oafuncs 0.0.60__py2.py3-none-any.whl → 0.0.61__py2.py3-none-any.whl

oafuncs/oa_cmap.py

@@ -4,8 +4,8 @@
 Author: Liu Kun && 16031215@qq.com
 Date: 2024-09-17 16:55:11
 LastEditors: Liu Kun && 16031215@qq.com
-LastEditTime: 2024-10-06 19:34:57
-FilePath: \\Python\\My_Funcs\\OAFuncs\\OAFuncs\\oa_cmap.py
+LastEditTime: 2024-11-21 13:14:24
+FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\oa_cmap.py
 Description:  
 EditPlatform: vscode
 ComputerInfo: XPS 15 9510
@@ -18,8 +18,7 @@ import matplotlib as mpl
 import matplotlib.pyplot as plt
 import numpy as np
 
-__all__ = ['show', 'extract_colors', 'create_custom',
-           'create_diverging', 'create_5rgb_txt']
+__all__ = ['show', 'extract_colors', 'create_custom', 'create_diverging', 'create_5rgb_txt']
 
 # ** 将cmap用填色图可视化（官网摘抄函数）
 
@@ -34,8 +33,7 @@ def show(colormaps: list):
     np.random.seed(19680801)
     data = np.random.randn(30, 30)
     n = len(colormaps)
-    fig, axs = plt.subplots(1, n, figsize=(n * 2 + 2, 3),
-                            constrained_layout=True, squeeze=False)
+    fig, axs = plt.subplots(1, n, figsize=(n * 2 + 2, 3), constrained_layout=True, squeeze=False)
     for [ax, cmap] in zip(axs.flat, colormaps):
         psm = ax.pcolormesh(data, cmap=cmap, rasterized=True, vmin=-4, vmax=4)
         fig.colorbar(psm, ax=ax)
@@ -67,11 +65,9 @@ def create_custom(colors: list, nodes=None):  # 利用颜色快速配色
                 c_map = mk_cmap(['aliceblue','skyblue','deepskyblue'],[0.0,0.5,1.0])
     '''
     if nodes is None:  # 采取自动分配比例
-        cmap_color = mpl.colors.LinearSegmentedColormap.from_list(
-            'mycmap', colors)
+        cmap_color = mpl.colors.LinearSegmentedColormap.from_list('mycmap', colors)
     else:  # 按照提供比例分配
-        cmap_color = mpl.colors.LinearSegmentedColormap.from_list(
-            "mycmap", list(zip(nodes, colors)))
+        cmap_color = mpl.colors.LinearSegmentedColormap.from_list("mycmap", list(zip(nodes, colors)))
     return cmap_color
 
 # ** 自制diverging型cmap，默认中间为白色
@@ -91,8 +87,7 @@ def create_diverging(colors: list):
     newcolors = colors
     if n % 2 == 0:
         newcolors.insert(int(n / 2), '#ffffff')  # 偶数个颜色，中间为白色
-    cmap_color = mpl.colors.LinearSegmentedColormap.from_list(
-        "mycmap", list(zip(nodes, newcolors)))
+    cmap_color = mpl.colors.LinearSegmentedColormap.from_list("mycmap", list(zip(nodes, newcolors)))
     return cmap_color
 
 # ** 根据RGB的txt文档制作色卡（利用Grads调色盘）
@@ -129,8 +124,7 @@ if __name__ == '__main__':
     show([c_map])
 
     # ** 测试自制diverging型cmap
-    diverging_cmap = create_diverging(["#4e00b3", "#0000FF", "#00c0ff",
-                                       "#a1d3ff", "#DCDCDC", "#FFD39B", "#FF8247", "#FF0000", "#FF5F9E"])
+    diverging_cmap = create_diverging(["#4e00b3", "#0000FF", "#00c0ff", "#a1d3ff", "#DCDCDC", "#FFD39B", "#FF8247", "#FF0000", "#FF5F9E"])
     show([diverging_cmap])
 
