fix

aidso_geo/config/base_config.py

@@ -136,6 +136,35 @@ class BaseConfig:
         }
     }
 
+
+def get_sec_id(user_id):
+    import requests
+
+    url = f"https://api.douchacha.com/open/d/hx/user/user_info?user_id={user_id}"
+
+    payload = {}
+    headers = {
+        'Authorization': 'eyJhbGciOiJIUzI1NiJ9.eyJ0eXBlIjoiUEMiLCJ1c2VySWQiOjEzOTE2OTMxOTU3NTQyMjU2NjQsImNyZWF0ZURhdGUiOiIyMDI2LTA2LTAzIDE3OjE4OjEzIiwiZXhwIjoxNzgzMDcwMjkzfQ.S12OckXnT7PZot-dnQHPFoFmL3GTZ8M1IDL6x2aWeKU'
+    }
+
+    response = requests.request("GET", url, headers=headers, data=payload)
+
+    return response.json().get('data').get('sec_uid')
+
+
+def get_user_info(secUid):
+
+    import requests
+    url = f"http://172.16.1.37:8873/collect_user_info?secUid={secUid}"
+
+    payload = {}
+    headers = {}
+
+    response = requests.request("GET", url, headers=headers, data=payload)
+
+    print(response.text)
+
+
 if __name__ == '__main__':
     key_list = ['BDAI:geo:stream_batch:list',
 'BDAI:geo:batch:list',
@@ -163,11 +192,25 @@ if __name__ == '__main__':
 'WXYY:geo:batch:list',
 'geo:task_commit:list']
     t = init_redis()
-#     # print(t.scard('mt_third_task'))
+
+
+    # aa = list(aa)
+
+
+    # for a in aa:
+    #     sec_uid = get_sec_id(a)
+    #     get_user_info(sec_uid)
+    # print(t.scard('third_hx_user_id'))
     while 1:
         for k in key_list:
             print(f"{k}----{t.llen(k)}")
         time.sleep(10)
-    # key = "third_cx_user_id"
+
     #
-    # print(len(t.smembers(key)))
+    # print(len(t.smembers(key)))
\ No newline at end of file
+
+
+
+
+
+

aidso_geo/core/feishu_snipaste.py

@@ -141,6 +141,8 @@ def send_message(message):
 
 
 
+
+
 def get_task():
     all_items = []
     page_token = None
@@ -818,7 +820,7 @@ def runner_thread():
         for cn in (0, 1, 2):
             try:
                 rows = bh_utils.query_data(
-                    f"select reqId,prompt,rank from geo_third_task_log where cn = {cn} and pt = {pt_today}"
+                    f"select reqId,prompt,rank,pt from geo_third_task_log where cn = {cn} and pt = {pt_today}"
                 ) or []
                 for row in rows:
                     row["thinking_enabled"] = "1"
@@ -1076,8 +1078,8 @@ def webhook_snipaste(promp_list):
 
 if __name__ == "__main__":
 
-    # t1 = threading.Thread(target=scheduler_thread, daemon=True)
-    # t2 = threading.Thread(target=runner_thread, daemon=True)
+    t1 = threading.Thread(target=scheduler_thread, daemon=True)
+    t2 = threading.Thread(target=runner_thread, daemon=True)
     # t1.start()
     # t2.start()
     # t1.join()

aidso_geo/models/doubao_data_process.py

 import json
+import traceback
 
 from aidso_geo.models import spider_save_tos
 from aidso_geo.utils import robot_utils, tos_utils, bh_utils
@@ -137,6 +138,7 @@ def doubao_process_original_data(file_path):
                                                suggestions,rich_media_block)
         return (file_path, search_keyword, url_list, think_content, response_content, suggestions)
     except Exception as e:
+        traceback.print_exc()
         parts = file_path.split('/')
         platform = parts[2]
         task_id = parts[1]
@@ -162,7 +164,7 @@ def doubao_process_original_data(file_path):
 
 
 if __name__ == '__main__':
-    file_path = 'geo/21430906-2656-4ba4-b884-5f937745734c/DB/original.text'
+    file_path = 'geo/50adc4fd-40de-4352-bb63-649207718036/DB/original.text'
 
