oafuncs 0.0.66__py2.py3-none-any.whl → 0.0.68__py2.py3-none-any.whl

oafuncs/oa_down/hycom_3hourly.py

@@ -4,13 +4,13 @@
 Author: Liu Kun && 16031215@qq.com
 Date: 2024-11-01 10:31:09
 LastEditors: Liu Kun && 16031215@qq.com
-LastEditTime: 2024-11-30 11:40:53
+LastEditTime: 2024-11-30 20:24:34
 FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\oa_down\\hycom_3hourly.py
 Description:
 EditPlatform: vscode
 ComputerInfo: XPS 15 9510
 SystemInfo: Windows 11
-Python Version: 3.11
+Python Version: 3.12
 '''
 import datetime
 import os
@@ -29,7 +29,7 @@ from rich.progress import Progress
 
 warnings.filterwarnings("ignore", category=RuntimeWarning, message="Engine '.*' loading failed:.*")
 
-__all__ = ['draw_time_range', 'download', 'how_to_use', 'get_time_list', 'get_hour_list', 'get_day_list']
+__all__ = ['draw_time_range', 'download', 'how_to_use', 'get_time_list']
 
 # time resolution
 data_info = {'yearly': {}, 'monthly': {}, 'daily': {}, 'hourly': {}}
@@ -229,106 +229,46 @@ def draw_time_range(pic_save_folder=None):
     plt.close()
 
 
-def transform_time(time_str):
-    # old_time = '2023080203'
-    # time_new = '2023-08-02T03%3A00%3A00Z'
-    time_new = f'{time_str[:4]}-{time_str[4:6]}-{time_str[6:8]}T{time_str[8:10]}%3A00%3A00Z'
-    return time_new
-
-
-def get_time_list(time_s, time_e, delta_hour):
-    '''
-    Description: get a list of time strings from time_s to time_e with delta_hour
-    Args:
-        time_s: start time string, e.g. '2023080203'
-        time_e: end time string, e.g. '2023080303'
-        delta_hour: interval of hours
-    Returns:
-        dt_list: a list of time strings
-    '''
-    dt = datetime.datetime.strptime(time_s, '%Y%m%d%H')
-    dt_list = []
-    while dt.strftime('%Y%m%d%H') <= time_e:
-        dt_list.append(dt.strftime('%Y%m%d%H'))
-        dt = dt + datetime.timedelta(hours=delta_hour)
-    return dt_list
-
-
-def get_hour_list(time_s, time_e, delta_hour):
+def get_time_list(time_s, time_e, delta, interval_type='hour'):
     '''
-    Description: get a list of time strings from time_s to time_e with delta_hour
+    Description: get a list of time strings from time_s to time_e with a specified interval
     Args:
-        time_s: start time string, e.g. '2023080203'
-        time_e: end time string, e.g. '2023080303'
-        delta_hour: interval of hours
+        time_s: start time string, e.g. '2023080203' for hours or '20230802' for days
+        time_e: end time string, e.g. '2023080303' for hours or '20230803' for days
+        delta: interval of hours or days
+        interval_type: 'hour' for hour interval, 'day' for day interval
     Returns:
         dt_list: a list of time strings
     '''
-    dt = datetime.datetime.strptime(time_s, '%Y%m%d%H')
-    dt_list = []
-    while dt.strftime('%Y%m%d%H') <= time_e:
-        dt_list.append(dt.strftime('%Y%m%d%H'))
-        dt = dt + datetime.timedelta(hours=delta_hour)
-    return dt_list
-
+    time_s, time_e = str(time_s), str(time_e)
+    if interval_type == 'hour':
+        time_format = '%Y%m%d%H'
+        delta_type = 'hours'
+    elif interval_type == 'day':
+        time_format = '%Y%m%d'
+        delta_type = 'days'
+        # Ensure time strings are in the correct format for days
+        time_s = time_s[:8]
+        time_e = time_e[:8]
+    else:
+        raise ValueError("interval_type must be 'hour' or 'day'")
 
-def get_day_list(time_s, time_e, delta_day):
-    '''
-    Description: get a list of time strings from time_s to time_e with delta_hour
-    Args:
-        time_s: start time string, e.g. '20230802'
-        time_e: end time string, e.g. '20230803'
-        delta_hour: interval of hours
-    Returns:
-        dt_list: a list of time strings
-    '''
-    time_s = time_s[:8]
-    time_e = time_e[:8]
-    dt = datetime.datetime.strptime(time_s, '%Y%m%d')
+    dt = datetime.datetime.strptime(time_s, time_format)
     dt_list = []
-    while dt.strftime('%Y%m%d') <= time_e:
-        dt_list.append(dt.strftime('%Y%m%d'))
-        dt = dt + datetime.timedelta(days=delta_day)
+    while dt.strftime(time_format) <= time_e:
+        dt_list.append(dt.strftime(time_format))
+        dt += datetime.timedelta(**{delta_type: delta})
     return dt_list
 