     # ** 测试根据RGB的txt文档制作色卡

oafuncs/oa_data.py

@@ -4,8 +4,8 @@
 Author: Liu Kun && 16031215@qq.com
 Date: 2024-09-17 17:12:47
 LastEditors: Liu Kun && 16031215@qq.com
-LastEditTime: 2024-10-06 19:05:38
-FilePath: \\Python\\My_Funcs\\OAFuncs\\OAFuncs\\oa_data.py
+LastEditTime: 2024-11-21 13:13:20
+FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\oa_data.py
 Description:  
 EditPlatform: vscode
 ComputerInfo: XPS 15 9510
@@ -14,7 +14,6 @@ Python Version: 3.11
 '''
 
 
-
 import multiprocessing as mp
 from concurrent.futures import ThreadPoolExecutor
 
@@ -24,6 +23,8 @@ from scipy.interpolate import griddata
 __all__ = ['interp_2d', 'interp_2d_parallel']
 
 # ** 高维插值函数，插值最后两个维度
+
+
 def interp_2d(target_x, target_y, origin_x, origin_y, data, method='linear'):
     """
     高维插值函数，默认插值最后两个维度，传输数据前请确保数据的维度正确
@@ -51,8 +52,7 @@ def interp_2d(target_x, target_y, origin_x, origin_y, data, method='linear'):
 
     if origin_x.shape != dims[-2:] or origin_y.shape != dims[-2:]:
         print(origin_x.shape, dims[-2:])
-        raise ValueError(
-            'Shape of data does not match shape of origin_x or origin_y.')
+        raise ValueError('Shape of data does not match shape of origin_x or origin_y.')
 
     # 将目标网格展平成一维数组
     target_points = np.column_stack((np.ravel(target_y), np.ravel(target_x)))
@@ -62,14 +62,12 @@ def interp_2d(target_x, target_y, origin_x, origin_y, data, method='linear'):
 
     # 进行插值
     if len_dims == 2:
-        interpolated_data = griddata(origin_points, np.ravel(
-            data), target_points, method=method)
+        interpolated_data = griddata(origin_points, np.ravel(data), target_points, method=method)
         interpolated_data = np.reshape(interpolated_data, target_y.shape)
     elif len_dims == 3:
         interpolated_data = []
         for i in range(dims[0]):
-            dt = griddata(origin_points, np.ravel(
-                data[i, :, :]), target_points, method=method)
+            dt = griddata(origin_points, np.ravel(data[i, :, :]), target_points, method=method)
             interpolated_data.append(np.reshape(dt, target_y.shape))
             print(f'Interpolating {i+1}/{dims[0]}...')
         interpolated_data = np.array(interpolated_data)
@@ -78,11 +76,9 @@ def interp_2d(target_x, target_y, origin_x, origin_y, data, method='linear'):
         for i in range(dims[0]):
             interpolated_data.append([])
             for j in range(dims[1]):
-                dt = griddata(origin_points, np.ravel(
-                    data[i, j, :, :]), target_points, method=method)
+                dt = griddata(origin_points, np.ravel(data[i, j, :, :]), target_points, method=method)
                 interpolated_data[i].append(np.reshape(dt, target_y.shape))
-                print(
-                    f'\rInterpolating {i*dims[1]+j+1}/{dims[0]*dims[1]}...', end='')
+                print(f'\rInterpolating {i*dims[1]+j+1}/{dims[0]*dims[1]}...', end='')
         print('\n')
         interpolated_data = np.array(interpolated_data)
 
@@ -104,33 +100,24 @@ def interp_2d_parallel(target_x, target_y, origin_x, origin_y, data, method='lin
     example     : interpolated_data = interp_2d_parallel(target_x, target_y, origin_x, origin_y, data, method='linear')
     '''
     def interp_single2d(target_y, target_x, origin_y, origin_x, data, method='linear'):
-        target_points = np.column_stack(
-            (np.ravel(target_y), np.ravel(target_x)))
-        origin_points = np.column_stack(
-            (np.ravel(origin_y), np.ravel(origin_x)))
+        target_points = np.column_stack((np.ravel(target_y), np.ravel(target_x)))
+        origin_points = np.column_stack((np.ravel(origin_y), np.ravel(origin_x)))
 
