# _*_ coding : UTF-8 _*_
# @Time : 2024/11/24 04:06
# @UpdateTime : 2024/11/24 04:06
# @Author : haochen zhong
# @File : CrawlZhongguohuanjingbao.py
# @Software : PyCharm
# @Comment : 本程序采集中国环境报数据
import asyncio
import random
import re
from datetime import datetime

from bs4 import BeautifulSoup, Comment
from httpx import AsyncClient
from motor.motor_asyncio import AsyncIOMotorClient

start_date = datetime.strptime('2013-08', '%Y-%m')
"""中国环境报2013年8月份开始有数据"""
end_date = datetime.today()
"""截止到今天"""
headers = {
    'User-Agent': 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 Edg/107.0.1418.42'}

pattern = r'<a href=([^>]+)><div[^>]*>([^<]+)</div></a>'
# 链接数据库
client = AsyncIOMotorClient('mongodb://localhost:27017')
db = client['buweijiguanbao']
collection = db['zhongguohuanjingbao']


async def main():
    collection_names = await db.list_collection_names()
    # 判断数据表是否存在
    if "zhongguohuanjingbao" not in collection_names:
        print("中国环境报数据表不存在，开始采集！")
        await getData(start_date, end_date)
    else:
        # 如果存在，则从数据库中获取最后一条记录的日期
        last_record = await collection.find_one({}, sort=[('release_time', -1)])
        last_date_str = last_record['release_time']
        print("数据库截止时间:", last_date_str)
        await getData(last_date_str, end_date)


async def getContent(soup: BeautifulSoup) -> str:
    """
    :param soup: BeautifulSoup对象
    :return: 文章内容
    """
    content = ""
    for p in soup.select("#ozoom p"):
        para = p.text.strip()
        if para:
            content += para
            content += '\n'
    return content


async def getData(start_date: datetime, end_date: datetime):
    """
    :param start_date: 开始日期
    :param end_date: 结束日期
    :return: None
    """
    crawl_num = 0
    # 创建一个列表保存月份
    months = []
    # 从开始日期到结束日期，每个月份都添加到列表中
    current_date = start_date
    while current_date <= end_date:
        months.append(current_date)
        # 增加一个月
        if current_date.month == 12:
            current_date = current_date.replace(year=current_date.year + 1, month=1)
        else:
            current_date = current_date.replace(month=current_date.month + 1)
        # 遍历月份列表
    for month in months:
        # 构造URL
        url = f'http://news.cenews.com.cn/html/{month.strftime("%Y-%m")}/period.xml'
        """http://news.cenews.com.cn/html/2013-08/period.xml"""
        print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url)
        async with AsyncClient(headers=headers, timeout=60) as client:
            response = await client.get(url)
            response.encoding = response.charset_encoding
            print(f"一级连接状态：{response.status_code}")
            if response.status_code == 200:
                soup = BeautifulSoup(response.text, 'xml')
                for period in soup.select("period"):
                    period_name = datetime.strptime(period.find("period_name").text.strip(), "%Y-%m-%d")
                    front_page = period.find("front_page").text.strip()
                    try:
                        url1 = f"http://news.cenews.com.cn/html/{period_name.strftime('%Y-%m/%d')}/{front_page}"
                        """http://news.cenews.com.cn/html/2013-08/14/node_2.htm"""
                        print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url1)
                        response2 = await client.get(url1)
                        response2.encoding = response2.charset_encoding
                        print(f"二级连接状态：{response2.status_code}")
                        if response2.status_code == 200:
                            soup2 = BeautifulSoup(response2.text, 'lxml')
                            for item in soup2.select("#pgn #pageLink"):
                                banmianming = item.text.split("： ")[-1]
                                banmianhao = item.text.split("： ")[0]
                                url2 = f"http://news.cenews.com.cn/html/{period_name.strftime('%Y-%m/%d')}/" + item.get(
                                    "href").replace("./", "").strip()
                                """http://news.cenews.com.cn/html/2013-08/14/node_2.htm"""
                                print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2)
                                response3 = await client.get(url2)
                                response3.encoding = response3.charset_encoding
                                print(f"三级连接状态：{response3.status_code}")
                                if response3.status_code == 200:
                                    for href, title in re.findall(pattern, response3.text, re.IGNORECASE):
                                        url3 = f"http://news.cenews.com.cn/html/{period_name.strftime('%Y-%m/%d')}/" + href.replace(
                                            "./", "").strip()
                                        """http://news.cenews.com.cn/html/2013-08/14/content_17724.htm"""
                                        if await collection.find_one({"detail_url": url3}, {"_id": False}):
                                            continue
                                        print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url3)
                                        response4 = await client.get(url3)
                                        response4.encoding = response4.charset_encoding
                                        print(f"四级连接状态：{response4.status_code}")
                                        if response4.status_code == 200:
                                            soup4 = BeautifulSoup(response4.text, 'html.parser')
                                            try:
                                                comments = soup4.find_all(string=lambda text: isinstance(text, Comment))
                                                for comment in comments:
                                                    if 'enpproperty' in comment:
                                                        # 提取注释内容
                                                        enpproperty_content = comment.strip()
                                                        inner_soup = BeautifulSoup(enpproperty_content, 'html.parser')
                                                        # 提取特定标签值
                                                        title = inner_soup.find('founder-title').text
                                                        perTitle = inner_soup.find('founder-introtitle').text
                                                        subTitle = inner_soup.find("founder-subtitle").text
                                                        author = inner_soup.find('founder-author').text
                                                        keywordlist = inner_soup.find("founder-keyword").text
                                            except:
                                                title = title
                                                perTitle = ""
                                                subTitle = ""
                                                author = ""
                                                keywordlist = ""
                                            content = await getContent(soup4)
                                            await collection.insert_one({
                                                "title": title,
                                                "subtitle": subTitle,
                                                "preTitle": perTitle,
                                                "author": author,
                                                "banmianming": banmianming,
                                                "banmianhao": banmianhao,
                                                'keywordlist': keywordlist,
                                                'detail_url': url3,
                                                'release_time': period_name,
                                                'insert_timestamp': datetime.today(),
                                                'content': content
                                            })
                                            crawl_num += 1
                                            print(
                                                f"中国环境报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！")
                                            await asyncio.sleep(random.randint(5, 15))
                                    print(
                                        f"中国环境报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！")
                                    await asyncio.sleep(random.randint(5, 15))
                        print(
                            f"中国环境报---{period_name.strftime('%Y-%m-%d')}------采集完成！")
                        await asyncio.sleep(random.randint(5, 15))
                    except Exception as e:
                        print(e)
                        await collection.insert_one(
                            {'banmianhao': 'empty',
                             'banmianming': 'empty',
                             'preTitle': 'empty',
                             'title': 'empty',
                             'subtitle': 'empty',
                             'author': 'empty',
                             'keywordlist': 'empty',
                             'detail_url': url,
                             'release_time': period_name,
                             'insert_timestamp': datetime.today(),
                             'content': 'empty'}
                        )
    print(f"中国环境报采集完毕，共采集{crawl_num}条数据！")


asyncio.run(main())