 
-def get_nearest_level_index(depth):
-    level_depth = [0.0, 2.0, 4.0, 6.0, 8.0, 10.0, 12.0, 15.0, 20.0, 25.0, 30.0, 35.0, 40.0, 45.0, 50.0, 60.0, 70.0, 80.0, 90.0, 100.0, 125.0, 150.0, 200.0, 250.0, 300.0, 350.0, 400.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0, 1250.0, 1500.0, 2000.0, 2500.0, 3000.0, 4000.0, 5000]
-    return min(range(len(level_depth)), key=lambda i: abs(level_depth[i]-depth))
-
-
-def set_query_dict_no_vertical(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh):
-    query_dict = {
-        'var': variable_info[var]['var_name'],
-        'north': lat_max,
-        'west': lon_min,
-        'east': lon_max,
-        'south': lat_min,
-        'horizStride': 1,
-        'time': transform_time(time_str_ymdh),
-        'addLatLon': 'true',
-        'accept': 'netcdf4',
-    }
-    return query_dict
-
-
-def set_query_dict_depth_or_level(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh):
-    query_dict = {
-        'var': variable_info[var]['var_name'],
-        'north': lat_max,
-        'west': lon_min,
-        'east': lon_max,
-        'south': lat_min,
-        'horizStride': 1,
-        'time': transform_time(time_str_ymdh),
-        'vertCoord': 0,
-        'addLatLon': 'true',
-        'accept': 'netcdf4',
-    }
-    return query_dict
+def transform_time(time_str):
+    # old_time = '2023080203'
+    # time_new = '2023-08-02T03%3A00%3A00Z'
+    time_new = f'{time_str[:4]}-{time_str[4:6]}-{time_str[6:8]}T{time_str[8:10]}%3A00%3A00Z'
+    return time_new
 
 
-def set_query_dict_full(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh):
+def get_query_dict(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh, mode='single_depth', depth=None, level_num=None):
     query_dict = {
         'var': variable_info[var]['var_name'],
         'north': lat_max,
@@ -337,64 +277,62 @@ def set_query_dict_full(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh):
         'south': lat_min,
         'horizStride': 1,
         'time': transform_time(time_str_ymdh),
-        'vertStride': 1,
+        'vertCoord': None,
+        'vertStride': None,
         'addLatLon': 'true',
         'accept': 'netcdf4',
     }
-    return query_dict
-
 
-def get_query_dict_single_depth(var, lon_min, lon_max, lat_min, lat_max, depth, time_str_ymdh):
-    if var in ['ssh']:
-        query_dict = set_query_dict_no_vertical(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh)
-    else:
-        query_dict = set_query_dict_depth_or_level(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh)
-    if var in ['u', 'v', 'temp', 'salt']:
-        print('Please ensure the depth is in the range of 0-5000 m')
-        query_dict['vertCoord'] = get_nearest_level_index(depth)+1
-    return query_dict
+    def get_nearest_level_index(depth):
+        level_depth = [0.0, 2.0, 4.0, 6.0, 8.0, 10.0, 12.0, 15.0, 20.0, 25.0, 30.0, 35.0, 40.0, 45.0, 50.0, 60.0, 70.0, 80.0, 90.0, 100.0, 125.0, 150.0, 200.0, 250.0, 300.0, 350.0, 400.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0, 1250.0, 1500.0, 2000.0, 2500.0, 3000.0, 4000.0, 5000]
+        return min(range(len(level_depth)), key=lambda i: abs(level_depth[i]-depth))
+
+    if var not in ['ssh', 'u_b', 'v_b', 'temp_b', 'salt_b'] and var in ['u', 'v', 'temp', 'salt']:
+        if mode == 'depth':
+            if depth < 0 or depth > 5000:
+                print('Please ensure the depth is in the range of 0-5000 m')
+            query_dict['vertCoord'] = get_nearest_level_index(depth) + 1
+        elif mode == 'level':
+            if level_num < 1 or level_num > 40:
+                print('Please ensure the level_num is in the range of 1-40')
+            query_dict['vertCoord'] = max(1, min(level_num, 40))
+        elif mode == 'full':
+            query_dict['vertStride'] = 1
+        else:
+            raise ValueError("Invalid mode. Choose from 'depth', 'level', or 'full'")
 
+    query_dict = {k: v for k, v in query_dict.items() if v is not None}
 
-def get_query_dict_single_level(var, lon_min, lon_max, lat_min, lat_max, level_num, time_str_ymdh):
-    if var in ['ssh']:
-        query_dict = set_query_dict_no_vertical(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh)
-    else:
-        # level_num: 1-40
-        query_dict = set_query_dict_depth_or_level(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh)
-    if var in ['u', 'v', 'temp', 'salt']:
-        print('Please ensure the level_num is in the range of 1-40')
-        if level_num == 0:
-            level_num = 1
-            print('The level_num is set to 1')
-        if level_num > 40:
-            level_num = 40
-            print('The level_num is set to 40')
-        query_dict['vertCoord'] = level_num
     return query_dict
 
 
-def get_query_dict_full_level(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh):
-    if var in ['ssh']:
-        query_dict = set_query_dict_no_vertical(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh)
-    else:
-        query_dict = set_query_dict_full(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh)
-    return query_dict
+def check_time_in_dataset_and_version(time_input, time_end=None):
+    # 判断是处理单个时间点还是时间范围
+    is_single_time = time_end is None
 
-
-def get_query_dict_full_depth(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh):
-    if var in ['ssh']:
-        query_dict = set_query_dict_no_vertical(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh)
+    # 如果是单个时间点，初始化时间范围
+    if is_single_time:
+        time_start = int(time_input)
+        time_end = time_start
+        time_input_str = str(time_input)
     else:
-        query_dict = set_query_dict_full(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh)
-    return query_dict
+        time_start = int(time_input)
+        time_end = int(time_end)
+        time_input_str = f'{time_input}-{time_end}'
 