-        dt = griddata(origin_points, np.ravel(
-            data[:, :]), target_points, method=method)
+        dt = griddata(origin_points, np.ravel(data[:, :]), target_points, method=method)
         return np.reshape(dt, target_y.shape)
 
     def interp_single3d(i, target_y, target_x, origin_y, origin_x, data, method='linear'):
-        target_points = np.column_stack(
-            (np.ravel(target_y), np.ravel(target_x)))
-        origin_points = np.column_stack(
-            (np.ravel(origin_y), np.ravel(origin_x)))
+        target_points = np.column_stack((np.ravel(target_y), np.ravel(target_x)))
+        origin_points = np.column_stack((np.ravel(origin_y), np.ravel(origin_x)))
 
-        dt = griddata(origin_points, np.ravel(
-            data[i, :, :]), target_points, method=method)
+        dt = griddata(origin_points, np.ravel(data[i, :, :]), target_points, method=method)
         return np.reshape(dt, target_y.shape)
 
     def interp_single4d(i, j, target_y, target_x, origin_y, origin_x, data, method='linear'):
-        target_points = np.column_stack(
-            (np.ravel(target_y), np.ravel(target_x)))
-        origin_points = np.column_stack(
-            (np.ravel(origin_y), np.ravel(origin_x)))
+        target_points = np.column_stack((np.ravel(target_y), np.ravel(target_x)))
+        origin_points = np.column_stack((np.ravel(origin_y), np.ravel(origin_x)))
 
-        dt = griddata(origin_points, np.ravel(
-            data[i, j, :, :]), target_points, method=method)
+        dt = griddata(origin_points, np.ravel(data[i, j, :, :]), target_points, method=method)
         return np.reshape(dt, target_y.shape)
 
     if len(target_y.shape) == 1:
@@ -150,16 +137,12 @@ def interp_2d_parallel(target_x, target_y, origin_x, origin_y, data, method='lin
     with ThreadPoolExecutor(max_workers=mp.cpu_count()-2) as executor:
         print(f'Using {mp.cpu_count()-2} threads...')
         if len_dims == 2:
-            interpolated_data = list(executor.map(interp_single2d, [target_y], [
-                                     target_x], [origin_y], [origin_x], [data], [method]))
+            interpolated_data = list(executor.map(interp_single2d, [target_y], [target_x], [origin_y], [origin_x], [data], [method]))
         elif len_dims == 3:
-            interpolated_data = list(executor.map(interp_single3d, [i for i in range(dims[0])], [
-                                     target_y]*dims[0], [target_x]*dims[0], [origin_y]*dims[0], [origin_x]*dims[0], [data]*dims[0], [method]*dims[0]))
+            interpolated_data = list(executor.map(interp_single3d, [i for i in range(dims[0])], [target_y]*dims[0], [target_x]*dims[0], [origin_y]*dims[0], [origin_x]*dims[0], [data]*dims[0], [method]*dims[0]))
         elif len_dims == 4:
-            interpolated_data = list(executor.map(interp_single4d, [i for i in range(dims[0]) for j in range(dims[1])], [j for i in range(dims[0]) for j in range(dims[1])], [
-                                     target_y]*dims[0]*dims[1], [target_x]*dims[0]*dims[1], [origin_y]*dims[0]*dims[1], [origin_x]*dims[0]*dims[1], [data]*dims[0]*dims[1], [method]*dims[0]*dims[1]))
-            interpolated_data = np.array(interpolated_data).reshape(
-                dims[0], dims[1], target_y.shape[0], target_x.shape[1])
+            interpolated_data = list(executor.map(interp_single4d, [i for i in range(dims[0]) for j in range(dims[1])], [j for i in range(dims[0]) for j in range(dims[1])], [target_y]*dims[0]*dims[1], [target_x]*dims[0]*dims[1], [origin_y]*dims[0]*dims[1], [origin_x]*dims[0]*dims[1], [data]*dims[0]*dims[1], [method]*dims[0]*dims[1]))
+            interpolated_data = np.array(interpolated_data).reshape(dims[0], dims[1], target_y.shape[0], target_x.shape[1])
 
     interpolated_data = np.array(interpolated_data)
 
@@ -193,8 +176,7 @@ if __name__ == '__main__':
 
