guoneimeitishujucaiji/地方政策/报刊/CrawlAnhui.py

# _*_ coding : UTF-8 _*_
# @Time : 2024/11/08 20:29
# @UpdateTime : 2024/11/08 20:29
# @Author : haochen zhong
# @File : CrawlAnhui.py
# @Software : PyCharm
# @Comment : 本程序采集安徽日报数字报数据


import asyncio
import random
from datetime import datetime, timedelta

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

start_date = datetime.strptime('2017-09-29', '%Y-%m-%d')
"""安徽日报报2017年09月29日开始有数据"""
end_date = datetime.today()
"""截止到今天"""
headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6,zh-TW;q=0.5,de-DE;q=0.4,de;q=0.3',
    'Connection': 'keep-alive',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36 Edg/130.0.0.0',
    'sec-ch-ua': '"Chromium";v="130", "Microsoft Edge";v="130", "Not?A_Brand";v="99"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Windows"',
    'sec-gpc': '1',
}

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


async def main():
    collection_names = await db.list_collection_names()
    # 判断数据表是否存在
    if "anhuiribao" not in collection_names:
        # 如果不存在，则从2017年9月开始爬取
        print("安徽日报报数据表不存在，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(".content p"):
        para = p.text.strip()
        if para:
            content += para
            content += '\n'
    return content


async def getData(start_date: datetime, end_date: datetime):
    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')
        base_url = "https://szb.ahnews.com.cn/ahrb/layout/" + date_now_s + '/'
        url = base_url + 'node_01.html'
        """https://szb.ahnews.com.cn/ahrb/layout/201811/01/node_01.html"""
        try:
            async with AsyncClient(headers=headers, timeout=60, http2=False) as client:
                print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url)
                for t in range(5):
                    try:
                        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')
                            for item in soup.select(".Chunkiconlist p > a:nth-child(1)"):
                                banmianming = item.text.split("：")[-1].strip()
                                banmianhao = item.text.split("：")[0].replace(" ", "").replace(" ", "").strip()
                                url1 = base_url + item.get("href")
                                print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url1)
                                for y in range(5):
                                    try:
                                        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 item2 in soup2.select(".newslist a"):
                                                url2 = "https://szb.ahnews.com.cn/ahrb/" + item2.get("href")[9:]
                                                """https://szb.ahnews.com.cn/ahrb/content/201709/29/c17310.html"""
                                                if await collection.find_one({"detail_url": url2}, {"_id": False}):
                                                    continue
                                                title = item2.text.strip()
                                                print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2)
                                                # 启用超时重连
                                                for z in range(5):
                                                    try:
                                                        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')
                                                            content = await getContent(soup3)
                                                            try:
                                                                title = soup3.select(".newsdetatit h3")[0].text.strip()
                                                            except:
                                                                title = title
                                                            try:
                                                                subTitle = soup3.select(".newsdetatext p")[
                                                                    0].text.strip()
                                                            except:
                                                                subTitle = ""
                                                            await collection.insert_one({
                                                                "title": title,
                                                                "subtitle": subTitle,
                                                                "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"安徽日报---{date_now_s}---{banmianming}---{banmianhao}---{title}---采集完成！")
                                                            await asyncio.sleep(random.randint(8, 20))
                                                            break
                                                    except Exception as e:
                                                        print(e)
                                                        # 随机等待重连
                                                        await asyncio.sleep(random.randint(8, 20))
                                                        print(f"尝试第{z + 1}次重连！")
                                            break
                                    except Exception as e:
                                        print(e)
                                        await asyncio.sleep(random.randint(8, 20))
                                        print(f"尝试第{t + 1}次重连！")
                                print(f"安徽日报---{date_now_s}---{banmianming}---{banmianhao}-----采集完成！")
                                await asyncio.sleep(random.randint(8, 20))
                            break
                    except Exception as e:
                        if t >= 4:
                            print(f"尝试第{t + 1}次重连失败，请检查网络环境！")
                            break
                        await asyncio.sleep(random.randint(8, 20))
                        print(f"尝试第{t + 1}次重连！")
                print(f"安徽日报---{date_now_s}-----采集完成！")
                await asyncio.sleep(random.randint(8, 20))
        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': date_now,
                 'insert_timestamp': datetime.today(),
                 'content': 'empty'}
            )
    print(f"安徽日报采集完毕，共采集{crawl_num}条数据！")


asyncio.run(main())