# _*_ coding : UTF-8 _*_
# @Time : 2022/12/29 13:48
# @Author : Haochen Zhong
# @File : CrawlNingxia.py
# @Software : PyCharm
# @Comment : 本程序采集宁夏日报版面数据

import random
import time
from datetime import timedelta, datetime

import pymongo
import requests
from bs4 import BeautifulSoup

# 数据库起止时间
start_date = datetime.strptime('2022-01-31', '%Y-%m-%d')
"""宁夏日报2022-02-01开始有数据"""
end_date = datetime.today()
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36'}
# 创建数据库
client = pymongo.MongoClient('localhost', 27017)
mydb = client.dfdm_sjribao
ningxiaribao = mydb.ningxiaribao
# 设置随机时间
sleeptime = random.randint(2, 10)


def main():
    # 判断数据库是否存在
    collist = mydb.list_collection_names()
    if "ningxiaribao" in collist:  # 检测集合是否存在
        print("宁夏集合存在，更新数据库")
        # 数据库最新一条内容的时间
        db_time = ningxiaribao.find_one(sort=[('release_time', -1)])[
            'release_time']  # 或者find().sort('_id', -1).limit(1)
        print('数据库截止时间%s' % db_time)
        # 输入更新数据库时间
        input_time = datetime.today()
        if db_time < input_time:
            getData(db_time, input_time)
        else:
            print('数据库无需更新!')
    else:
        # 爬取网页并建立数据库
        print("数据库不存在，建立数据库！")
        getData(start_date, end_date)


def get_content(soup3):
    content = ""
    for p in soup3.select("#ozoom p"):
        para = p.text.strip()
        if para:
            content += para
            content += '\n'
    return content


def getData(start_date, end_date):
    crawl_num = 0
    for i in range((end_date - start_date).days):  # gu:时间长度
        date_now = start_date + timedelta(days=i + 1)
        date_now_s = date_now.strftime('%Y%m/%d')
        base_url = "https://szb.nxrb.cn/nxrb/pc/layout/" + date_now_s + "/"
        url = base_url + "node_01.html"
        # https://szb.nxrb.cn/nxrb/pc/layout/202202/01/node_01.html
        try:
            response = requests.get(url=url, headers=headers, timeout=(30, 45))
            response.encoding = response.apparent_encoding
            print(f"一级连接状态: {response.status_code}")
            if response.status_code == 200:
                soup = BeautifulSoup(response.text, "lxml")
                for item in soup.select(".nav-list .btn-block"):
                    banmianhao = item.text.split("：")[0].strip()
                    banmianming = item.text.split("：")[-1].strip()
                    url1 = base_url + item.get("href")
                    response2 = requests.get(url=url1, headers=headers, timeout=(30, 45))
                    response2.encoding = response2.apparent_encoding
                    print(f"二级连接状态：{response2.status_code}")
                    if response2.status_code == 200:
                        soup2 = BeautifulSoup(response2.text, "lxml")
                        for item2 in soup2.select(".news-list .resultList a"):
                            url_title = item2.text.strip()
                            url2 = "https://szb.nxrb.cn/nxrb/pc/" + item2.get("href")[9:]
                            print(url2)
                            response3 = requests.get(url=url2, headers=headers, timeout=(30, 45))
                            response3.encoding = response3.apparent_encoding
                            print(f"三级连接状态：{response3.status_code}")
                            if response3.status_code == 200:
                                soup3 = BeautifulSoup(response3.text, "lxml")
                                try:
                                    pretitle = soup3.select("#PreTitle")[0].text.strip()
                                except:
                                    pretitle = ""
                                try:
                                    title = soup3.select("#Title")[0].text.strip()
                                except:
                                    title = url_title
                                try:
                                    subtitle = soup3.select("SubTitle")[0].text.strip()
                                except:
                                    subtitle = ""
                                content = get_content(soup3)
                                ningxiaribao.insert_one({'banmianhao': banmianhao,
                                                         'banmianming': banmianming,
                                                         'title': title,
                                                         'subtitle': subtitle,
                                                         'h3title': pretitle,
                                                         'author': '',
                                                         'keywordlist': 'empty',
                                                         'detail_url': url2,
                                                         'release_time': date_now,
                                                         'insert_timestamp': datetime.today(),
                                                         'content': content})
                                crawl_num += 1
                                print(f"宁夏日报-{date_now_s}-{banmianhao}-{title}-已完成")
                                time.sleep(sleeptime)
                        print(f"宁夏日报-{date_now_s}-{banmianhao}-已完成")
                        time.sleep(sleeptime)
                print(f"宁夏日报-{date_now_s}-已完成")
                time.sleep(sleeptime)
        except Exception as result:
            ningxiaribao.insert_one({'banmianhao': 'empty',
                                     'banmianming': 'empty',
                                     'title': 'empty',
                                     'subtitle': 'empty',
                                     'h3title': 'empty',
                                     'author': 'empty',
                                     'keywordlist': 'empty',
                                     'detail_url': url,
                                     'release_time': date_now,
                                     'insert_timestamp': datetime.today(),
                                     'content': 'empty'})
            print(result)
    print(f"宁夏日报采集完成，成功采集{crawl_num}条数据！")


if __name__ == '__main__':
    main()