oafuncs 0.0.98.5__py3-none-any.whl → 0.0.98.7__py3-none-any.whl

oafuncs/oa_down/hycom_3hourly.py

@@ -19,11 +19,11 @@ import logging
 import os
 import random
 import re
-import time
 import warnings
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from pathlib import Path
 from threading import Lock
+from oafuncs.oa_tool import pbar
 
 import httpx
 import matplotlib.pyplot as plt
@@ -32,7 +32,6 @@ import numpy as np
 import pandas as pd
 import xarray as xr
 from rich import print
-from rich.progress import Progress
 
 from oafuncs.oa_down.idm import downloader as idm_downloader
 from oafuncs.oa_down.user_agent import get_ua
@@ -668,17 +667,19 @@ def _correct_time(nc_file):
     modify_nc(nc_file, "time", None, time_difference)
 
 
+def setup_logger(level=logging.INFO):
+    logging.basicConfig(format="%(asctime)s - %(levelname)s - %(message)s", level=level)
+
+
 class _HycomDownloader:
     def __init__(self, tasks, delay_range=(3, 6), timeout_factor=120, max_var_count=5, max_retries=3):
-        """
-        :param tasks: List of (url, save_path)
-        """
         self.tasks = tasks
         self.delay_range = delay_range
         self.timeout_factor = timeout_factor
         self.max_var_count = max_var_count
         self.max_retries = max_retries
         self.count = {"success": 0, "fail": 0}
+        setup_logger()
 
     def user_agent(self):
         return get_ua()
@@ -688,61 +689,84 @@ class _HycomDownloader:
         headers = {"User-Agent": self.user_agent()}
         var_count = min(max(url.count("var="), 1), self.max_var_count)
         timeout_max = self.timeout_factor * var_count
-        timeout = random.randint(timeout_max // 2, timeout_max)
 
         retry = 0
         while retry <= self.max_retries:
+            timeout = random.randint(timeout_max // 2, timeout_max)
             try:
                 await asyncio.sleep(random.uniform(*self.delay_range))
                 start = datetime.datetime.now()
+
                 async with httpx.AsyncClient(
                     timeout=httpx.Timeout(timeout),
                     limits=httpx.Limits(max_connections=2, max_keepalive_connections=2),
                     transport=httpx.AsyncHTTPTransport(retries=2),
                 ) as client:
-                    print(f"[bold #f0f6d0]Requesting {file_name} (Attempt {retry + 1}) ...")
+                    logging.info(f"Requesting {file_name} (Attempt {retry + 1}) ...")
                     response = await client.get(url, headers=headers, follow_redirects=True)
                     response.raise_for_status()
                     if not response.content:
                         raise ValueError("Empty response received")
 
-                    print(f"[bold #96cbd7]Downloading {file_name} ...")
+                    logging.info(f"Downloading {file_name} ...")
                     with open(save_path, "wb") as f:
+                        total = int(response.headers.get("Content-Length", 0))
+                        downloaded = 0
+                        last_percent = -1
+
                         async for chunk in response.aiter_bytes(32 * 1024):
                             f.write(chunk)
+                            downloaded += len(chunk)
+
+                            if total > 0:
+                                percent = int(downloaded * 100 / total)
+                                if percent != last_percent:
+                                    logging.info(f"{file_name}: {percent}% ({downloaded / 1024:.1f} KB / {total / 1024:.1f} KB)")
+                                    last_percent = percent
+
 
                     elapsed = datetime.datetime.now() - start
-                    print(f"[#3dfc40]File [bold #dfff73]{file_name} [#3dfc40]downloaded, Time: [#39cbdd]{elapsed}")
+                    # logging.info(f"File {file_name} downloaded, Time: {elapsed}")
+                    logging.info(f"Saving {file_name} ...")
+                    logging.info(f"Timing {elapsed} ...")
                     self.count["success"] += 1
                     count_dict["success"] += 1
+                    # 输出一条绿色的成功消息
+                    timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S,%f")[:-3]
+                    # print(f"{timestamp} - INFO - ", end="") # Output log prefix without newline
+                    # print("[bold #3dfc40]Success")
+                    print(f"{timestamp} - RESULT - [bold #3dfc40]Success")
                     return
 
             except Exception as e:
-                print(f"[bold red]Failed ({type(e).__name__}): {e}")
+                logging.error(f"Failed ({type(e).__name__}): {e}")
                 if retry < self.max_retries:
                     backoff = 2**retry
-                    print(f"[yellow]Retrying in {backoff:.1f}s ...")
+                    logging.warning(f"Retrying in {backoff:.1f}s ...")
                     await asyncio.sleep(backoff)
                     retry += 1
                 else:
-                    print(f"[red]Giving up on {file_name}")
+                    logging.error(f"Giving up on {file_name}")
                     self.count["fail"] += 1
                     count_dict["fail"] += 1
+                    timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S,%f")[:-3]
+                    # print(f"{timestamp} - ERROR - ", end="")
+                    # print("[bold red]Failed")
+                    print(f"{timestamp} - RESULT - [bold red]Failure")
                     return
 
     async def run(self):
-        print(f"📥 Starting download of {len(self.tasks)} files ...")
+        logging.info(f"📥 Starting download of {len(self.tasks)} files ...")
         for url, save_path in self.tasks:
             await self._download_one(url, save_path)
 
