feat: 增加农民日报

国内党媒/CrawlNongminribao.py

@@ -0,0 +1,152 @@
+# _*_ coding : UTF-8 _*_
+# @Time : 2024/11/27 21:13
+# @UpdateTime : 2024/11/27 21:13
+# @Author : haochen zhong
+# @File : CrawlNongminribao.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('2021-01', '%Y-%m')
+"""农民日报2021年1月份开始有数据"""
+end_date = datetime.today()
+"""截止到今天"""
+headers = {
+    "connection": 'keep-alive',
+    "host": "szb.farmer.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['nongminribao']
+
+
+async def main():
+    collection_names = await db.list_collection_names()
+    # 判断数据表是否存在
+    if "nongminribao" not in collection_names:
+        # 如果不存在，则从2017年9月开始爬取
+        print("农民日报数据表不存在，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
+    start_date = int(start_date.strftime("%Y%m%d"))
+    try:
+        async with AsyncClient(headers=headers, timeout=60) as client:
+            response = await client.get("https://szb.farmer.com.cn/nmrb/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://szb.farmer.com.cn/nmrb/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://szb.farmer.com.cn/nmrb/html/{day.__str__()[:4]}/{day}/{day}_{item['pageNo']}/{article['articleHref']}"
+                                    """https://szb.farmer.com.cn/nmrb/html/2024/20241127/20241127_1/nmrb_20241127_12872_1_1861525833392427013.html"""
+                                    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
+                                        author = soup.select_one(".author-style").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"农民日报---{day}---{banmianming}---{banmianhao}---{title}---采集完成！")
+                                        await asyncio.sleep(random.randint(5, 15))
+                                print(f"农民日报---{day}---{banmianming}---{banmianhao}-----采集完成！")
+                                await asyncio.sleep(random.randint(5, 15))
+                            print(f"农民日报---{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"农民日报采集完毕，共采集{crawl_num}条数据！")
+
+
+asyncio.run(main())

国内党媒/README.md

@@ -11,4 +11,5 @@
 | 9  |  ✅   |    中华人民共和国司法部     |        [法治日报](./CrawlFazhiribao.py)         |         [epaper.legaldaily.com.cn](http://epaper.legaldaily.com.cn/fzrb/content/20210101/Page01TB.htm)         | buweijiguanbao |       fazhiribao       |   法治日报2021年1月1日开始有数据   |
 | 10 |  ✅   |    中华人民共和国财政部     |    [中国财经报](./CrawlZhongguocaijingbao.py)    |                                  [114.118.9.73](http://114.118.9.73/epaper/)                                   | buweijiguanbao |   zhongguocaijingbao   |  中国财经报2017年11月份开始有数据   |
 | 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    |
+| 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   |