+    # 根据时间长度补全时间格式
+    if len(str(time_start)) == 8:
+        time_start = str(time_start) + '00'
+    if len(str(time_end)) == 8:
+        time_end = str(time_end) + '21'
+    time_start, time_end = int(time_start), int(time_end)
 
-def ymdh_in_which_dataset_and_version(time_ymdh):
-    time_ymdh = int(time_ymdh)
     d_list = []
     v_list = []
     trange_list = []
     have_data = False
+
+    # 遍历数据集和版本
     for dataset_name in data_info['hourly']['dataset'].keys():
         for version_name in data_info['hourly']['dataset'][dataset_name]['version'].keys():
             time_s, time_e = list(data_info['hourly']['dataset'][dataset_name]['version'][version_name]['time_range'].values())
@@ -403,70 +341,84 @@ def ymdh_in_which_dataset_and_version(time_ymdh):
                 time_s = time_s + '00'
             if len(time_e) == 8:
                 time_e = time_e + '21'
-            if time_ymdh >= int(time_s) and time_ymdh <= int(time_e):
-                d_list.append(dataset_name)
-                v_list.append(version_name)
-                trange_list.append(f'{time_s}-{time_e}')
-                have_data = True
-    print(f'[bold red]{time_ymdh} is in the following dataset and version:')
+            # 检查时间是否在数据集的时间范围内
+            if is_single_time:
+                if time_start >= int(time_s) and time_start <= int(time_e):
+                    d_list.append(dataset_name)
+                    v_list.append(version_name)
+                    trange_list.append(f'{time_s}-{time_e}')
+                    have_data = True
+            else:
+                if time_start >= int(time_s) and time_end <= int(time_e):
+                    d_list.append(dataset_name)
+                    v_list.append(version_name)
+                    trange_list.append(f'{time_s}-{time_e}')
+                    have_data = True
+
+    # 输出结果
+    print(f'[bold red]{time_input_str} is in the following dataset and version:')
     if have_data:
         for d, v, trange in zip(d_list, v_list, trange_list):
             print(f'[bold blue]{d} {v} {trange}')
         return True
     else:
-        # raise ValueError(f'{time_ymdh} is not in any dataset and version')
-        print(f'[bold red]{time_ymdh} is not in any dataset and version')
+        print(f'[bold red]{time_input_str} is not in any dataset and version')
         return False
 
 
-def ymd_in_which_dataset_and_version(time_ymd):
-    time_ymd = int(str(time_ymd)[:8])
-    d_list = []
-    v_list = []
-    trange_list = []
-    have_data = False
-    for dataset_name in data_info['hourly']['dataset'].keys():
-        for version_name in data_info['hourly']['dataset'][dataset_name]['version'].keys():
-            time_s, time_e = list(data_info['hourly']['dataset'][dataset_name]['version'][version_name]['time_range'].values())
-            time_s, time_e = str(time_s), str(time_e)
-            if len(time_s) == 8:
-                time_s = time_s + '00'
-            if len(time_e) == 8:
-                time_e = time_e + '21'
-            if time_ymd*100 >= int(time_s) and time_ymd*100+21 <= int(time_e):
-                d_list.append(dataset_name)
-                v_list.append(version_name)
-                trange_list.append(f'{time_s}-{time_e}')
-                have_data = True
-    print(f'[bold red]{time_ymd} is in the following dataset and version:')
-    if have_data:
-        for d, v, trange in zip(d_list, v_list, trange_list):
-            print(f'[bold blue]{d} {v} {trange}')
+def ensure_time_in_specific_dataset_and_version(dataset_name, version_name, time_input, time_end=None):
+    # 根据时间长度补全时间格式
+    if len(str(time_input)) == 8:
+        time_input = str(time_input) + '00'
+    time_start = int(time_input)
+    if time_end is not None:
+        if len(str(time_end)) == 8:
+            time_end = str(time_end) + '21'
+        time_end = int(time_end)
+    else:
+        time_end = time_start
+
+    # 检查指定的数据集和版本是否存在
+    if dataset_name not in data_info['hourly']['dataset']:
+        print(f'[bold red]Dataset {dataset_name} not found.')
+        return False
+    if version_name not in data_info['hourly']['dataset'][dataset_name]['version']:
+        print(f'[bold red]Version {version_name} not found in dataset {dataset_name}.')
+        return False
+
+    # 获取指定数据集和版本的时间范围
+    time_range = data_info['hourly']['dataset'][dataset_name]['version'][version_name]['time_range']
+    time_s, time_e = list(time_range.values())
+    time_s, time_e = str(time_s), str(time_e)
+    if len(time_s) == 8:
+        time_s = time_s + '00'
+    if len(time_e) == 8:
+        time_e = time_e + '21'
+    time_s, time_e = int(time_s), int(time_e)
+
+    # 检查时间是否在指定数据集和版本的时间范围内
+    if time_start >= time_s and time_end <= time_e:
+        print(f'[bold blue]Time {time_input} to {time_end} is within dataset {dataset_name} and version {version_name}.')
         return True
     else:
-        # raise ValueError(f'[bold red]{time_ymd} is not in any dataset and version')
-        print(f'[bold red]{time_ymd} is not in any dataset and version')
+        print(f'[bold red]Time {time_input} to {time_end} is not within dataset {dataset_name} and version {version_name}.')
         return False
 