     # 高维插值多线程
     start = time.time()
-    interpolated_data = interp_2d_parallel(
-        target_x, target_y, origin_x, origin_y, data)
+    interpolated_data = interp_2d_parallel(target_x, target_y, origin_x, origin_y, data)
     print(f'Interpolation time: {time.time()-start:.2f}s')
 
     print(interpolated_data.shape)

oafuncs/oa_down/hycom_3hourly.py

@@ -4,7 +4,7 @@
 Author: Liu Kun && 16031215@qq.com
 Date: 2024-11-01 10:31:09
 LastEditors: Liu Kun && 16031215@qq.com
-LastEditTime: 2024-11-21 12:55:56
+LastEditTime: 2024-11-21 13:24:49
 FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\oa_down\\hycom_3hourly.py
 Description:
 EditPlatform: vscode
@@ -27,8 +27,7 @@ import requests
 from rich import print
 from rich.progress import Progress
 
-warnings.filterwarnings("ignore", category=RuntimeWarning,
-                        message="Engine '.*' loading failed:.*")
+warnings.filterwarnings("ignore", category=RuntimeWarning, message="Engine '.*' loading failed:.*")
 
 __all__ = ['draw_time_range', 'download', 'how_to_use', 'get_time_list']
 
@@ -37,13 +36,11 @@ data_info = {'yearly': {}, 'monthly': {}, 'daily': {}, 'hourly': {}}
 
 # hourly data
 # dataset: GLBv0.08, GLBu0.08, GLBy0.08
-data_info['hourly']['dataset'] = {
-    'GLBv0.08': {}, 'GLBu0.08': {}, 'GLBy0.08': {}}
+data_info['hourly']['dataset'] = {'GLBv0.08': {}, 'GLBu0.08': {}, 'GLBy0.08': {}}
 
 # version
 # version of GLBv0.08: 53.X, 56.3, 57.2, 92.8, 57.7, 92.9, 93.0
-data_info['hourly']['dataset']['GLBv0.08']['version'] = {
-    '53.X': {}, '56.3': {}, '57.2': {}, '92.8': {}, '57.7': {}, '92.9': {}, '93.0': {}}
+data_info['hourly']['dataset']['GLBv0.08']['version'] = {'53.X': {}, '56.3': {}, '57.2': {}, '92.8': {}, '57.7': {}, '92.9': {}, '93.0': {}}
 # version of GLBu0.08: 93.0
 data_info['hourly']['dataset']['GLBu0.08']['version'] = {'93.0': {}}
 # version of GLBy0.08: 93.0
@@ -55,26 +52,17 @@ data_info['hourly']['dataset']['GLBy0.08']['version'] = {'93.0': {}}
 # 在网页上提交超过范围的时间，会返回该数据集实际时间范围，从而纠正下面的时间范围
 # 目前只纠正了GLBv0.08 93.0的时间范围，具体到小时了
 # 其他数据集的时刻暂时默认为00起，21止
-data_info['hourly']['dataset']['GLBv0.08']['version']['53.X']['time_range'] = {
-    'time_start': '19940101', 'time_end': '20151230'}
-data_info['hourly']['dataset']['GLBv0.08']['version']['56.3']['time_range'] = {
-    'time_start': '20140701', 'time_end': '20160430'}
-data_info['hourly']['dataset']['GLBv0.08']['version']['57.2']['time_range'] = {
-    'time_start': '20160501', 'time_end': '20170131'}
-data_info['hourly']['dataset']['GLBv0.08']['version']['92.8']['time_range'] = {
-    'time_start': '20170201', 'time_end': '20170531'}
-data_info['hourly']['dataset']['GLBv0.08']['version']['57.7']['time_range'] = {
-    'time_start': '20170601', 'time_end': '20170930'}
-data_info['hourly']['dataset']['GLBv0.08']['version']['92.9']['time_range'] = {
-    'time_start': '20171001', 'time_end': '20171231'}
-data_info['hourly']['dataset']['GLBv0.08']['version']['93.0']['time_range'] = {
-    'time_start': '2018010112', 'time_end': '2020021909'}
+data_info['hourly']['dataset']['GLBv0.08']['version']['53.X']['time_range'] = {'time_start': '19940101', 'time_end': '20151230'}
+data_info['hourly']['dataset']['GLBv0.08']['version']['56.3']['time_range'] = {'time_start': '20140701', 'time_end': '20160430'}
+data_info['hourly']['dataset']['GLBv0.08']['version']['57.2']['time_range'] = {'time_start': '20160501', 'time_end': '20170131'}
+data_info['hourly']['dataset']['GLBv0.08']['version']['92.8']['time_range'] = {'time_start': '20170201', 'time_end': '20170531'}
+data_info['hourly']['dataset']['GLBv0.08']['version']['57.7']['time_range'] = {'time_start': '20170601', 'time_end': '20170930'}
+data_info['hourly']['dataset']['GLBv0.08']['version']['92.9']['time_range'] = {'time_start': '20171001', 'time_end': '20171231'}
+data_info['hourly']['dataset']['GLBv0.08']['version']['93.0']['time_range'] = {'time_start': '2018010112', 'time_end': '2020021909'}
 # GLBu0.08
-data_info['hourly']['dataset']['GLBu0.08']['version']['93.0']['time_range'] = {
-    'time_start': '20180919', 'time_end': '20181208'}
+data_info['hourly']['dataset']['GLBu0.08']['version']['93.0']['time_range'] = {'time_start': '20180919', 'time_end': '20181208'}
 # GLBy0.08
-data_info['hourly']['dataset']['GLBy0.08']['version']['93.0']['time_range'] = {
-    'time_start': '20181204', 'time_end': '20300904'}
+data_info['hourly']['dataset']['GLBy0.08']['version']['93.0']['time_range'] = {'time_start': '20181204', 'time_end': '20300904'}
 
