guoneimeitishujucaiji/国内党媒/CrawlKejiribao.py

# _*_ coding : UTF-8 _*_
# @Time : 2024/11/10 21:23
# @UpdateTime : 2024/11/10 21:23
# @Author : haochen zhong
# @File : CrawlKejiribao.py
# @Software : PyCharm
# @Comment : 本程序采集科技日报数据


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('2011-01', '%Y-%m')
"""科技日报报2011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['kejiribao']


async def main():
    collection_names = await db.list_collection_names()
    # 判断数据表是否存在
    if "kejiribao" not in collection_names:
        # 如果不存在，则从2017年9月开始爬取
        print("科技日报数据表不存在，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:
        # 构造URL
        url = f'https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{month.strftime("%Y-%m")}/period.xml'
        """https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/2011-10/period.xml"""
        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
                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.select_one("period_name").text.strip(), "%Y-%m-%d")
                        front_page = period.select_one("front_page").text.strip()
                        url1 = f"https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{period_name.strftime('%Y-%m/%d')}/{front_page}"
                        """https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/2024-10/30/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("#pageLink"):
                                banmianming = item.text.split("：")[-1]
                                banmianhao = item.text.split("：")[0]
                                url2 = f"https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{period_name.strftime('%Y-%m/%d')}/" + item.get(
                                    "href").replace("./", "").strip()
                                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')
                                    pages = soup3.select(".ul02_l a")
                                    if pages:
                                        titleTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > strong"
                                        subTitleTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > span:nth-child(5)"
                                        preTitleTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > span:nth-child(1)"
                                        authorTag = "body > table:nth-child(2) > tbody > tr:nth-child(1) > td:nth-child(2) > table:nth-child(3) > tbody > tr:nth-child(1) > td > table > tbody > tr > td > span:nth-child(7)"
                                    else:
                                        pages = soup3.select(".title a")
                                        titleTag = ".biaoti"
                                        subTitleTag = ".futi"
                                        preTitleTag = ".yinti"
                                        authorTag = ".autor"
                                    for item2 in pages:
                                        url3 = f"https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/{period_name.strftime('%Y-%m/%d')}/" + item2.get(
                                            "href")
                                        """https://digitalpaper.stdaily.com/http_www.kjrb.com/kjrb/html/2024-10/30/content_579753.htm?div=-1"""
                                        if await collection.find_one({"detail_url": url3}, {"_id": False}):
                                            continue
                                        title = item2.text.strip()
                                        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, 'lxml')
                                            try:
                                                title = soup4.select_one(titleTag).text.strip()
                                            except:
                                                title = title
                                            try:
                                                subTitle = soup4.select(subTitleTag)[0].text.strip()
                                            except:
                                                subTitle = ""
                                            try:
                                                author = soup4.select_one(authorTag).text.strip()
                                            except:
                                                author = ""
                                            try:
                                                perTitle = soup4.select(preTitleTag)[-1].text.strip()
                                            except:
                                                perTitle = ""
                                            try:
                                                keywordlist = soup4.find("founder-keyword").text.strip()
                                            except:
                                                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"科技日报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！")
                                            await asyncio.sleep(random.randint(5, 15))
                                    print(
                                        f"科技日报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！")
                                    await asyncio.sleep(random.randint(5, 15))
                        print(f"科技日报---{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"科技日报采集完毕，共采集{crawl_num}条数据！")


asyncio.run(main())