 
-def direct_choose_dataset_and_version(time_ymdh):
-    time_ymdh = int(time_ymdh)
-    for dataset_name in data_info['hourly']['dataset'].keys():
-        for version_name in data_info['hourly']['dataset'][dataset_name]['version'].keys():
-            [time_s, time_e] = list(data_info['hourly']['dataset'][dataset_name]['version'][version_name]['time_range'].values())
-            time_s, time_e = str(time_s), str(time_e)
-            if len(time_s) == 8:
-                time_s = time_s + '00'
-            if len(time_e) == 8:
-                time_e = time_e + '21'
-            if time_ymdh >= int(time_s) and time_ymdh <= int(time_e):
-                print(f'[bold purple]dataset: {dataset_name}, version: {version_name} is chosen')
-                return dataset_name, version_name
-    return None, None
+def direct_choose_dataset_and_version(time_input, time_end=None):
+    # 假设 data_info 是一个字典，包含了数据集和版本的信息
+    # 示例结构：data_info['hourly']['dataset'][dataset_name]['version'][version_name]['time_range']
+
+    if len(str(time_input)) == 8:
+        time_input = str(time_input) + '00'
 
+    # 如果 time_end 是 None，则将 time_input 的值赋给它
+    if time_end is None:
+        time_end = time_input
+
+    # 处理开始和结束时间，确保它们是完整的 ymdh 格式
+    time_start, time_end = int(str(time_input)[:10]), int(str(time_end)[:10])
 
-def direct_choose_dataset_and_version_whole_day(time_ymd):
-    time_ymd = int(str(time_ymd)[:8])
     for dataset_name in data_info['hourly']['dataset'].keys():
         for version_name in data_info['hourly']['dataset'][dataset_name]['version'].keys():
             [time_s, time_e] = list(data_info['hourly']['dataset'][dataset_name]['version'][version_name]['time_range'].values())
@@ -475,10 +427,16 @@ def direct_choose_dataset_and_version_whole_day(time_ymd):
                 time_s = time_s + '00'
             if len(time_e) == 8:
                 time_e = time_e + '21'
-            if time_ymd*100 >= int(time_s) and time_ymd*100+21 <= int(time_e):
+            time_s, time_e = int(time_s), int(time_e)
+
+            # 检查时间是否在数据集版本的时间范围内
+            if time_start >= time_s and time_end <= time_e:
                 print(f'[bold purple]dataset: {dataset_name}, version: {version_name} is chosen')
                 return dataset_name, version_name
 
+    # 如果没有找到匹配的数据集和版本，返回 None
+    return None, None
+
 
 def get_base_url(dataset_name, version_name, var, year_str):
     url_dict = data_info['hourly']['dataset'][dataset_name]['version'][version_name]['url']
@@ -525,7 +483,7 @@ def check_existing_file(file_full_path):
         print(f'[bold #FFA54F]{file_full_path} exists')
         return True
     else:
-        print(f'{file_full_path} does not exist')
+        # print(f'{file_full_path} does not exist')
         return False
 
 
@@ -543,8 +501,8 @@ def get_ua():
         "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv,2.0.1) Gecko/20100101 Firefox/4.0.1",
         "Mozilla/5.0 (Windows NT 6.1; rv,2.0.1) Gecko/20100101 Firefox/4.0.1",
         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2",
-        "MAC：Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36",
-        "Windows：Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36",
+        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
         "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
         "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
         "Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
@@ -594,10 +552,10 @@ def get_ua():
         "NOKIA5700/UCWEB7.0.2.37/28/999",
         "Openwave/UCWEB7.0.2.37/28/999",
         "Openwave/UCWEB7.0.2.37/28/999",
+
     ]
-    ua_index = random.randint(0, len(ua_list)-1)
-    ua = ua_list[ua_index]
     # print(f'Using User-Agent: {ua}')
+    ua = random.choice(ua_list)
     return ua
 
 
@@ -621,7 +579,7 @@ def get_proxy():
 
 
 def dlownload_file(target_url, store_path, file_name, check=False):
-    print(f'[bold red]Downloading {file_name}...')
+    print(f'[bold #96cbd7]Downloading {file_name}...')
     # 创建会话
     s = requests.Session()
     download_success = False
@@ -632,14 +590,19 @@ def dlownload_file(target_url, store_path, file_name, check=False):
         if check_existing_file(filename):
             return
     clear_existing_file(filename)
-    print(f'Download_start_time: {datetime.datetime.now()}')
+    # print(f'Download_start_time: {datetime.datetime.now()}')
+    download_time_s = datetime.datetime.now()
     while not download_success:
+        if request_times >= 10:
+            # print(f'下载失败，已重试 {request_times} 次\n可先跳过，后续再试')
+            print(f'[bold #ffe5c0]Download failed after {request_times} times\nYou can skip it and try again later')
+            break
         if request_times > 0:
-            print(f'\r正在重试第 {request_times} 次', end="")
+            # print(f'\r正在重试第 {request_times} 次', end="")
+            print(f'[bold #ffe5c0]Retrying the {request_times} time...')
         # 尝试下载文件
         try:
-            headers = {
-                'User-Agent': get_ua()}
+            headers = {'User-Agent': get_ua()}
             response = s.get(target_url, headers=headers, timeout=5)
             response.raise_for_status()  # 如果请求返回的不是200，将抛出HTTPError异常
 