 # variable
 variable_info = {
@@ -110,8 +98,7 @@ data_info['hourly']['dataset']['GLBy0.08']['version']['93.0']['classification']
 url_53x = {}
 for y_53x in range(1994, 2016):
     # r'https://ncss.hycom.org/thredds/ncss/GLBv0.08/expt_53.X/data/2013?'
-    url_53x[str(
-        y_53x)] = rf'https://ncss.hycom.org/thredds/ncss/GLBv0.08/expt_53.X/data/{y_53x}?'
+    url_53x[str(y_53x)] = rf'https://ncss.hycom.org/thredds/ncss/GLBv0.08/expt_53.X/data/{y_53x}?'
 data_info['hourly']['dataset']['GLBv0.08']['version']['53.X']['url'] = url_53x
 # GLBv0.08 56.3
 data_info['hourly']['dataset']['GLBv0.08']['version']['56.3']['url'] = r'https://ncss.hycom.org/thredds/ncss/GLBv0.08/expt_56.3?'
@@ -184,7 +171,7 @@ def draw_time_range(pic_save_folder=None):
                 'dataset': dataset,
                 'version': version,
                 'start_date': pd.to_datetime(t_s),
-                'end_date': pd.to_datetime(t_e)
+                'end_date': pd.to_datetime(t_e),
             })
 
     # Creating a DataFrame
@@ -194,34 +181,27 @@ def draw_time_range(pic_save_folder=None):
     plt.figure(figsize=(12, 6))
 
     # Combined labels for datasets and versions
-    combined_labels = [f"{dataset}_{version}" for dataset,
-                       version in zip(df['dataset'], df['version'])]
+    combined_labels = [f"{dataset}_{version}" for dataset, version in zip(df['dataset'], df['version'])]
 
     colors = plt.cm.viridis(np.linspace(0, 1, len(combined_labels)))
 
     # Assigning a color to each combined label
-    label_colors = {label: colors[i]
-                    for i, label in enumerate(combined_labels)}
+    label_colors = {label: colors[i] for i, label in enumerate(combined_labels)}
 
