import datetime
import json
import logging
import time

import requests
from bs4 import BeautifulSoup

import MDBUtil

logger = logging.getLogger()
logger.setLevel('INFO')
BASIC_FORMAT = "%(asctime)s:%(levelname)s:%(message)s"
DATE_FORMAT = '%Y-%m-%d %H:%M:%S'
formatter = logging.Formatter(BASIC_FORMAT, DATE_FORMAT)
filename = time.strftime('%Y-%m-%d', time.localtime(time.time()))
chlr = logging.StreamHandler()  # 输出到控制台的handler
chlr.setFormatter(formatter)
chlr.setLevel('INFO')  # 也可以不设置，不设置就默认用logger的level
fhlr = logging.FileHandler("./log/" + filename + "_ccgp_anhui.log")  # 输出到文件的handler
fhlr.setFormatter(formatter)
logger.addHandler(chlr)
logger.addHandler(fhlr)


class ccgp_anhui():
    # 初始化数据
    def __init__(self):
        self.cookies = dict()
        self.session = requests.session()
        # 随机headers
        self.get_headers = {
            'Host': 'www.ccgp-anhui.gov.cn',
            '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=0.9',
            'Accept-Encoding': 'gzip, deflate',
            'Accept-Language': 'zh-CN,zh;q=0.9',
            '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 Edg/111.0.1661.62'
        }
        self.post_headers = {
            'Host': 'www.ccgp-anhui.gov.cn',
            'Accept': 'application/json, text/plain, */*',
            'Accept-Encoding': 'gzip, deflate',
            'Content-Type': 'application/json',
            '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 Edg/111.0.1661.62'
        }
        self.timeout = 30

    # 更新cookie
    def update_cookies(self, new_cookies):
        for key in new_cookies:
            self.cookies[key] = new_cookies[key]

    # 请求数据（GET)
    def req_get(self, url):
        requests.session().cookies = requests.utils.cookiejar_from_dict(self.cookies)
        resp = self.session.get(url, headers=self.get_headers, timeout=self.timeout)
        self.update_cookies(requests.utils.dict_from_cookiejar(resp.cookies))
        return resp

    # 请求数据（POST)
    def req_post(self, url, data):
        cookies = dict()
        session = requests.session()
        requests.session().cookies = requests.utils.cookiejar_from_dict(cookies)
        resp = session.post(url, data=data, headers=self.post_headers, timeout=self.timeout, cookies=cookies)
        cookies = self.update_cookies(cookies)
        return resp

    def get_purchase_list(self, query_param_obj):
        next_page_num = 1
        is_last_page = False
        pageNo = int(query_param_obj['pageNo'])
        pageSize = int(query_param_obj['pageSize'])
        next_pageNo = pageNo
        while not is_last_page:
            try:
                query_param_obj["pageNo"] = next_pageNo
                self.url = 'http://www.ccgp-anhui.gov.cn/portal/category'
                query_param_json = json.dumps(query_param_obj)
                response = self.req_post(self.url, query_param_json)
                parse_list = []
                response_code = response.status_code
                if response_code == 200:
                    logger.info("get_purchase_list,请求成功", exc_info=True)
                    responseDataText = response.text
                    responseData = json.loads(responseDataText)
                    result = responseData['result']
                    result_data = result['data']
                    total = result_data['total']
                    result_list = result_data['data']

                    if total > next_pageNo * pageSize:
                        is_last_page = False
                    else:
                        is_last_page = True
                    next_pageNo = next_pageNo + 1

                    def get_val_from_object(obj, key):
                        if obj.__contains__(key):
                            return str(obj[key])
                        return ''

                    for one in result_list:
                        objid = get_val_from_object(one, 'articleId').replace('==','')
                        publishtime = get_val_from_object(one, 'publishDate')
                        publishtime = datetime.datetime.fromtimestamp(int(publishtime) / 1000.0).strftime(
                            '%Y-%m-%d %H:%M:%S')

                        cggg_content = self.get_cggg(objid)
                        prjName = get_val_from_object(cggg_content, 'projectName')
                        prjNo = get_val_from_object(cggg_content, 'projectCode')
                        article = get_val_from_object(cggg_content, 'title')
                        cggg_content_text = get_val_from_object(cggg_content, 'content_text')
                        cggg_content_url = get_val_from_object(cggg_content, 'cggg_content_url')

                        area = get_val_from_object(one, 'districtName')
                        purchaseType = get_val_from_object(one, 'pathName')
                        prjId = get_val_from_object(one, 'articleId')

                        p_zone_code = get_val_from_object(one, 'pZoneCode')
                        p_zone_name = get_val_from_object(one, 'pZoneName')
                        zone_code = get_val_from_object(one, 'zoneCode')
                        zone_name = get_val_from_object(one, 'zoneName')
                        purchasePerson = get_val_from_object(one, 'buyerName')
                        agency = get_val_from_object(one, 'agentName')

                        data = (objid, publishtime, prjName, prjNo, area, purchaseType, purchasePerson,
                                agency, article, prjId, p_zone_code, p_zone_name, zone_code, zone_name,
                                cggg_content_text,
                                cggg_content_url,'安徽省')

                        parse_list.append(data)
                    MDBUtil.insert_t_purchase_list(parse_list)
                else:
                    logger.info("get_station_list,请求异常，返回状态[%d]" % (response_code,), exc_info=True)
                print(response)
            except:
                logger.error("get_station_list,获取数据失败异常,页数[%d]" % (next_page_num,), exc_info=True)

    """
            根据ggid，获取采购公告内容
    """
    def get_cggg(self, ggid):
        self.url = 'http://www.ccgp-anhui.gov.cn/CSPDREL3BvcnRhbC9kZXRhaWw/YXJ0aWNsZUlkPUl0UDRVMmhnbjI0SjlQaUl3TTNTRVE=?wzwscspd=MC4wLjAuMA=='
        response = self.req_get(self.url)

        ggid = ggid.replace('+','%2B')
        detail_url = 'http://www.ccgp-anhui.gov.cn/portal/detail?articleId=%s' % (ggid)

        content_text = ''
        try:
            response = self.req_get(detail_url)
            response.encoding = 'utf-8'
            response_code = response.status_code
            cggg_content = {}
            if response_code == 200:
                responseDataText = response.text
                responseData = json.loads(responseDataText)
                result_data = responseData['result']['data']
                result_data_content = responseData['result']['data']['content']
                content_text = BeautifulSoup(result_data_content, "lxml").text
                cggg_content['content_text'] = content_text
                cggg_content['districtCode'] = result_data['districtCode']
                cggg_content['projectCode'] = result_data['projectCode']
                cggg_content['projectName'] = result_data['projectName']
                cggg_content['title'] = result_data['title']
                cggg_content['cggg_content_url'] = self.url

                logger.info("ggid[%s],请求成功" % (ggid,), exc_info=True)
        except:
            logger.error("ggid[%s],请求失败" % (ggid,), exc_info=True)
        return cggg_content

if __name__ == '__main__':
    work = ccgp_anhui()
    publishDateEnd = datetime.datetime.now().strftime("%Y-%m-%d")
    publishDateBegin = (datetime.datetime.now() - datetime.timedelta(days=100)).strftime('%Y-%m-%d')

    query_param_obj = {
        "categoryCode": "ZcyAnnouncement2",
        "keyword": "环境",
        "pageNo": 1,
        "pageSize": "15",
        'districtCode': None,
        'leaf': None,
        "publishDateBegin": publishDateBegin,
        "publishDateEnd": publishDateEnd
    }

    work.get_purchase_list(query_param_obj)