@@ -647,10 +610,12 @@ def dlownload_file(target_url, store_path, file_name, check=False):
             with open(filename, 'wb') as f:
                 f.write(response.content)
             # print(f'\r文件 {filename} 下载成功', end="")
-            # query_ncfile_time(filename) # 这个函数在linux上目前会出问题
             if os.path.exists(filename):
                 download_success = True
-                print(f'[bold green]文件 {filename} 下载成功')
+                download_time_e = datetime.datetime.now()
+                download_delta = download_time_e - download_time_s
+                print(f'[#65b168]File [bold #dfff73]{filename} [#65b168]has been downloaded successfully, Time: [#39cbdd]{download_delta}')
+                # print(f'Download_end_time: {datetime.datetime.now()}')
 
         except requests.exceptions.HTTPError as errh:
             print(f"Http Error: {errh}")
@@ -663,7 +628,6 @@ def dlownload_file(target_url, store_path, file_name, check=False):
 
         time.sleep(3)
         request_times += 1
-    print(f'Download_end_time: {datetime.datetime.now()}')
 
 
 def check_hour_is_valid(ymdh_str):
@@ -675,53 +639,65 @@ def check_hour_is_valid(ymdh_str):
         return False
 
 
-def check_dataset_version_single_time(dataset_name, version_name, download_time):
-    download_time = str(download_time)
-    if not check_hour_is_valid(download_time):
+def check_dataset_version(dataset_name, version_name, download_time, download_time_end=None):
+    if dataset_name is not None and version_name is not None:
+        just_ensure = ensure_time_in_specific_dataset_and_version(dataset_name, version_name, download_time, download_time_end)
+        if just_ensure:
+            return dataset_name, version_name
+        else:
+            return None, None
+
+    # 确保下载时间是一个字符串
+    download_time_str = str(download_time)
+
+    if len(download_time_str) == 8:
+        download_time_str = download_time_str + '00'
+
+    # 检查小时是否有效（如果需要的话）
+    if download_time_end is None and not check_hour_is_valid(download_time_str):
         print('Please ensure the hour is 00, 03, 06, 09, 12, 15, 18, 21')
         raise ValueError('The hour is invalid')
-    have_data = ymdh_in_which_dataset_and_version(download_time)
-    if not have_data:
-        return None, None
-    if dataset_name is None and version_name is None:
-        print('The dataset_name and version_name are None, so the dataset and version will be chosen according to the download_time.\nIf there is more than one dataset and version in the time range, the first one will be chosen.')
-        print('If you wanna choose the dataset and version by yourself, please set the dataset_name and version_name together.')
-        dataset_name, version_name = direct_choose_dataset_and_version(download_time)
-    elif dataset_name is None and version_name is not None:
-        print('Please ensure the dataset_name is not None')
-        print('If you do not add the dataset_name, both the dataset and version will be chosen according to the download_time.')
-        dataset_name, version_name = direct_choose_dataset_and_version(download_time)
-    elif dataset_name is not None and version_name is None:
-        print('Please ensure the version_name is not None')
-        print('If you do not add the version_name, both the dataset and version will be chosen according to the download_time.')
-        dataset_name, version_name = direct_choose_dataset_and_version(download_time)
+
+    # 根据是否检查整个天来设置时间范围
+    if download_time_end is not None:
+        if len(str(download_time_end)) == 8:
+            download_time_end = str(download_time_end) + '21'
+        have_data = check_time_in_dataset_and_version(download_time_str, download_time_end)
+        if have_data:
+            return direct_choose_dataset_and_version(download_time_str, download_time_end)
     else:
-        print('The dataset_name and version_name are both set by yourself.')
+        have_data = check_time_in_dataset_and_version(download_time_str)
+        if have_data:
+            return direct_choose_dataset_and_version(download_time_str)
 
-    return dataset_name, version_name
+    return None, None
 
 
 def get_submit_url_var(var, depth, level_num, lon_min, lon_max, lat_min, lat_max, dataset_name, version_name, download_time):
     year_str = str(download_time)[:4]
     if depth is not None and level_num is not None:
         print('Please ensure the depth or level_num is None')
-    elif depth is not None:
-        print(f'Data of single depth ({depth}m) will be downloaded...')
-        query_dict = get_query_dict_single_depth(var, lon_min, lon_max, lat_min, lat_max, depth, download_time)
-    elif level_num is not None:
+        print('Progress will use the depth')
+        which_mode = 'depth'
+    elif depth is not None and level_num is None:
+        print(f'Data of single depth (~{depth} m) will be downloaded...')
+        which_mode = 'depth'
+    elif level_num is not None and depth is None:
         print(f'Data of single level ({level_num}) will be downloaded...')
-        query_dict = get_query_dict_single_level(var, lon_min, lon_max, lat_min, lat_max, level_num, download_time)
+        which_mode = 'level'
     else:
         print('Full depth or full level data will be downloaded...')
-        query_dict = get_query_dict_full_level(var, lon_min, lon_max, lat_min, lat_max, download_time)
+        which_mode = 'full'
+    query_dict = get_query_dict(var, lon_min, lon_max, lat_min, lat_max, download_time, which_mode, depth, level_num)
     submit_url = get_submit_url(
         dataset_name, version_name, var, year_str, query_dict)
     return submit_url
 
 
-def direct_download_single_time(var, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90, download_time='2024083100', depth=None, level_num=None, store_path=None, dataset_name=None, version_name=None, check=False):
+def direct_download_single_hour(var, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90, download_time='2024083100', depth=None, level_num=None, store_path=None, dataset_name=None, version_name=None, check=False):
+    print('[bold #ecdbfe]-'*150)
     download_time = str(download_time)
-    dataset_name, version_name = check_dataset_version_single_time(dataset_name, version_name, download_time)
+    dataset_name, version_name = check_dataset_version(dataset_name, version_name, download_time)
     if dataset_name is None and version_name is None:
         return
 