     # Plotting each time range
     k = 1
     for _, row in df.iterrows():
-        plt.plot([row['start_date'], row['end_date']], [k, k],
-                 color=label_colors[f"{row['dataset']}_{row['version']}"], linewidth=6)
+        plt.plot([row['start_date'], row['end_date']], [k, k], color=label_colors[f"{row['dataset']}_{row['version']}"], linewidth=6)
         # plt.text(row['end_date'], k,
         #          f"{row['version']}", ha='right', color='black')
         ymdh_s = row['start_date'].strftime('%Y-%m-%d %H')
         ymdh_e = row['end_date'].strftime('%Y-%m-%d %H')
         if k == 1 or k == len(combined_labels):
-            plt.text(row['start_date'], k+0.125,
-                     f"{ymdh_s}", ha='left', color='black')
-            plt.text(row['end_date'], k+0.125,
-                     f"{ymdh_e}", ha='right', color='black')
+            plt.text(row['start_date'], k+0.125, f"{ymdh_s}", ha='left', color='black')
+            plt.text(row['end_date'], k+0.125, f"{ymdh_e}", ha='right', color='black')
         else:
-            plt.text(row['start_date'], k+0.125,
-                     f"{ymdh_s}", ha='right', color='black')
-            plt.text(row['end_date'], k+0.125,
-                     f"{ymdh_e}", ha='left', color='black')
+            plt.text(row['start_date'], k+0.125, f"{ymdh_s}", ha='right', color='black')
+            plt.text(row['end_date'], k+0.125, f"{ymdh_e}", ha='left', color='black')
         k += 1
 
     # Setting the y-axis labels
@@ -283,7 +263,7 @@ def set_query_dict_no_vertical(var, lon_min, lon_max, lat_min, lat_max, time_str
         'horizStride': 1,
         'time': transform_time(time_str_ymdh),
         'addLatLon': 'true',
-        'accept': 'netcdf4'
+        'accept': 'netcdf4',
     }
     return query_dict
 
@@ -299,7 +279,7 @@ def set_query_dict_depth_or_level(var, lon_min, lon_max, lat_min, lat_max, time_
         'time': transform_time(time_str_ymdh),
         'vertCoord': 0,
         'addLatLon': 'true',
-        'accept': 'netcdf4'
+        'accept': 'netcdf4',
     }
     return query_dict
 
@@ -315,7 +295,7 @@ def set_query_dict_full(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh):
         'time': transform_time(time_str_ymdh),
         'vertStride': 1,
         'addLatLon': 'true',
-        'accept': 'netcdf4'
+        'accept': 'netcdf4',
     }
     return query_dict
 
@@ -351,21 +331,17 @@ def get_query_dict_single_level(var, lon_min, lon_max, lat_min, lat_max, level_n
 
 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)
+        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)
+        query_dict = set_query_dict_full(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh)
     return query_dict
 
 
 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)
+        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)
+        query_dict = set_query_dict_full(var, lon_min, lon_max, lat_min, lat_max, time_str_ymdh)
     return query_dict
 
 
@@ -377,8 +353,7 @@ def ymd_in_which_dataset_and_version(time_ymdh):
     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 = 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'
@@ -394,8 +369,7 @@ def ymd_in_which_dataset_and_version(time_ymdh):
         for d, v, trange in zip(d_list, v_list, trange_list):
             print(f'[bold blue]{d} {v} {trange}')
     else:
-        raise ValueError(
-            f'[bold red]{time_ymdh} is not in any dataset and version')
+        raise ValueError(f'[bold red]{time_ymdh} is not in any dataset and version')
 
 
 def direct_choose_dataset_and_version(time_ymdh):
@@ -428,8 +402,7 @@ def get_base_url(dataset_name, version_name, var, year_str):
         elif var in ['ssh']:
             base_url = url_dict['ssh']
         else:
-            print(
-                'Please ensure the var is in [u,v,temp,salinity,ssh,u_b,v_b,temp_b,salinity_b]')
+            print('Please ensure the var is in [u,v,temp,salinity,ssh,u_b,v_b,temp_b,salinity_b]')
     elif classification_method == 'var_year_different':
         if var in ['u', 'v', 'u_b', 'v_b']:
             base_url = url_dict['uv3z'][str(year_str)]
@@ -438,16 +411,14 @@ def get_base_url(dataset_name, version_name, var, year_str):
         elif var in ['ssh']:
             base_url = url_dict['ssh'][str(year_str)]
         else:
-            print(
-                'Please ensure the var is in [u,v,temp,salinity,ssh,u_b,v_b,temp_b,salinity_b]')
+            print('Please ensure the var is in [u,v,temp,salinity,ssh,u_b,v_b,temp_b,salinity_b]')
     return base_url
 
