# _*_ coding : UTF-8 _*_
# @Time : 2024/11/13 02:34
# @UpdateTime : 2024/11/13 02:34
# @Author : haochen zhong
# @File : CrawlRenmingonganbao.py
# @Software : PyCharm
# @Comment : 本程序采集人民公安报数据

import asyncio
import random
import re
from datetime import datetime, timedelta

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

pattern = r"window\.location\.href=['\"](.*?)['\"]"
"""正则匹配ID"""
start_date = datetime.strptime('2020-04-01', '%Y-%m-%d')
"""人民公安报2020年4月1日开始有数据"""
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'}

# 链接数据库
client = AsyncIOMotorClient('mongodb://localhost:27017')
db = client['buweijiguanbao']
collection = db['renmingonganbao']


async def main():
    collection_names = await db.list_collection_names()
    # 判断数据表是否存在
    if "renmingonganbao" not in collection_names:
        # 如果不存在，则从2017年9月开始爬取
        print("中国民族数据表不存在，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("div.content_main > div:nth-child(2) .contentP"):
        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
    for i in range((end_date - start_date).days):
        date_now = start_date + timedelta(days=i + 1)
        date_now_s = date_now.strftime('%Y_%m_%d')
        url = f"http://epaper.cpd.com.cn/szb/wwwcpd_9/dzb_16465/rmga/{date_now.year}/{date_now_s}/"
        """http://epaper.cpd.com.cn/szb/wwwcpd_9/dzb_16465/rmga/2020/2020_04_05/"""
        print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url)
        try:
            async with AsyncClient(headers=headers, timeout=60) as client:
                response = await client.get(url)
                response.encoding = response.charset_encoding
                text = response.text
                match = re.search(pattern, text)
                if match:
                    url = url + match.group(1).replace("./", "")
                    print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url)
                    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, 'lxml')
                        cont_main = soup.select_one(".tab-title")
                        if cont_main:
                            script_tag = cont_main.find("script")
                            if script_tag:
                                script_content = script_tag.string
                                soup1 = BeautifulSoup(
                                    script_content.replace("document.write('", "").replace("')", "").replace(";",
                                                                                                             "").replace(
                                        "'+'", "").strip(), "lxml")
                                for item in soup1.select(".title-item"):
                                    banmianming = item.select_one(".title").text.split(" ")[-1]
                                    banmianhao = item.select_one(".title").text.split(" ")[0]
                                    for item2 in item.select(".title-list a"):
                                        title = item2.text
                                        url2 = item2.get("href")
                                        print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2)
                                        response2 = await client.get(url2)
                                        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')
                                            try:
                                                title = soup2.select_one(
                                                    ".cont-box > div>div:nth-child(2)").text.strip()
                                            except:
                                                title = title
                                            try:
                                                subtitle = soup2.select_one(
                                                    ".cont-box > div>div:nth-child(3)").text.strip()
                                            except:
                                                subtitle = ""
                                            try:
                                                preTitle = soup2.select_one(
                                                    ".cont-box > div>div:nth-child(1)").text.strip()
                                            except:
                                                preTitle = ""
                                            content = await getContent(soup2)
                                            await collection.insert_one({
                                                "title": title,
                                                "subtitle": subtitle,
                                                "preTitle": preTitle,
                                                "author": "",
                                                "banmianming": banmianming,
                                                "banmianhao": banmianhao,
                                                'keywordlist': "empty",
                                                'detail_url': url2,
                                                'release_time': date_now,
                                                'insert_timestamp': datetime.today(),
                                                'content': content
                                            })
                                            crawl_num += 1
                                            print(
                                                f"人民公安报---{date_now_s}---{banmianming}---{banmianhao}---{title}---采集完成！")
                                            await asyncio.sleep(random.randint(5, 15))
                                    print(f"人民公安报---{date_now_s}---{banmianming}---{banmianhao}-----采集完成！")
                                    await asyncio.sleep(random.randint(5, 15))
                    print(f"人民公安报---{date_now_s}-----采集完成！")
                    await asyncio.sleep(random.randint(5, 15))
        except Exception as e:
            await collection.insert_one(
                {'banmianhao': 'empty',
                 'banmianming': 'empty',
                 'preTitle': 'empty',
                 'title': 'empty',
                 'subtitle': 'empty',
                 'author': 'empty',
                 'keywordlist': 'empty',
                 'detail_url': url,
                 'release_time': date_now,
                 'insert_timestamp': datetime.today(),
                 'content': 'empty'}
            )
            print(e)
    print(f"人民公安报采集完毕，共采集{crawl_num}条数据！")


asyncio.run(main())