小红书时间修复

aidso_geo/models/spider_save_tos.py

 import json
 import os
 
-
+import re
+from datetime import datetime,timedelta
 from aidso_geo.utils.tos_utils import put_string_to_tos
 from aidso_geo.utils import bh_utils
 from aidso_geo.utils import url_utils
@@ -285,10 +286,62 @@ def yuanbao_android_process_quote(url_list):
         quto_list.append(raw_data)
     return quto_list
 
+def parse_date_to_ymd(value, now=None):
+
+    if now is None:
+        now = datetime.now()
+
+    if value is None:
+        return ""
+
+    value = str(value).strip()
+
+    if not value or value in ("空", "null", "None", "-"):
+        return ""
+
+    # 2026-05-30
+    if re.fullmatch(r"\d{4}-\d{1,2}-\d{1,2}", value):
+        dt = datetime.strptime(value, "%Y-%m-%d")
+        return dt.strftime("%Y-%m-%d")
+
+    # 05-30，默认补当前年份
+    if re.fullmatch(r"\d{1,2}-\d{1,2}", value):
+        year = now.year
+        dt = datetime.strptime(f"{year}-{value}", "%Y-%m-%d")
+        return dt.strftime("%Y-%m-%d")
+
+    # 1天前 / 10天前
+    match = re.fullmatch(r"(\d+)天前", value)
+    if match:
+        days = int(match.group(1))
+        dt = now - timedelta(days=days)
+        return dt.strftime("%Y-%m-%d")
+
+    # 10小时前 / 1小时前
+    match = re.fullmatch(r"(\d+)小时前", value)
+    if match:
+        hours = int(match.group(1))
+        dt = now - timedelta(hours=hours)
+        return dt.strftime("%Y-%m-%d")
+
+    # 今天
+    if value == "今天":
+        return now.strftime("%Y-%m-%d")
+
+    # 昨天
+    if value == "昨天":
+        return (now - timedelta(days=1)).strftime("%Y-%m-%d")
+
+    return ""
+
+
 def xiaohongshu_android_process_quote(url_list):
     quto_list = []
 
     for index, item in enumerate(url_list):
+        published_at = item.get('time', '')
+        published_at = parse_date_to_ymd(published_at)
+
         url = ""
         id = item.get('id')
         if id:
@@ -298,7 +351,7 @@ def xiaohongshu_android_process_quote(url_list):
             "title": item.get('title', ''),
             "snippet": item.get('content', ''),
             "index": index,
-            "published_at": item.get('time', ''),
+            "published_at":published_at ,
             "site_name": '小红书',
             "site_icon": 'www.xiaohongshu.com',
         }
@@ -521,3 +574,5 @@ def process_and_save_files_ai(file_path, search_keyword, url_list, think_content
     ]
     for content, file_name in data_config:
         save_data_to_tos_ai(target_dir, content, file_name)
+
+# if __name__ == '__main__':

aidso_geo/models/xiaohongshu_android_data_process.py

@@ -2,7 +2,7 @@ import json
 import traceback
 
 from aidso_geo.models import spider_save_tos
-from aidso_geo.utils import robot_utils
+from aidso_geo.utils import robot_utils, bh_utils
 from aidso_geo.utils.ai_interface import get_parse_sse_result
 from aidso_geo.utils.tos_utils import get_string_from_tos
 
@@ -28,6 +28,8 @@ def xiaohongshu_android_process_original_data(data):
         items = json_content.get('items')
         response_content = base_info.get('text')
         url_list = items
+
+
         if "</complex_list>" in response_content:
             response_content = response_content.replace('</complex_list>','')
 
@@ -59,5 +61,33 @@ def xiaohongshu_android_process_original_data(data):
     return (file_path, search_keyword, url_list, think_content, response_content, suggestions)
 
 if __name__ == '__main__':
-    file_path2 = 'geo/XHSA-XHSA-01-2XH12SA-X1H22SA1/XHSA/original.text'
-    xiaohongshu_android_process_original_data(file_path2)
+    # file_path2 = 'geo/7ac6f0c7-988d-4c3e-a45b-f317e144b68e/XHSA/original.text'
+    # xiaohongshu_android_process_original_data(file_path2)
+
+
+    data_list = bh_utils.query_data(f"select * from geo_commit_task  where platform  = 'XHSA' and taskId = 'aeb60818-5221-4062-820d-e4523f184d56'")
+
+    # # #
+    # # #
+    # # # # #
+    def handle_item(i):
+        if i.get('comWordsMap'):
+            i['comWordsMap'] = json.loads(i.get('comWordsMap'))
+        if i.get('brandWords'):
+            i['brandWords'] = json.loads(i.get('brandWords'))
+        if i.get('comWords'):
+            i['comWords'] = json.loads(i.get('comWords'))
+        if i.get('keywords'):
+            i['keywords'] = json.loads(i.get('keywords'))
+        if i.get('productWordsMap'):
+            i['productWordsMap'] = json.loads(i.get('productWordsMap'))
+        print(i.get('taskId'))
+        return xiaohongshu_android_process_original_data(i)
+
+# 喜欢非遗手作的看这里！周末到河北之涿州！
+    if data_list:
+        for i in data_list:
+            try:
+                handle_item(i)
+            except Exception as e:
+                ...