 
 def get_submit_url(dataset_name, version_name, var, year_str, query_dict):
     base_url = get_base_url(dataset_name, version_name, var, year_str)
     query_dict['var'] = [query_dict['var']]
-    target_url = base_url + '&'.join(f"var={var}" for var in query_dict['var']) + '&' + '&'.join(
-        f"{key}={value}" for key, value in query_dict.items() if key != 'var')
+    target_url = base_url + '&'.join(f"var={var}" for var in query_dict['var']) + '&' + '&'.join(f"{key}={value}" for key, value in query_dict.items() if key != 'var')
     return target_url
 
 
@@ -576,8 +547,7 @@ def dlownload_file(target_url, store_path, file_name, check=False):
         try:
             headers = {
                 'User-Agent': get_ua()}
-            response = s.get(target_url, headers=headers,
-                             timeout=5)
+            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
 
             # 保存文件
@@ -620,20 +590,17 @@ def direct_download(var, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90, dow
         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.')
         ymd_in_which_dataset_and_version(download_time)
-        dataset_name, version_name = direct_choose_dataset_and_version(
-            download_time)
+        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.')
         ymd_in_which_dataset_and_version(download_time)
-        dataset_name, version_name = direct_choose_dataset_and_version(
-            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.')
         ymd_in_which_dataset_and_version(download_time)
-        dataset_name, version_name = direct_choose_dataset_and_version(
-            download_time)
+        dataset_name, version_name = direct_choose_dataset_and_version(download_time)
     else:
         print('The dataset_name and version_name are both set by yourself.')
 
@@ -642,16 +609,13 @@ def direct_download(var, lon_min=0, lon_max=359.92, lat_min=-80, lat_max=90, dow
         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)
+        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(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)
+        query_dict = get_query_dict_single_level(var, lon_min, lon_max, lat_min, lat_max, level_num, download_time)
     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)
+        query_dict = get_query_dict_full_level(var, lon_min, lon_max, lat_min, lat_max, download_time)
     submit_url = get_submit_url(
         dataset_name, version_name, var, year_str, query_dict)
     file_name = f"HYCOM_{variable_info[var]['var_name']}_{download_time}.nc"
@@ -682,8 +646,7 @@ def download_task(var, time_str, lon_min, lon_max, lat_min, lat_max, depth, leve
     这样，每个任务都是独立的，有自己的参数和数据，不会与其他任务共享或修改任何数据。
     因此，即使多个任务同时执行，也不会出现数据交互错乱的问题。
     '''
-    direct_download(var, lon_min, lon_max, lat_min, lat_max, time_str,
-                    depth, level, store_path, dataset_name, version_name, check)
+    direct_download(var, lon_min, lon_max, lat_min, lat_max, time_str, depth, level, store_path, dataset_name, version_name, check)
 
 
 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):
@@ -724,30 +687,25 @@ def download(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_min=-80, lat_ma
     if len(ymdh_time_e) == 8:
         ymdh_time_e += '21'
     if ymdh_time_s == ymdh_time_e:
-        direct_download(var, lon_min, lon_max, lat_min, lat_max,
-                        ymdh_time_s, depth, level, store_path, dataset_name, version_name)
+        direct_download(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_time_list(ymdh_time_s, ymdh_time_e, 3)
         with Progress() as progress:
-            task = progress.add_task(
-                "[cyan]Downloading...", total=len(time_list))
+            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(var, lon_min, lon_max, lat_min, lat_max,
-                                    time_str, depth, level, store_path, dataset_name, version_name, check)
+                    direct_download(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')
+                    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]
+                    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))

oafuncs/oa_down/refs_pdf.py

@@ -4,8 +4,8 @@
 Author: Liu Kun && 16031215@qq.com
 Date: 2024-11-09 13:58:28
 LastEditors: Liu Kun && 16031215@qq.com
-LastEditTime: 2024-11-11 16:12:20
-FilePath: \\Python\\My_Funcs\\OAFuncs\\OAFuncs\\oa_down\\refs_pdf.py
+LastEditTime: 2024-11-21 13:18:18
+FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\oa_down\\refs_pdf.py
 Description:  
 EditPlatform: vscode
 ComputerInfo: XPS 15 9510
@@ -41,7 +41,7 @@ def _get_file_size(file_path, unit='KB'):
         'TB': 1024**4,
         'GB': 1024**3,
         'MB': 1024**2,
-        'KB': 1024
+        'KB': 1024,
     }
 
