guoneimeitishujucaiji/国内党媒/CrawlRenminyoudianbao.py

# _*_ coding : UTF-8 _*_
# @Time : 2024/11/11 21:41
# @UpdateTime : 2024/11/11 21:41
# @Author : haochen zhong
# @File : CrawlRenminyoudianbao.py
# @Software : PyCharm
# @Comment : 本程序采集人民邮电报


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('2024-09', '%Y-%m')
"""人民邮电报2024年9月份开始有数据"""
end_date = datetime.today()
"""截止到今天"""
headers = {
    "connection": 'keep-alive',
    "host": "rmydb.cnii.com.cn",
    '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['renminyoudianbao']


async def main():
    collection_names = await db.list_collection_names()
    # 判断数据表是否存在
    if "renminyoudianbao" not in collection_names:
        # 如果不存在，则从2017年9月开始爬取
        print("人民邮电报数据表不存在，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
    start_date = int(start_date.strftime("%Y%m%d"))
    try:
        async with AsyncClient(headers=headers, timeout=60) as client:
            response = await client.get("https://rmydb.cnii.com.cn/period/yearMonthDay.json")
            response.encoding = response.charset_encoding
            print(f"一级连接状态：{response.status_code}")
            if response.status_code == 200:
                data = response.json()
                dayList = []
                for value in data.values():
                    for item in value.values():
                        dayList += item
                dayList.sort()
                dayList = list(filter(lambda x: x >= start_date, list(map(int, dayList))))
                for day in dayList:
                    try:
                        url = f"https://rmydb.cnii.com.cn/html/{day.__str__()[:4]}/{day}/data.json"
                        print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url)
                        response = await client.get(url)
                        response.encoding = response.charset_encoding
                        print(f"二级连接状态：{response.status_code}")
                        if response.status_code == 200:
                            data = response.json()
                            for item in data:
                                banmianming = item["pageName"]
                                banmianhao = f"第{item['pageNo']}版"
                                for article in item["onePageArticleList"]:
                                    title = article["mainTitle"]
                                    url2 = f"https://rmydb.cnii.com.cn/html/{day.__str__()[:4]}/{day}/{day}_{item['pageNo']}/{article['articleHref']}"
                                    """https://rmydb.cnii.com.cn/html/2024/20240906/20240906_001/20240906_001_01_523.html"""
                                    author = article["articleAuthor"]
                                    if await collection.find_one({"detail_url": url2}, {"_id": False}):
                                        continue
                                    print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2)
                                    response2 = await client.get(url2)
                                    response2.encoding = response2.charset_encoding
                                    print(f"三级连接状态：{response2.status_code}")
                                    if response2.status_code == 200:
                                        soup = BeautifulSoup(response2.text, "lxml")
                                        preTitle = soup.select_one("#PreTitle").text
                                        title = soup.select_one("#Title").text
                                        subTitle = soup.select_one("#SubTitle").text
                                        content = await getContent(soup)
                                        await collection.insert_one({
                                            "title": title,
                                            "subtitle": subTitle,
                                            "preTitle": preTitle,
                                            "author": author,
                                            "banmianming": banmianming,
                                            "banmianhao": banmianhao,
                                            'keywordlist': "empty",
                                            'detail_url': url2,
                                            'release_time': datetime.strptime(str(day), "%Y%m%d"),
                                            'insert_timestamp': datetime.today(),
                                            'content': content
                                        })
                                        crawl_num += 1
                                        print(
                                            f"人民邮电报---{day}---{banmianming}---{banmianhao}---{title}---采集完成！")
                                        await asyncio.sleep(random.randint(5, 15))
                                print(f"人民邮电报---{day}---{banmianming}---{banmianhao}-----采集完成！")
                                await asyncio.sleep(random.randint(5, 15))
                            print(f"人民邮电报---{day}-----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': datetime.strptime(str(day), "%Y%m%d"),
                             'insert_timestamp': datetime.today(),
                             'content': 'empty'}
                        )
    except Exception as e:
        print(e)
    print(f"人民邮电报采集完毕，共采集{crawl_num}条数据！")


asyncio.run(main())