aidso_geo/utils/robot_utils.py

@@ -5,102 +5,8 @@ import json
 from loguru import logger
 from apscheduler.schedulers.blocking import BlockingScheduler
 
-from aidso_geo.config.base_config import init_redis, init_redis8
+from aidso_geo.config.base_config import init_redis
 from aidso_geo.utils import bh_utils
-from datetime import datetime
-
-redis_client = init_redis8()
-
-
-def safe_int(value, default=0):
-    try:
-        if value is None:
-            return default
-        return int(value)
-    except Exception:
-        return default
-
-
-def get_active_channels():
-    """
-    查询所有启用中的第三方 channel
-    """
-    sql = """
-        select channel, daily_limit, total_limit
-        from geo_third_token
-        where status = 1
-    """
-    return bh_utils.query_data(sql) or []
-
-
-def sync_third_usage_once():
-    """
-    每小时同步第三方 token 用量快照。
-
-    读取：
-    1. Redis hash third_geo_daily：field = channel + YYYYMMDD
-    2. Redis hash third_geo_total：field = channel
-
-    写入：
-    geo_third_usage_snapshot
-    """
-    now = datetime.now()
-    today_pt = now.strftime("%Y%m%d")
-    sync_time = now.strftime("%Y-%m-%d %H:%M:%S")
-    insertime = int(time.time())
-
-    try:
-        channels = get_active_channels()
-        if not channels:
-            logger.info(f"[{sync_time}] sync_third_usage_once 无启用中的 channel")
-            return
-
-        # 一次性拉 Redis hash，避免用户多时频繁 hget
-        daily_map = redis_client.hgetall("third_geo_daily") or {}
-        total_map = redis_client.hgetall("third_geo_total") or {}
-
-        insert_rows = []
-
-        for item in channels:
-            channel = str(item.get("channel", "")).strip()
-            if not channel:
-                continue
-
-            daily_limit = safe_int(item.get("daily_limit"), 0)
-            total_limit = safe_int(item.get("total_limit"), 0)
-
-            daily_key = f"{channel}{today_pt}"
-
-            today_used = safe_int(daily_map.get(daily_key), 0)
-            total_used = safe_int(total_map.get(channel), 0)
-
-            insert_rows.append({
-                "channel": channel,
-                "pt": today_pt,
-                "daily_limit": daily_limit,
-                "total_limit": total_limit,
-                "today_used": today_used,
-                "total_used": total_used,
-                "today_remain": max(daily_limit - today_used, 0),
-                "total_remain": max(total_limit - total_used, 0),
-                "sync_time": sync_time,
-                "insertime": insertime
-            })
-
-        if not insert_rows:
-            logger.info(f"[{sync_time}] sync_third_usage_once 无可写入数据")
-            return
-
-        ok = bh_utils.insert_data("geo_third_usage_snapshot", insert_rows)
-        if ok:
-            logger.info(f"[{sync_time}] sync_third_usage_once 同步成功 rows={len(insert_rows)}")
-        else:
-            logger.error(f"[{sync_time}] sync_third_usage_once 同步失败 rows={len(insert_rows)}")
-
-    except Exception as e:
-        logger.exception(f"[{sync_time}] sync_third_usage_once 执行异常: {e}")
-
-
 
 owner_map = {
     "XHSA": "崔士豪",
@@ -120,7 +26,7 @@ owner_map = {
 
 platform_list = [
     "BDAI", "DB", "DOUBA", "DP", "DPA", "DYAI",
-    "KIMI", "TXYB", "TXYBA", "TYQW", "TYQWA", "WXYY"
+    "KIMI", "TXYB", "TXYBA", "TYQW", "TYQWA", "WXYY", "XHSA"
 ]
 
 
@@ -366,21 +272,9 @@ if __name__ == '__main__':
         replace_existing=True
     )
 
-    scheduler.add_job(
-        sync_third_usage_once,
-        trigger='cron',
-        minute=5,
-        id='sync_third_usage_once',
-        max_instances=1,
-        coalesce=True,
-        replace_existing=True
-    )
     logger.info(
         "定时任务注册完成："
         "fail_task_send_feishu(每6小时), "
-        "task_queue_backlog(每小时), "
-        "sync_third_usage_once(每小时)"
+        "task_queue_backlog(每小时)"
     )
     scheduler.start()
-
-