From 5844aa24d8eaad5860673492208eef45f9009d45 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E7=9A=93=E6=9C=88=E5=BD=92=E5=B0=98?= Date: Thu, 28 Nov 2024 23:01:21 +0800 Subject: [PATCH] =?UTF-8?q?feat:=20=E6=B7=BB=E5=8A=A0=E5=9B=BD=E9=99=85?= =?UTF-8?q?=E5=95=86=E6=8A=A5?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- 国内党媒/CrawlGuojishangbao.py | 177 +++++++++++++++++++++++++++++++++ 国内党媒/README.md | 1 + 2 files changed, 178 insertions(+) create mode 100644 国内党媒/CrawlGuojishangbao.py diff --git a/国内党媒/CrawlGuojishangbao.py b/国内党媒/CrawlGuojishangbao.py new file mode 100644 index 0000000..51ebda4 --- /dev/null +++ b/国内党媒/CrawlGuojishangbao.py @@ -0,0 +1,177 @@ +# _*_ coding : UTF-8 _*_ +# @Time : 2024/11/28 22:34 +# @UpdateTime : 2024/11/28 22:34 +# @Author : haochen zhong +# @File : CrawlGuojishangbao.py +# @Software : PyCharm +# @Comment : 本程序 + +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('2022-08', '%Y-%m') +"""国际商报2022年8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['guojishangbao'] + + +async def main(): + collection_names = await db.list_collection_names() + # 判断数据表是否存在 + if "guojishangbao" not in collection_names: + # 如果不存在，则从2017年9月开始爬取 + print("国际商报数据表不存在，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 + 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://epa.comnews.cn/pc/layout/{month.strftime("%Y%m")}/period.xml' + """https://epa.comnews.cn/pc/layout/202209/period.xml""" + print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url) + 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"): + try: + period_name = datetime.strptime(period.find("period_name").text.strip(), "%Y-%m-%d") + front_page = period.find("front_page").text.strip() + url1 = f"https://epa.comnews.cn/pc/layout/{period_name.strftime('%Y%m/%d')}/{front_page}" + """https://epa.comnews.cn/pc/layout/202410/30/node_01.html""" + 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(".posRelative > a"): + banmianming = item.text.split("：")[-1] + banmianhao = item.text.split("：")[0] + url2 = f"https://epa.comnews.cn/pc/layout/{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') + for item2 in soup3.select("#articlelist a"): + url3 = f"https://epa.comnews.cn/pc/" + item2.get("href").replace("../", + "").strip() + 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, title) + 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("#Title").text.strip() + except: + title = title + try: + subTitle = soup4.select_one("#SubTitle").text.strip() + except: + subTitle = "" + try: + perTitle = soup4.select_one("#PreTitle").text.strip() + except: + perTitle = "" + content = await getContent(soup4) + await collection.insert_one({ + "title": title, + "subtitle": subTitle, + "preTitle": perTitle, + "author": "", + "banmianming": banmianming, + "banmianhao": banmianhao, + 'keywordlist': "empty", + 'detail_url': url3, + 'release_time': period_name, + 'insert_timestamp': datetime.today(), + 'content': content + }) + crawl_num += 1 + print( + f"国际商报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！") + await asyncio.sleep(random.randint(5, 15)) + print( + f"国际商报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！") + await asyncio.sleep(random.randint(5, 15)) + print(f"国际商报---{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"国际商报采集完毕，共采集{crawl_num}条数据！") + + +asyncio.run(main()) diff --git a/国内党媒/README.md b/国内党媒/README.md index c3e2b4a..29d4ee4 100644 --- a/国内党媒/README.md +++ b/国内党媒/README.md @@ -13,3 +13,4 @@ | 11 | ✅ | 中华人民共和国自然资源部 | [中国自然资源报](./CrawlZhongguoziranziyuanbao.py) | [szb.iziran.net](http://szb.iziran.net/bz/html/index.html?date=2024-11-21&cid=1) | buweijiguanbao | zhongguoziranziyuanbao | 中国自然资源报2018年5月18日开始有数据 | | 12 | ✅ | 中华人民共和国生态环境部 | [中国环境报](./CrawlZhongguohuanjingbao.py) | [news.cenews.com.cn](http://news.cenews.com.cn/html/2024-10/30/node_2.htm) | buweijiguanbao | zhongguohuanjingbao | 中国环境报2013年8月开始有数据 | | 13 | ✅ | 中华人民共和国农业农村部 | [农民日报](./CrawlNongminribao.py) | [szb.farmer.com.cn](https://szb.farmer.com.cn/nmrb/html/2024/20241127/20241127_1/nmrb_20241127_12872_1.html) | buweijiguanbao | nongminribao | 农民日报2021年1月13日开始有数据 | +| 14 | ✅ | 中华人民共和国商务部 | [国际商报](./CrawlGuojishangbao.py) | [epa.comnews.cn](https://epa.comnews.cn/pc/layout/202208/26/node_01.html) | buweijiguanbao | guojishangbao | 国际商报2022年8月1日开始有数据 | \ No newline at end of file