feat: 添加安徽日报同步版本

地方政策/报刊/CrawlAnhui-sync.py

@@ -0,0 +1,143 @@
+# _*_ 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()