# -*- coding = utf-8 -*-
# @Time : 2021/12/2 20:34
# @Author : sonder
# @File : CrawlRenminribao.py
# @Software : PyCharm
# @Comment : 本程序用于采集人民日报版面数据


import asyncio
import random
from datetime import datetime

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

start_date = datetime.strptime('2024-12', '%Y-%m')
"""人民日报只开放3年内有效数据"""
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['zydb']
collection = db['renminribao']


async def main():
    collection_names = await db.list_collection_names()
    # 判断数据表是否存在
    if "renminribao" not in collection_names:
        print("人民日报数据表不存在，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
    current_date = current_date.replace(day=1)
    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:
        if month < datetime(2024, 12, 1):
            # 构造URL
            url = f'http://paper.people.com.cn/rmrb/html/{month.strftime("%Y-%m")}/period.xml'
            """http://paper.people.com.cn/rmrb/html/2022-01/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://paper.people.com.cn/rmrb/html/{period_name.strftime('%Y-%m/%d')}/{front_page}"
                            """http://paper.people.com.cn/rmrb/html/2024-01/01/nw.D110000renmrb_20240101_1-01.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("#pageLink"):
                                    banmianming = item.text.split("：")[-1]
                                    banmianhao = item.text.split("：")[0]
                                    url2 = f"http://paper.people.com.cn/rmrb/html/{period_name.strftime('%Y-%m/%d')}/" + item.get(
                                        "href").replace("./", "").strip()
                                    """http://paper.people.com.cn/rmrb/html/2024-01/01/nw.D110000renmrb_20240101_1-01.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:
                                        soup3 = BeautifulSoup(response3.text, 'lxml')
                                        for item2 in soup3.select(".news-list a"):
                                            url3 = f"http://paper.people.com.cn/rmrb/html/{period_name.strftime('%Y-%m/%d')}/" + item2.get(
                                                "href").replace(
                                                "./", "").strip()
                                            """http://paper.people.com.cn/rmrb/html/2024-01/01/nw.D110000renmrb_20240101_1-01.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 'mpproperty' in comment:
                                                            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.strip()
                                                            perTitle = inner_soup.find(
                                                                'founder-introtitle').text.strip()
                                                            subTitle = inner_soup.find("founder-subtitle").text.strip()
                                                            author = inner_soup.find('founder-author').text.strip()
                                                            keywordlist = inner_soup.find(
                                                                "founder-keyword").text.strip()
                                                except:
                                                    title = title
                                                    perTitle = ""
                                                    subTitle = ""
                                                    author = ""
                                                content = await getContent(soup4)
                                                await collection.insert_one({
                                                    "title": title,
                                                    "subtitle": subTitle,
                                                    "preTitle": perTitle,
                                                    "author": author,
                                                    "banmianming": banmianming,
                                                    "banmianhao": banmianhao,
                                                    'detail_url': url3,
                                                    'release_time': period_name,
                                                    'insert_timestamp': datetime.today(),
                                                    'content': content
                                                })
                                                crawl_num += 1
                                                print(
                                                    f"人民日报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！")
                                                await asyncio.sleep(random.randint(5, 15))
                                        print(
                                            f"人民日报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！")
                                        await asyncio.sleep(random.randint(5, 15))
                            print(
                                f"人民日报---{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'}
                            )
        else:
            # 构造URL
            url = f'http://paper.people.com.cn/rmrb/pc/layout/{month.strftime("%Y%m")}/period.xml'
            """http://paper.people.com.cn/rmrb/pc/layout/202412/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://paper.people.com.cn/rmrb/pc/layout/{period_name.strftime('%Y%m/%d')}/{front_page}"
                            """http://paper.people.com.cn/rmrb/pc/layout/202502/01/node_1.html"""
                            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("#pageLink"):
                                    banmianming = item.text.split("：")[-1]
                                    banmianhao = item.text.split("：")[0]
                                    url2 = f"http://paper.people.com.cn/rmrb/pc/layout/{period_name.strftime('%Y%m/%d')}/" + item.get(
                                        "href").replace("./", "").strip()
                                    """http://paper.people.com.cn/rmrb/pc/layout/202502/01/node_1.html"""
                                    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:
                                        soup3 = BeautifulSoup(response3.text, 'lxml')
                                        for item2 in soup3.select(".news-list a"):
                                            url3 = f"http://paper.people.com.cn/rmrb/pc/" + item2.get(
                                                "href").replace(
                                                "../", "").strip()
                                            """http://paper.people.com.cn/rmrb/pc/content/202502/07/content_30055144.html"""
                                            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('title').text.strip()
                                                            perTitle = inner_soup.find('introtitle').text.strip()
                                                            subTitle = inner_soup.find("subtitle").text.strip()
                                                            author = inner_soup.find('author').text.strip()
                                                except:
                                                    title = title
                                                    perTitle = ""
                                                    subTitle = ""
                                                    author = ""
                                                content = await getContent(soup4)
                                                await collection.insert_one({
                                                    "title": title,
                                                    "subtitle": subTitle,
                                                    "preTitle": perTitle,
                                                    "author": author,
                                                    "banmianming": banmianming,
                                                    "banmianhao": banmianhao,
                                                    'detail_url': url3,
                                                    'release_time': period_name,
                                                    'insert_timestamp': datetime.today(),
                                                    'content': content
                                                })
                                                crawl_num += 1
                                                print(
                                                    f"人民日报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！")
                                                await asyncio.sleep(random.randint(5, 15))
                                        print(
                                            f"人民日报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！")
                                        await asyncio.sleep(random.randint(5, 15))
                            print(
                                f"人民日报---{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"人民日报采集完毕，共采集{crawl_num}条数据！")


asyncio.run(main())