feat: 添加中国文化报

国内党媒/CrawlZhongguowenhuabao.py

@@ -0,0 +1,264 @@
+# _*_ coding : UTF-8 _*_
+# @Time : 2024/12/25 14:24
+# @UpdateTime : 2024/12/25 14:24
+# @Author : haochen zhong
+# @File : CrawlZhongguowenhuabao.py
+# @Software : PyCharm
+# @Comment : 本程序采集中国文化报版面数据
+
+
+import asyncio
+import base64
+import json
+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('2008-08', '%Y-%m')
+"""中国文化报2008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['zhongguowenhuabao']
+
+
+async def main():
+    collection_names = await db.list_collection_names()
+    # 判断数据表是否存在
+    if "zhongguowenhuabao" not in collection_names:
+        # 如果不存在，则从2008年8月开始爬取
+        print("中国文化报数据表不存在，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
+    if current_date > datetime(2020, 1, 16):
+        await getDataNew(start_date, end_date)
+    current_date = current_date.replace(day=1)
+    while current_date <= datetime(2020, 1, 15):
+        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://nepaper.ccdy.cn/html/{month.strftime("%Y-%m")}/period.xml'
+        """https://nepaper.ccdy.cn/html/2008-08/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")
+                        url1 = f"https://nepaper.ccdy.cn/html/{period_name.strftime('%Y-%m/%d')}/node_2.htm"
+                        """https://nepaper.ccdy.cn/html/2008-01/30/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://nepaper.ccdy.cn/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')
+                                    for item2 in soup3.select(".paper_div a"):
+                                        url3 = f"https://nepaper.ccdy.cn/html/{period_name.strftime('%Y-%m/%d')}/" + item2.get(
+                                            "href")
+                                        """https://nepaper.ccdy.cn/html/2009-01/01/content_17502.htm"""
+                                        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(".font01").text.strip()
+                                            except:
+                                                title = title
+                                            try:
+                                                subTitle = soup4.select(".font02")[1].text.strip()
+                                            except:
+                                                subTitle = ""
+                                            try:
+                                                author = soup4.select(".font02")[-1].text.strip()
+                                            except:
+                                                author = ""
+                                            try:
+                                                perTitle = soup4.select(".font02")[0].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"中国文化报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---采集完成！")
+                                            await asyncio.sleep(random.randint(5, 15))
+                                    print(
+                                        f"中国文化报---{period_name.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}-----采集完成！")
+                                    await asyncio.sleep(random.randint(5, 15))
+                        print(f"中国文化报---{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"中国文化报采集完毕，共采集{crawl_num}条数据！")
+
+
+async def getDataNew(start_date: datetime, end_date: datetime):
+    """
+    获取2020-01-16号后面的数据
+    """
+    crawl_num = 0
+    for i in range(0, (end_date - start_date).days + 1, 30):
+        date_now = start_date + timedelta(days=i)
+        start_now = date_now - timedelta(days=30)
+        start_now_s = start_now.strftime("%Y-%m-%d")
+        date_now_s = date_now.strftime('%Y-%m-%d')
+        token = "5ea1ae83de3c22d2703a5b08"
+        params = {"condition": {"date": {"$lte": date_now_s, "$gte": start_now_s}, "state": ["Y"]},
+                  "range": {"structure": 0, "data": 1, "total": 0}, "content": "", "sort": {"date": "-1"},
+                  "pagination": {"currentPage": 1, "pageSize": 30}}
+        url = f"https://zcy.ccmapp.cn/apis/resource/digitalboardnew/get?token={token}&data={base64.b64encode(str(json.dumps(params, ensure_ascii=False)).encode('utf-8')).decode('utf-8')}"
+        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)
+                print(f"一级连接状态：{response.status_code}")
+                if response.status_code == 200 and response.json()['code'] == 200:
+                    data = response.json()
+                    for item in data['data']["list"]:
+                        date = datetime.strptime(item['date'], '%Y-%m-%d')
+                        digitaldata = json.loads(item['digitaldata'])
+                        for item2 in digitaldata["data"]:
+                            banmianming = item2.get('pageTitle', "")
+                            banmianhao = f"第{item2['pageNo']}版"
+                            indexTitle = item2["indexTitle"]
+                            for item3 in item2['polygons']:
+                                hid = item3["id"]
+                                url2 = f"https://npaper.ccmapp.cn/zh-CN/?date={item['date']}&page={indexTitle}&Hid={hid}"
+                                if await collection.find_one({"detail_url": url2}, {"_id": False}):
+                                    continue
+                                title = item3.get("title", "")
+                                subtitle = item3["subtitle"]
+                                description = item3["description"]
+                                content = BeautifulSoup(item3["content"], 'lxml').text
+                                await collection.insert_one({
+                                    "title": title,
+                                    "subtitle": subtitle,
+                                    "preTitle": description,
+                                    "author": "empty",
+                                    "banmianming": banmianming,
+                                    "banmianhao": banmianhao,
+                                    'keywordlist': "empty",
+                                    'detail_url': url2,
+                                    'release_time': date,
+                                    'insert_timestamp': datetime.today(),
+                                    'content': content
+                                })
+                                crawl_num += 1
+                                print(
+                                    f"中国文化报---{date.strftime('%Y-%m-%d')}----{banmianming}---{banmianhao}---{title}---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': date_now,
+                 'insert_timestamp': datetime.today(),
+                 'content': 'empty'}
+            )
+    print(f"中国文化报采集完毕，共采集{crawl_num}条数据！")
+
+
+asyncio.run(main())

国内党媒/README.md

@@ -13,4 +13,5 @@
 | 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   |
+| 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   |
+| 15 |  ✅   |   中华人民共和国文化和旅游部   |     [中国文化报](./CrawlZhongguolvyoubao.py)     |                           [npaper.ccmapp.cn](https://npaper.ccmapp.cn/zh-CN/?page=1)                           | buweijiguanbao |    zhongguolvyoubao    |   中国文化报2008年8月开始有数据    |