# -*-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 tools.serverAPI import upload_file
from tools.give_an_alarm import send_email

class KanJiangRBao():
    def __init__(self,ccdate,id=''):#20230101
        self.url = f'http://paper.gdzjdaily.com.cn/html/{ccdate[:4]}-{ccdate[4:6]}/{ccdate[6:]}/node_1.htm'
        self.ccdate = ccdate
        self.id = id
        self.name = '湛江日报'
        print('初始化：',self.name, self.url)
        self.mid = hashlib.md5((self.name+'_baozi').encode()).hexdigest()
        if not os.path.isdir(SAVEPATH+self.mid):
            os.mkdir(SAVEPATH+self.mid)


    def index(self,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(self.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'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:
            text = response.content.decode('utf-8')
            html = etree.HTML(text)
            bans = html.xpath('//table[@id="bmdhTable"]//tr')
            i = 0
            for banItem in bans:
                title = str(i) + banItem.xpath('.//a[@id="pageLink"]/text()')[0]
                if not title:
                    title = f'未知标题{i}'
                print(self.name,title)
                burl = banItem.xpath('.//td[2]/a/@href')[0]
                print(burl)
                if 'pdf' in burl:
                    pdf_url = 'http://paper.gdzjdaily.com.cn/'+ burl
                else:
                    continue
                tid = hashlib.md5((self.name+title+self.ccdate).encode()).hexdigest()
                file = tid + '.pdf'
                if pdf_url:
                    pdf_url = pdf_url.replace('../../..','')
                    print(pdf_url),
                    self.__download(file,pdf_url,title,tid)
                i += 1
        else:
            send_email(f'报纸采集系统异常-{self.name}-{int(time.time())}',
                       f'主页响应状态码异常：{response.status_code}。'
                       f'请求的报纸主页：{self.url}. 报纸：{self.name}. mid: {self.mid}.  报纸日期：{self.ccdate}.')



    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 = '20240408'
    hr = KanJiangRBao(ccdate)
    hr.run()