@@ -763,32 +739,10 @@ def direct_download_single_time(var, lon_min=0, lon_max=359.92, lat_min=-80, lat
                 dlownload_file(submit_url, store_path, file_name, check)
 
 
-def check_dataset_version_whold_day(dataset_name, version_name, download_time):
-    download_time = str(download_time)
-    have_data = ymd_in_which_dataset_and_version(download_time)
-    if not have_data:
-        return None, None
-    if dataset_name is None and version_name is None:
-        print('The dataset_name and version_name are None, so the dataset and version will be chosen according to the download_time.\nIf there is more than one dataset and version in the time range, the first one will be chosen.')
-        print('If you wanna choose the dataset and version by yourself, please set the dataset_name and version_name together.')
-        dataset_name, version_name = direct_choose_dataset_and_version_whole_day(download_time)
-    elif dataset_name is None and version_name is not None:
-        print('Please ensure the dataset_name is not None')
-        print('If you do not add the dataset_name, both the dataset and version will be chosen according to the download_time.')
-        dataset_name, version_name = direct_choose_dataset_and_version_whole_day(download_time)
-    elif dataset_name is not None and version_name is None:
-        print('Please ensure the version_name is not None')
-        print('If you do not add the version_name, both the dataset and version will be chosen according to the download_time.')
-        dataset_name, version_name = direct_choose_dataset_and_version_whole_day(download_time)
-    else:
-        print('The dataset_name and version_name are both set by yourself.')
-
-    return dataset_name, version_name
-
-
 def direct_download_whole_day(var, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90, download_time='20240831', depth=None, level_num=None, store_path=None, dataset_name=None, version_name=None, check=False):
+    print('[bold #ecdbfe]-'*150)
     download_time = str(download_time)[:8]+'00'
-    dataset_name, version_name = check_dataset_version_whold_day(dataset_name, version_name, download_time[:8])
+    dataset_name, version_name = check_dataset_version(dataset_name, version_name, download_time, str(download_time)[:8]+'21')
     if dataset_name is None and version_name is None:
         return
 
@@ -867,10 +821,10 @@ def download_task(var, time_str, lon_min, lon_max, lat_min, lat_max, depth, leve
     if len(time_str) == 8:
         direct_download_whole_day(var, lon_min, lon_max, lat_min, lat_max, time_str, depth, level, store_path, dataset_name, version_name, check)
     else:
-        direct_download_single_time(var, lon_min, lon_max, lat_min, lat_max, time_str, depth, level, store_path, dataset_name, version_name, check)
+        direct_download_single_hour(var, lon_min, lon_max, lat_min, lat_max, time_str, depth, level, store_path, dataset_name, version_name, check)
 
 
-def download_single_hour(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90,  depth=None, level=None, store_path=None, dataset_name=None, version_name=None, num_workers=None, check=False):
+def download_single_hour(var, time_s, time_e=None, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90,  depth=None, level=None, store_path=None, dataset_name=None, version_name=None, num_workers=None, check=False):
     '''
     Description:
     Download the data of single time or a series of time
@@ -912,21 +866,24 @@ def download_single_hour(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_min
     ymdh_time_s = str(time_s)
     if len(ymdh_time_s) == 8:
         ymdh_time_s += '00'
-    ymdh_time_e = str(time_e)
-    if len(ymdh_time_e) == 8:
-        ymdh_time_e += '21'
+    if time_e is None:
+        ymdh_time_e = ymdh_time_s[:]
+    else:
+        ymdh_time_e = str(time_e)
+        if len(ymdh_time_e) == 8:
+            ymdh_time_e += '21'
     if ymdh_time_s == ymdh_time_e:
-        direct_download_single_time(var, lon_min, lon_max, lat_min, lat_max, ymdh_time_s, depth, level, store_path, dataset_name, version_name)
+        direct_download_single_hour(var, lon_min, lon_max, lat_min, lat_max, ymdh_time_s, depth, level, store_path, dataset_name, version_name)
     elif int(ymdh_time_s) < int(ymdh_time_e):
         print('Downloading a series of files...')
-        time_list = get_hour_list(ymdh_time_s, ymdh_time_e, 3)
+        time_list = get_time_list(ymdh_time_s, ymdh_time_e, 3, 'hour')
         with Progress() as progress:
             task = progress.add_task("[cyan]Downloading...", total=len(time_list))
             if num_workers is None or num_workers <= 1:
                 # 串行方式
-                for time_str in time_list:
-                    direct_download_single_time(var, lon_min, lon_max, lat_min, lat_max, time_str, depth, level, store_path, dataset_name, version_name, check)
-                    progress.update(task, advance=1)
+                for i, time_str in enumerate(time_list):
+                    direct_download_single_hour(var, lon_min, lon_max, lat_min, lat_max, time_str, depth, level, store_path, dataset_name, version_name, check)
+                    progress.update(task, advance=1, description=f'[cyan]Downloading... {i+1}/{len(time_list)}')
             else:
                 # 并行方式
                 if num_workers > 10:
@@ -935,13 +892,13 @@ def download_single_hour(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_min
                     num_workers = 10
                 with ThreadPoolExecutor(max_workers=num_workers) as executor:
                     futures = [executor.submit(download_task, var, time_str, lon_min, lon_max, lat_min, lat_max, depth, level, store_path, dataset_name, version_name, check) for time_str in time_list]
-                    for future in futures:
-                        future.add_done_callback(lambda _: progress.update(task, advance=1))
+                    for i, future in enumerate(futures):
+                        future.add_done_callback(lambda _: progress.update(task, advance=1, description=f'[cyan]Downloading... {i+1}/{len(time_list)}'))
     else:
         print('Please ensure the time_s is less than the time_e')
 
