guoneimeitishujucaiji/地方政策/报刊/CrawlAnhui-sync.py

# _*_ coding : UTF-8 _*_
# @Time : 2024/11/13 13:42
# @UpdateTime : 2024/11/13 13:42
# @Author : haochen zhong
# @File : CrawlAnhui-sync.py
# @Software : PyCharm
# @Comment : 本程序采集

import random
import time
from datetime import timedelta, datetime

import pymongo
import requests
from bs4 import BeautifulSoup

start_date = datetime.strptime('2017-09-29', '%Y-%m-%d')
"""安徽日报报2018年09月29日开始有数据"""
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 = pymongo.MongoClient('mongodb://localhost:27017')
db = client['dfdm_sjribao']
collection = db['anhuiribao']


def main():
    collection_names = 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！")
        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 = 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)
        getData(last_date_str, end_date)


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


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)
        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:
            print(url)
            response = requests.get(url=url, headers=headers, timeout=60)
            response.encoding = response.apparent_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)
                    response2 = requests.get(url1, headers=headers, timeout=60)
                    response2.encoding = response2.apparent_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 collection.find_one({"detail_url": url2}, {"_id": False}):
                                continue
                            title = item2.text.strip()
                            print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url2)
                            response3 = requests.get(url=url2, headers=headers, timeout=60)
                            response3.encoding = response3.apparent_encoding
                            print(f"三级连接状态：{response3.status_code}")
                            if response3.status_code == 200:
                                soup3 = BeautifulSoup(response3.text, 'lxml')
                                content = 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 = ""
                                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！")
                                time.sleep(random.randint(5, 15))
                    print(f"安徽日报---{date_now_s}---{banmianming}---{banmianhao}-----采集完成！")
                    time.sleep(random.randint(5, 15))
                print(f"安徽日报---{date_now_s}-----采集完成！")
                time.sleep(random.randint(5, 15))
        except Exception as e:
            print(e)
            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！")


main()