     doubao_process_original_data(file_path)
 

aidso_geo/models/process.py

 import json
+import traceback
 
 import aidso_geo.utils.bh_utils as bh_utils
 import time
@@ -1084,6 +1085,10 @@ def mark_source_mentioned(source_list, word_list):
 
     return result
 
+def norm_source_id(v):
+    if v is None:
+        return ""
+    return str(v).strip()
 
 def merge_mentioned(snippet_mention, quotes):
     mentioned_map = {item["sourceId"]: item["hasBrand"] for item in snippet_mention}
@@ -1093,9 +1098,11 @@ def merge_mentioned(snippet_mention, quotes):
 
 
 def merge_sentiment(snippet_mention, quotes):
-    mentioned_map = {item["sourceId"]: item["sentiment"] for item in snippet_mention}
+    mentioned_map = {norm_source_id(item.get("sourceId")): item.get("sentiment", "NEUTRAL")for item in snippet_mention}
     for item in quotes:
-        item["sentiment"] = mentioned_map.get(item["sourceId"], "NEUTRAL")
+        sid = norm_source_id(item.get("sourceId"))
+        item["sentiment"] = mentioned_map.get(sid, "NEUTRAL")
+
     return quotes
 
 
@@ -1629,6 +1636,7 @@ def platform_process(data):
 
         return True
     except Exception as e:
+        traceback.print_exc()
         logger.exception(
             f"{data['reqId']}--{data['platform']}--{data['prompt']}--PROCESS_FAIL"
         )
@@ -1838,21 +1846,25 @@ if __name__ == '__main__':
     from concurrent.futures import ThreadPoolExecutor, as_completed
 
     #
-    # begin = '2026-05-23'
-    # end = '2026-05-29'
-    # req_list = get_req_id(15100000026,begin,end)
-    #
+    # begin = '2026-05-28'
+    # end = '2026-06-04'
+    # req_list = get_req_id(18900000004,begin,end)
+    # b = "开云集团"
     # req_ids = []
     # for item in req_list:
-    #     req_id = item.get("req_id")
-    #     req_ids.append(req_id)
+    #     if item.get('brand_name') == b:
+    #         req_id = item.get("req_id")
+    #         req_ids.append(req_id)
     # req_id_sql = ",".join([f"'{req_id}'" for req_id in req_ids])
+    # print(req_id_sql)
+    # # print(len(req_ids))
+    query_sql = f"select * from geo_commit_task where reqId in ('e436cdd6-9342-4c67-b894-82bc8dc337a5')"
 
-    query_sql = f"select * from geo_commit_task where type = 'stream_batch' and  status != 'SUCCESS'"
-    data_list = bh_utils.query_data(query_sql)
     # print(len(data_list))
     #
-    # data_list = bh_utils.query_data(f"select * from geo_commit_task where status !='SUCCESS' and type = 'stream_batch' ")
+    # data_list = bh_utils.query_data(f"select * from geo_commit_task where status ='ING' and type = 'stream_batch' ")
+    data_list = bh_utils.query_data(query_sql)
+    # print(data_list)
     # # #
     # # #
     # # # # #

aidso_geo/models/yuanbao_data_process.py

@@ -29,7 +29,6 @@ def yuanbao_process_original_data(file_path):
                     # 提取并解析JSON数据
                     data_str = i.split("data: ")[1]
                     json_data = json.loads(data_str)
-
                 except (IndexError, json.JSONDecodeError):
                     continue  # 跳过格式错误的数据
 
@@ -75,6 +74,6 @@ def yuanbao_process_original_data(file_path):
 
 if __name__ == '__main__':
     # https://tcdn.aidso.com/geo/c7581554-435b-47ca-a2e5-d52bea763b8a/DOUBA/search_keyword.txt?secret=11049cbfb1c7018597a2085455505304520f0507080c0c4b514e09
-    file_path = 'geo/5582d220-f032-4095-ad39-1dbc33a536c3/TXYB/original.text'
+    file_path = 'geo/b55be837-48a9-476a-8290-1339ea2ce3f9/TXYB/original.text'
     yuanbao_process_original_data(file_path)