 
-def download_whole_day(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90,  depth=None, level=None, store_path=None, dataset_name=None, version_name=None, num_workers=None, check=False):
+def download_whole_day(var, time_s, time_e=None, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90,  depth=None, level=None, store_path=None, dataset_name=None, version_name=None, num_workers=None, check=False):
     '''
     Description:
     Download the data of single time or a series of time
@@ -980,20 +937,24 @@ def download_whole_day(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_min=-
         print('The range of lon_min, lon_max is 0~359.92')
         print('The range of lat_min, lat_max is -80~90')
         raise ValueError('The lon or lat is invalid')
-    time_s, time_e = str(time_s)[:8], str(time_e)[:8]
+    time_s = str(time_s)[:8]
+    if time_e is None:
+        time_e = time_s[:]
+    else:
+        time_e = str(time_e)[:8]
 
     if time_s == time_e:
         direct_download_whole_day(var, lon_min, lon_max, lat_min, lat_max, time_s, depth, level, store_path, dataset_name, version_name)
     elif int(time_s) < int(time_e):
         print('Downloading a series of files...')
-        time_list = get_day_list(time_s, time_e, 1)
+        time_list = get_time_list(time_s, time_e, 1, 'day')
         with Progress() as progress:
             task = progress.add_task("[cyan]Downloading...", total=len(time_list))
             if num_workers is None or num_workers <= 1:
                 # 串行方式
-                for time_str in time_list:
+                for i, time_str in enumerate(time_list):
                     direct_download_whole_day(var, lon_min, lon_max, lat_min, lat_max, time_str, depth, level, store_path, dataset_name, version_name, check)
-                    progress.update(task, advance=1)
+                    progress.update(task, advance=1, description=f'[cyan]Downloading... {i+1}/{len(time_list)}')
             else:
                 # 并行方式
                 if num_workers > 10:
@@ -1002,13 +963,13 @@ def download_whole_day(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_min=-
                     num_workers = 10
                 with ThreadPoolExecutor(max_workers=num_workers) as executor:
                     futures = [executor.submit(download_task, var, time_str, lon_min, lon_max, lat_min, lat_max, depth, level, store_path, dataset_name, version_name, check) for time_str in time_list]
-                    for future in futures:
-                        future.add_done_callback(lambda _: progress.update(task, advance=1))
+                    for i, future in enumerate(futures):
+                        future.add_done_callback(lambda _: progress.update(task, advance=1, description=f'[cyan]Downloading... {i+1}/{len(time_list)}'))
     else:
         print('Please ensure the time_s is less than the time_e')
 
