fix: 修复人民邮电报偶尔出现日期匹配失败问题

国内党媒/CrawlRenminyoudianbao.py

@@ -9,7 +9,7 @@
 
 import asyncio
 import random
-from datetime import datetime, timedelta
+from datetime import datetime
 
 from bs4 import BeautifulSoup
 from httpx import AsyncClient
@@ -20,8 +20,8 @@ start_date = datetime.strptime('2017-09', '%Y-%m')
 end_date = datetime.today()
 """截止到今天"""
 headers = {
-    "connection":'keep-alive',
-    "host":"rmydb.cnii.com.cn",
+    "connection": 'keep-alive',
+    "host": "rmydb.cnii.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
@@ -67,6 +67,7 @@ async def getData(start_date: datetime, end_date: datetime):
     """
     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://rmydb.cnii.com.cn/period/yearMonthDay.json")
             response.encoding = response.charset_encoding
@@ -82,7 +83,7 @@ async def getData(start_date: datetime, end_date: datetime):
                 for day in dayList:
                     try:
                         url = f"https://rmydb.cnii.com.cn/html/{day.__str__()[:4]}/{day}/data.json"
-                    print(url)
+                        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}")
@@ -98,7 +99,7 @@ async def getData(start_date: datetime, end_date: datetime):
                                     author = article["articleAuthor"]
                                     if await collection.find_one({"detail_url": url2}, {"_id": False}):
                                         continue
-                                print(url2)
+                                    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}")
@@ -122,7 +123,8 @@ async def getData(start_date: datetime, end_date: datetime):
                                             'content': content
                                         })
                                         crawl_num += 1
-                                    print(f"人民邮电报---{day}---{banmianming}---{banmianhao}---{title}---采集完成！")
+                                        print(
+                                            f"人民邮电报---{day}---{banmianming}---{banmianhao}---{title}---采集完成！")
                                         await asyncio.sleep(random.randint(5, 15))
                                 print(f"人民邮电报---{day}---{banmianming}---{banmianhao}-----采集完成！")
                                 await asyncio.sleep(random.randint(5, 15))
@@ -143,6 +145,9 @@ async def getData(start_date: datetime, end_date: datetime):
                              'insert_timestamp': datetime.today(),
                              'content': 'empty'}
                         )
+    except Exception as e:
+        print(e)
     print(f"人民邮电报采集完毕，共采集{crawl_num}条数据！")
 
+
 asyncio.run(main())