fix: 修复中国社会报首页正则匹配规则

国内党媒/CrawlZhongguoshehuibao.py

@@ -23,7 +23,7 @@ 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'}
 # 正则表达式提取年份、月份和数组内容
 pattern = r"_htep_(\d{4})_(\d{1,2})=new Array\((.*?)\);"
-pattern_url = r'<meta content="[^"]*URL=([^"]+)"[^>]*>'
+pattern_url = r'url=([^">]+)'
 # 链接数据库
 client = AsyncIOMotorClient('mongodb://localhost:27017')
 db = client['buweijiguanbao']
@@ -93,7 +93,7 @@ async def loading():
     end_time = time(23, 0, 0)  # 23:00:00
     # 判断当前时间是否在范围内
     if start_time <= now <= end_time:
-        # print("当前时间在07:00:00--23:00:00范围内,中国可正常采集！")
+        # print("当前时间在07:00:00--23:00:00范围内,中国社会报可正常采集！")
         return True
     else:
         print("当前时间不在07:00:00--23:00:00范围内，中国社会报无法采集")
@@ -142,6 +142,7 @@ async def getData(start_date: datetime, end_date: datetime):
                 match = re.search(pattern_url, response.text, re.IGNORECASE)
                 if match:
                     url = "https://epaper.shehuiwang.cn" + match.group(1)
+                    print(datetime.now().strftime("%Y-%m-%d %H:%M:%S"), url)
                     response = await client.get(url)
                     response.encoding = response.charset_encoding
                     print(f"一级连接状态：{response.status_code}")