guoneimeitishujucaiji/国内党媒/CrawlZhongguominzubao.py

# _*_ coding : UTF-8 _*_
# @Time : 2024/11/12 22:45
# @UpdateTime : 2024/11/12 22:45
# @Author : haochen zhong
# @File : CrawlZhongguominzubao.py
# @Software : PyCharm
# @Comment : 本程序采集中国民族报数据

import asyncio
import random
from datetime import datetime

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

start_date = datetime.strptime('2022-01', '%Y-%m')
"""中国民族报2022年1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'}

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


async def main():
    collection_names = await db.list_collection_names()
    # 判断数据表是否存在
    if "zhongguomizubao" 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 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
    async with AsyncClient(headers=headers, timeout=60) as client:
        for month in months:
            # 构造URL
            url = "http://210.12.104.26:81/reader/layout/getSZBDatePub.do"
            try:
                response = await client.post(url, params={"sj": month.strftime("%Y.%m")})
                response.encoding = response.charset_encoding
                print(f"一级连接状态：{response.status_code}")
                if response.status_code == 200:
                    data = response.json()
                    for item in data:
                        url2 = "http://210.12.104.26:81/reader/layout/findBmMenuPub.do"
                        response2 = await client.post(url2, params={"docPubTime": item.replace("/", "")})
                        response2.encoding = response2.charset_encoding
                        print(f"二级连接状态：{response2.status_code}")
                        if response2.status_code == 200:
                            data2 = response2.json()
                            for item2 in data2:
                                banmianming = item2["BM"]
                                banmianhao = item2["BC"]
                                url3 = f"http://210.12.104.26:81/reader/layout/getBmDetailPub.do?bc={item2['IRCATELOG']}&docpubtime={item.replace('/', '')}"
                                print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url3)
                                response3 = await client.get(url3)
                                response3.encoding = response3.charset_encoding
                                print(f"三级连接状态：{response3.status_code}")
                                if response3.status_code == 200:
                                    data3 = response3.json()
                                    for item3 in data3:
                                        url4 = "http://210.12.104.26:81/reader/layout/detailData.do"
                                        response4 = await client.post(url4, params={"guid": item3['ZB_GUID']})
                                        response4.encoding = response4.charset_encoding
                                        print(f"四级连接状态：{response4.status_code}")
                                        if response4.status_code == 200:
                                            data4 = response4.json()
                                            title = BeautifulSoup(data4['docTitle'], "lxml").text
                                            subTitle = BeautifulSoup(data4['fb'], "lxml").text
                                            preTitle = BeautifulSoup(data4['yt'], "lxml").text
                                            author = data4['docAuthor']
                                            content = BeautifulSoup(data4["content"], "lxml").text
                                            await collection.insert_one({
                                                "title": title,
                                                "subtitle": subTitle,
                                                "preTitle": preTitle,
                                                "author": author,
                                                "banmianming": banmianming,
                                                "banmianhao": banmianhao,
                                                'keywordlist': "empty",
                                                'detail_url': f"http://210.12.104.26:81/epaper/?id={item3['ZB_GUID']}&time={item.replace('/', '')}",
                                                'release_time': datetime.strptime(data4["docPubTime"],
                                                                                  "%Y/%m/%d %H:%M:%S"),
                                                'insert_timestamp': datetime.today(),
                                                'content': content
                                            })
                                        crawl_num += 1
                                        print(
                                            f"中国民族报---{item}---{banmianming}---{banmianhao}---{title}---采集完成！")
                                        await asyncio.sleep(random.randint(5, 15))
                                print(f"中国民族报---{item}---{banmianming}---{banmianhao}-----采集完成！")
                                await asyncio.sleep(random.randint(5, 15))
                    print(f"中国民族报---{item}----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': month,
                     'insert_timestamp': datetime.today(),
                     'content': 'empty'}
                )


asyncio.run(main())