# -*-coding:utf-8 -*-
# @Time: 2023/2/20 0020 下午 14:33
# @Author: Cwoner
# @Organization: CTIM
# @Software: PyCharm
import time

import requests
from lxml import etree
import hashlib
from setting import SAVEPATH
import os
import re
from urllib import parse

from tools.serverAPI import upload_file
from tools.give_an_alarm import send_email

class BenGangRBao():
    def __init__(self,ccdate,id=''):#20230101
        self.ccdate = ccdate
        self.id = id
        self.name = 'BenGangRBao'
        print('初始化：',self.name)
        self.mid = hashlib.md5((self.name+'_baozi').encode()).hexdigest()
        if not os.path.isdir(SAVEPATH+self.mid):
            os.mkdir(SAVEPATH+self.mid)
        self.pubTime = self.get_pubTime()

    def index(self,c=0):
        url = "https://s1-cdn.eqxiu.com/eqs/s/page/240274568"
        params = {
            "code": "W73ePtvF",
            "time": self.pubTime
        }
        try:
            response = requests.get(url, params=params,timeout=10)
        except:
            c += 1
            if c > 2:
                send_email(f'报纸采集系统异常-{self.name}-{int(time.time())}',f'主页请求器异常，异常次数超3次，采集退出。报纸：{self.name}. mid: {self.mid}.  报纸日期：{self.ccdate}.')
                return
            return self.index(c)
        if response.status_code == 200:
            data = response.json()
            data_list = data['list']
            elements = data_list[0]['elements']
            triggerGroup = data['list'][0]['properties']['triggerGroup']
            for element in elements:
                if 'content' in element and  '>' + str(int(self.ccdate[6:])) + '<' in element['content']:
                    print(element)
                    id = element['id']
                    for tItem in triggerGroup:
                        if id == tItem['targetId']:
                            targetContent = tItem['targetContent']
                            if targetContent and 'eqxiu.cn' in targetContent:
                                url = parse.unquote(targetContent)
                                pubTime = self.get_pubTime(url)
                                s_params = re.search('s/(.*)\?',url).group(1)
                                self.get_imageUrl(s_params,pubTime)




    def get_pubTime(self,url="https://q.eqxiu.com/s/W73ePtvF"):
        headers = {
            "authority": "q.eqxiu.com",
            "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=0.7",
            "accept-language": "zh-CN,zh;q=0.9",
            "cache-control": "max-age=0",
            "sec-ch-ua": "\"Google Chrome\";v=\"111\", \"Not(A:Brand\";v=\"8\", \"Chromium\";v=\"111\"",
            "sec-ch-ua-mobile": "?0",
            "sec-ch-ua-platform": "\"Windows\"",
            "sec-fetch-dest": "document",
            "sec-fetch-mode": "navigate",
            "sec-fetch-site": "same-origin",
            "sec-fetch-user": "?1",
            "upgrade-insecure-requests": "1",
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36"
        }
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            text = response.text
            publishTime = re.search('publishTime: (\d+),',text,re.M).group(1)
            return publishTime


    def get_imageUrl(self,code,pubTime):
        url = "https://s1-cdn.eqxiu.com/eqs/s/page/252057498"
        params = {
            "code": code,
            "time": pubTime
        }
        response = requests.get(url, params=params)
        if response.status_code == 200:
            data = response.json()
            code = data['code']
            if code == 120607:
                return
            data_list = data['list']
            if not data_list:
                return
            for item in data_list:
                element = item['elements'][1]
                title = item['name']
                properties = element['properties']
                if 'originSrc' in properties:
                    originSrc = properties['originSrc']
                    originSrc = 'https://asset.eqh5.com/' + originSrc
                    print(title,originSrc)
                    tid = hashlib.md5((self.name + title + self.ccdate).encode()).hexdigest()
                    file = tid + '.png'
                    self.__download(file,originSrc,title,tid)



    def __download(self,file,url,title,tid,c=0):
        headers = {
            "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=0.7",
            "Accept-Language": "zh-CN,zh;q=0.9",
            "Cache-Control": "max-age=0",
            "Connection": "keep-alive",
            "Upgrade-Insecure-Requests": "1",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36"
        }
        try:
            response = requests.get(url, headers=headers, verify=False,timeout=10)
        except:
            c += 1
            if c > 2:
                send_email(f'报纸采集系统异常-{self.name}-{int(time.time())}',f'下载报纸数据异常，异常次数超3次，现已终止该页面的采集。页面地址：{url}。 报纸：{self.name}. mid: {self.mid}.  报纸日期：{self.ccdate}.')
                return
            return self.__download(file,url,title,tid,c)
        if response.status_code == 200:
            path = SAVEPATH + self.mid + '/' + self.ccdate + '/'
            if not os.path.isdir(path):
                os.mkdir(path)
            with open(path + file,'wb',) as f:
                f.write(response.content)
            data = {
                'entity_id': self.mid,
                'title': title,
                'tid': tid,
                'file_name': file,
                'origin_url': url,
                'ndate': self.ccdate[:4] + '-' + self.ccdate[4:6] + '-' + self.ccdate[6:]
            }
            upload_file(data, response.content)

    def run(self):
        self.index()





if __name__ == '__main__':
    ccdate = '20230106'
    hr = BenGangRBao(ccdate)
    hr.run()