 
-def download_his1(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90,  depth=None, level=None, store_path=None, dataset_name=None, version_name=None, num_workers=None, check=False):
+def download(var, time_s, time_e=None, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90,  depth=None, level=None, store_path=None, dataset_name=None, version_name=None, num_workers=None, check=False, resolution='hour'):
     '''
     Description:
     Download the data of single time or a series of time
@@ -1031,72 +992,20 @@ def download_his1(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_min=-80, l
     Returns:
     None
     '''
-    if isinstance(var, list):
-        var = var[0]
-    var = convert_full_name_to_short_name(var)
-    if var is False:
-        raise ValueError('The var is invalid')
-    if lon_min < 0 or lon_min > 359.92 or lon_max < 0 or lon_max > 359.92 or lat_min < -80 or lat_min > 90 or lat_max < -80 or lat_max > 90:
-        print('Please ensure the lon_min, lon_max, lat_min, lat_max are in the range')
-        print('The range of lon_min, lon_max is 0~359.92')
-        print('The range of lat_min, lat_max is -80~90')
-        raise ValueError('The lon or lat is invalid')
-    ymdh_time_s = str(time_s)
-    if len(ymdh_time_s) == 8:
-        ymdh_time_s += '00'
-    ymdh_time_e = str(time_e)
-    if len(ymdh_time_e) == 8:
-        ymdh_time_e += '21'
-    if ymdh_time_s == ymdh_time_e:
-        direct_download_single_time(var, lon_min, lon_max, lat_min, lat_max, ymdh_time_s, depth, level, store_path, dataset_name, version_name)
-    elif int(ymdh_time_s) < int(ymdh_time_e):
-        print('Downloading a series of files...')
-        time_list = get_hour_list(ymdh_time_s, ymdh_time_e, 3)
-        with Progress() as progress:
-            task = progress.add_task("[cyan]Downloading...", total=len(time_list))
-            if num_workers is None or num_workers <= 1:
-                # 串行方式
-                for time_str in time_list:
-                    direct_download_single_time(var, lon_min, lon_max, lat_min, lat_max, time_str, depth, level, store_path, dataset_name, version_name, check)
-                    progress.update(task, advance=1)
-            else:
-                # 并行方式
-                if num_workers > 10:
-                    print('The number of workers is too large!')
-                    print('In order to avoid the server being blocked, the number of workers is set to 10')
-                    num_workers = 10
-                with ThreadPoolExecutor(max_workers=num_workers) as executor:
-                    futures = [executor.submit(download_task, var, time_str, lon_min, lon_max, lat_min, lat_max, depth, level, store_path, dataset_name, version_name, check) for time_str in time_list]
-                    for future in futures:
-                        future.add_done_callback(
-                            lambda _: progress.update(task, advance=1))
+    # 打印信息并处理数据集和版本名称
+    if dataset_name is None and version_name is None:
+        print('The dataset_name and version_name are None, so the dataset and version will be chosen according to the download_time.\nIf there is more than one dataset and version in the time range, the first one will be chosen.')
+        print('If you wanna choose the dataset and version by yourself, please set the dataset_name and version_name together.')
+    elif dataset_name is None and version_name is not None:
+        print('Please ensure the dataset_name is not None')
+        print('If you do not add the dataset_name, both the dataset and version will be chosen according to the download_time.')
+    elif dataset_name is not None and version_name is None:
+        print('Please ensure the version_name is not None')
+        print('If you do not add the version_name, both the dataset and version will be chosen according to the download_time.')
     else:
-        print('Please ensure the ymdh_time_s is less than the ymdh_time_e')
-
-
-def download(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90,  depth=None, level=None, store_path=None, dataset_name=None, version_name=None, num_workers=None, check=False, resolution='hour'):
-    '''
-    Description:
-    Download the data of single time or a series of time
-
-    Parameters:
-    var: str, the variable name, such as 'u', 'v', 'temp', 'salt', 'ssh', 'u_b', 'v_b', 'temp_b', 'salt_b' or 'water_u', 'water_v', 'water_temp', 'salinity', 'surf_el', 'water_u_bottom', 'water_v_bottom', 'water_temp_bottom', 'salinity_bottom'
-    time_s: str, the start time, such as '2024110100' or '20241101', if add hour, the hour should be 00, 03, 06, 09, 12, 15, 18, 21
-    time_e: str, the end time, such as '2024110221' or '20241102', if add hour, the hour should be 00, 03, 06, 09, 12, 15, 18, 21
-    lon_min: float, the minimum longitude, default is 0
-    lon_max: float, the maximum longitude, default is 359.92
-    lat_min: float, the minimum latitude, default is -80
-    lat_max: float, the maximum latitude, default is 90
-    depth: float, the depth, default is None
-    level: int, the level number, default is None
-    store_path: str, the path to store the data, default is None
-    dataset_name: str, the dataset name, default is None, example: 'GLBv0.08', 'GLBu0.08', 'GLBy0.08'
-    version_name: str, the version name, default is None, example: '53.X', '56.3'
-    num_workers: int, the number of workers, default is None
+        print('The dataset_name and version_name are both set by yourself.')
+        print('Please ensure the dataset_name and version_name are correct.')
 
-    Returns:
-    None
-    '''
     if resolution == 'hour':
         download_single_hour(var, time_s, time_e, lon_min, lon_max, lat_min, lat_max, depth, level, store_path, dataset_name, version_name, num_workers, check)
     elif resolution == 'day':
@@ -1112,7 +1021,7 @@ def how_to_use():
     print('''
     # 1. Choose the dataset and version according to the time:
     # 1.1 Use function to query
-    You can use the function ymd_in_which_dataset_and_version(time_ymd=20241101) to find the dataset and version  according to the time.
+    You can use the function check_time_in_dataset_and_version(time_input=20241101) to find the dataset and version  according to the time.
     Then, you can see the dataset and version in the output.
     # 1.2 Draw a picture to see
     You can draw a picture to see the time range of each dataset and version.
@@ -1159,8 +1068,8 @@ def how_to_use():
 
 if __name__ == '__main__':
     # help(hycom3h.download)
-    time_s, time_e = '2018010100', '2024103121'
-    merge_name = '2018_010300-020100'
+    time_s, time_e = '2018070100', '2019123121'
+    merge_name = '2018_2024'
     root_path = r'G:\Data\HYCOM\3hourly'
     location_dict = {'west': 105, 'east': 130, 'south': 15, 'north': 45}
     download_dict = {
@@ -1184,7 +1093,7 @@ if __name__ == '__main__':
     # if you wanna download all depth or level, set both False
     depth = None  # or 0-4000 meters
     level = None  # or 1-40 levels
-    num_workers = 2
+    num_workers = 1
 
     check = True
 
@@ -1200,7 +1109,7 @@ if __name__ == '__main__':
             download(var=var_list, time_s=time_s, time_e=time_e, store_path=Path(root_path), lon_min=location_dict['west'], lon_max=location_dict['east'], lat_min=location_dict['south'], lat_max=location_dict['north'], num_workers=num_workers, check=check, depth=depth, level=level)
 
     """ if combine_switch or copy_switch:
-        time_list = get_hour_list(time_s, time_e, 3)
+        time_list = get_time_list(time_s, time_e, 3, 'hour')
         for var_name in var_list:
             file_list = []
             if single_var:
@@ -1218,6 +1127,7 @@ if __name__ == '__main__':
                     fname = 'surf_el'
                 for time_str in time_list:
                     file_list.append(Path(root_path)/f'HYCOM_{fname}_{time_str}.nc')
+                merge_path_name = Path(root_path)/f'HYCOM_{fname}_{merge_name}.nc'
             if combine_switch:
                 merge5nc(file_list, var_name, 'time', merge_path_name)
             if copy_switch: