RS_zxgk/xgl/xgl.py

import json
import re
import time

from RS import Get_Cookie
from Captcha import Init_Captcha
import ddddocr

class Get_Info:
    def __init__(self):
        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/xgl/",
            "Accept-Language": "zh-CN,zh;q=0.9"
        }
        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/xgl"
        self.ListURL = "http://zxgk.court.gov.cn/xgl/searchXgl.do"
        self.ocr = ddddocr.DdddOcr()
        self.totalPage = 0
        self.pdfs = []
        self.file = open("xglLink.txt","w",encoding="utf-8")

    def init_page(self):
        init_page_response = self.session.get(url=self.initURL, headers=self.headers)
        print("init_page_response ===>", init_page_response)
        # 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/xgl/",
            "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)
        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.text.split("\n")[0] == "1":
            print("验证码验证通过")
            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 == 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, 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
        }
        url = self.ctx200.call("get_list", "POST", "searchXgl.do")
        print("url ===>",url)
        url = "http://zxgk.court.gov.cn" + url
        ListResponse = self.session.post(url=url,headers=self.headers,data=List_data)
        print("列表页的响应 ===>",ListResponse.text)
        self.updateCookie()
        try:
            self.totalPage = re.findall(r'"totalPage":(.*?),"',ListResponse.text)[0]
            print("totalPage ===>",self.totalPage)
            self.pdfs.append(re.findall(r'"FILEPATH":"(.*?)","', ListResponse.text))
            return True
        except:
            print("获取totalPage失败了 ListResponse ===> ",ListResponse.text)
            self.check_yzm()
            return False

    def write_link(self):
        for pdf in self.pdfs:
            for i in pdf:
                self.file.write(i)
                self.file.write("\n")
        self.pdfs = []

    def main(self):
        self.init_page()
        self.check_yzm()
        i = 1
        while True:
            print("i =====>",i)
            if i == int(self.totalPage):
                break
            if self.Get_List("张三",i):
                i += 1
                self.write_link()
        print("关键字为 张三 的内容写入完毕")
        self.file.close()

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