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


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

from tools.serverAPI import upload_file

class ShanWeiRBao():
    def __init__(self,ccdate,id=''):#20230101
        self.url = f'http://e.hznews.com/hzrb/pc/{ccdate[:6]}/{ccdate[6:]}/node_A01.html'
        self.ccdate = ccdate
        self.id = id
        self.name = '汕尾日报'
        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 get_date_data(self):
        headers = {
            "Accept": "application/json, text/javascript, */*; q=0.01",
            "Accept-Language": "zh,zh-CN;q=0.9",
            "Cache-Control": "no-cache",
            "Connection": "keep-alive",
            "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
            "Origin": "http://epaper.shanweinews.net",
            "Pragma": "no-cache",
            "Referer": "http://epaper.shanweinews.net/u/res/skin/epaper/htm/szb.html?siteid=2A90839E2034DF53854DA912D5496033",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36",
            "X-Requested-With": "XMLHttpRequest"
        }
        cookies = {
            "HA_STICKY_ucap1": "ucap1.srv2"
        }
        url = "http://epaper.shanweinews.net/u/epaper/issue/2A90839E2034DF53854DA912D5496033/ajaxList"
        params = {
            "issue": ""
        }
        data = {
            "issue_time": f"{self.ccdate[:4]}-{self.ccdate[4:6]}-{self.ccdate[6:]}",
            "issueid": ""
        }
        response = requests.post(url, headers=headers, cookies=cookies, params=params, data=data, verify=False)
        if response.status_code == 200:
            data = response.json()
            self.ISSUE_ID = data['ISSUE_ID']




    def index(self):
        self.get_date_data()
        headers = {
            "Accept": "application/json, text/javascript, */*; q=0.01",
            "Accept-Language": "zh,zh-CN;q=0.9",
            "Cache-Control": "no-cache",
            "Connection": "keep-alive",
            "Content-Length": "0",
            "Origin": "http://epaper.shanweinews.net",
            "Pragma": "no-cache",
            "Referer": "http://epaper.shanweinews.net/u/res/skin/epaper/htm/szb.html?siteid=2A90839E2034DF53854DA912D5496033",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36",
            "X-Requested-With": "XMLHttpRequest"
        }
        url = f"http://epaper.shanweinews.net/u/epaper/page/{self.ISSUE_ID}/ajaxList"
        params = {
            "pages": ""
        }
        response = requests.post(url, headers=headers, params=params, verify=False)
        if response.status_code == 200:
            data= response.json()
            bans = data
            x = 1
            for ban in bans:
                title = ban['page_name']
                img_url = 'http://epaper.shanweinews.net' + ban['page_image_location']
                tid = hashlib.md5((self.name + title + self.ccdate).encode()).hexdigest()
                print(title,img_url)
                file = tid + f'.{img_url.split(".")[-1]}'
                self.__download(file,img_url,title,tid)
                x += 1


    def get_image_url(self,url):
        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,zh-CN;q=0.9",
            "Cache-Control": "no-cache",
            "Pragma": "no-cache",
            "Proxy-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/121.0.0.0 Safari/537.36"
        }
        response = requests.get(url, headers=headers, verify=False)
        if response.status_code == 200:
            text = response.text
            html = etree.HTML(text)
            img = html.xpath('//img[@class="preview"]/@src')[0]
            img_url = f'http://e.hznews.com/hzrb/pc/pic{self.ccdate[:6]}/{self.ccdate[6:]}/{img}'
            return img_url




    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)
        except:
            if c > 3:
                return
            c += 1
            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):
        rid = self.index()




if __name__ == '__main__':
    ccdate = '20240408'
    hr = ShanWeiRBao(ccdate)
    hr.run()