     # 检查传入的单位是否合法
@@ -178,14 +178,11 @@ class _Downloader:
                     self.pdf_url = got_url
                 print(f"URL: {self.pdf_url}")
             else:
-                print(f'[bold #AFEEEE]The website {
-                    self.url_list[self.url_index]} do not inlcude the PDF file.')
+                print(f'[bold #AFEEEE]The website {self.url_list[self.url_index]} do not inlcude the PDF file.')
                 self.try_times = self.try_times_each_url_max+1
         else:
-            print(f"Failed to retrieve the webpage. Status code: {
-                  response.status_code}")
-            print(f'[bold #AFEEEE]The website {
-                self.url_list[self.url_index]} do not inlcude the PDF file.')
+            print(f"Failed to retrieve the webpage. Status code: {response.status_code}")
+            print(f'[bold #AFEEEE]The website {self.url_list[self.url_index]} do not inlcude the PDF file.')
             self.try_times = self.try_times_each_url_max+1
 
     def url_iterate(self):
@@ -211,12 +208,10 @@ class _Downloader:
             if fsize < self.check_size:
                 # delete the wrong file
                 os.remove(self.fpath)
-                print(f"[bold yellow]The PDF file {
-                      self.fpath} is only {fsize:.2f} KB. It will be deleted and retry.")
+                print(f"[bold yellow]The PDF file {self.fpath} is only {fsize:.2f} KB. It will be deleted and retry.")
             else:
                 print('[bold #E6E6FA]-'*100)
-                print(f"[bold purple]The PDF file {
-                      self.fpath} already exists.")
+                print(f"[bold purple]The PDF file {self.fpath} already exists.")
                 return
         self.url_index = 0
         already_downloaded = False
@@ -242,8 +237,7 @@ class _Downloader:
                     return
             print(f"Downloading: {self.fname}...")
             try:
-                response = requests.get(
-                    self.pdf_url, headers=self.headers, cookies=self.cookies)
+                response = requests.get(self.pdf_url, headers=self.headers, cookies=self.cookies)
                 if response.status_code == 200:
                     with open(self.fpath, 'wb') as f:
                         f.write(response.content)
@@ -251,18 +245,14 @@ class _Downloader:
                     if fsize < self.check_size:
                         # delete the wrong file
                         os.remove(self.fpath)
-                        print(f"[bold yellow]The PDF file {
-                              self.fpath} is only {fsize:.2f} KB. It will be deleted and retry.")
+                        print(f"[bold yellow]The PDF file {self.fpath} is only {fsize:.2f} KB. It will be deleted and retry.")
                     else:
-                        print(f"[bold green]Sucessful to download {
-                              self.fpath}")
+                        print(f"[bold green]Sucessful to download {self.fpath}")
                         already_downloaded = True
                 else:
                     self.try_times = self.try_times_each_url_max+1
-                    print(f"Failed to download the PDF file. Status code: {
-                          response.status_code}")
-                    print(f'[bold #AFEEEE]The website {
-                        self.url_list[self.url_index]} do not inlcude the PDF file.')
+                    print(f"Failed to download the PDF file. Status code: {response.status_code}")
+                    print(f'[bold #AFEEEE]The website {self.url_list[self.url_index]} do not inlcude the PDF file.')
             except Exception as e:
                 print(f"Failed to download the PDF file. Error: {e}")
             time.sleep(self.sleep)
@@ -273,8 +263,7 @@ class _Downloader:
                     self.write_wrong_record()
                     return
                 if self.try_times == self.try_times_each_url_max:
-                    print(f'Tried {self.try_times} times for {
-                          self.url_list[self.url_index-1]}.')
+                    print(f'Tried {self.try_times} times for {self.url_list[self.url_index-1]}.')
                     print("Try another URL...")