某的第几页数据
            index = 1
            while True:
                time.sleep(0.5)
                if self.Get_List(name, index):
                    id = 0
                    while True:
                        #返回True说明正确
                        # if len(self.id) == 0:
                        #     break
                        if id == len(self.id):
                            break
                        if self.get_detail(self.id[id]):
                            id += 1
                    if index == self.totalPage:
                        break
                    index += 1
                    self.id = []
            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()