-        print("\n✅ All tasks completed.")
-        print(f"✔️  Success: {self.count['success']} | ❌ Fail: {self.count['fail']}")
+        logging.info("✅ All tasks completed.")
+        logging.info(f"✔️  Success: {self.count['success']} | ❌ Fail: {self.count['fail']}")
 
 
 def _download_file(target_url, store_path, file_name, cover=False):
     save_path = Path(store_path) / file_name
-    file_name_split = file_name.split("_")
-    file_name_split = file_name_split[:-1]
+    file_name_split = file_name.split("_")[:-1]
     same_file = "_".join(file_name_split) + "*nc"
 
     if match_time is not None:
@@ -759,10 +783,12 @@ def _download_file(target_url, store_path, file_name, cover=False):
                 print(f"[bold green]{file_name} is correct")
         return
 
-    if not cover and os.path.exists(save_path):
-        print(f"[bold #FFA54F]{save_path} exists, skipping ...")
-        count_dict["skip"] += 1
-        return
+    # if not cover and os.path.exists(save_path):
+    #     print(f"[bold #FFA54F]{save_path} exists, skipping ...")
+    #     count_dict["skip"] += 1
+    #     return
+    if cover and os.path.exists(save_path):
+        _clear_existing_file(save_path)
 
     if same_file not in fsize_dict.keys():
         check_nc(save_path, delete_if_invalid=True, print_messages=False)
@@ -770,6 +796,7 @@ def _download_file(target_url, store_path, file_name, cover=False):
     get_mean_size = _get_mean_size_move(same_file, save_path)
 
     if _check_existing_file(save_path, get_mean_size):
+        print(f"[bold #FFA54F]{save_path} exists, skipping ...")
         count_dict["skip"] += 1
         return
 
@@ -778,12 +805,12 @@ def _download_file(target_url, store_path, file_name, cover=False):
     if not use_idm:
         python_downloader = _HycomDownloader([(target_url, save_path)])
         asyncio.run(python_downloader.run())
-        time.sleep(3 + random.uniform(0, 10))
+        # time.sleep(3 + random.uniform(0, 10))
     else:
         idm_downloader(target_url, store_path, file_name, given_idm_engine)
         idm_download_list.append(save_path)
         # print(f"[bold #3dfc40]File [bold #dfff73]{save_path} [#3dfc40]has been submit to IDM for downloading")
-        time.sleep(3 + random.uniform(0, 10))
+        # time.sleep(3 + random.uniform(0, 10))
 
 
 def _check_hour_is_valid(ymdh_str):
@@ -874,7 +901,7 @@ def _prepare_url_to_download(var, lon_min=0, lon_max=359.92, lat_min=-80, lat_ma
         else:
             if download_time < "2024081012":
                 varlist = [_ for _ in var]
-                for key, value in var_group.items():
+                for key, value in pbar(var_group.items(), description=f"Var Group {download_time} ->", total=len(var_group), color="#d7feb9", next_line=True):
                     current_group = []
                     for v in varlist:
                         if v in value:
@@ -896,7 +923,7 @@ def _prepare_url_to_download(var, lon_min=0, lon_max=359.92, lat_min=-80, lat_ma
                             file_name = f"HYCOM_{key}_{download_time}-{download_time_end}.nc"
                     _download_file(submit_url, store_path, file_name, cover)
             else:
-                for v in var:
+                for v in pbar(var, description=f"Var {download_time} ->", total=len(var), color="#d7feb9", next_line=True):
                     submit_url = _get_submit_url_var(v, depth, level_num, lon_min, lon_max, lat_min, lat_max, dataset_name, version_name, download_time, download_time_end)
                     file_name = f"HYCOM_{variable_info[v]['var_name']}_{download_time}.nc"
                     if download_time_end is not None:
@@ -930,7 +957,7 @@ def _download_hourly_func(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_mi
     if num_workers is not None and num_workers > 1:
         global parallel_counter
         parallel_counter = 0
-        counter_lock = Lock()
+        counter_lock = Lock()  # noqa: F841
     if ymdh_time_s == ymdh_time_e:
         _prepare_url_to_download(var, lon_min, lon_max, lat_min, lat_max, ymdh_time_s, None, depth, level, store_path, dataset_name, version_name, cover)
     elif int(ymdh_time_s) < int(ymdh_time_e):
@@ -938,17 +965,19 @@ def _download_hourly_func(var, time_s, time_e, lon_min=0, lon_max=359.92, lat_mi
             print("*" * mark_len)
             print("Downloading a series of files...")
         time_list = _get_time_list(ymdh_time_s, ymdh_time_e, interval_hour, "hour")
-        with Progress() as progress:
-            task = progress.add_task(f"[cyan]{bar_desc}", total=len(time_list))
-            if num_workers is None or num_workers <= 1:
-                for i, time_str in enumerate(time_list):
-                    _prepare_url_to_download(var, lon_min, lon_max, lat_min, lat_max, time_str, None, depth, level, store_path, dataset_name, version_name, cover)
-                    progress.update(task, advance=1, description=f"[cyan]{bar_desc} {i + 1}/{len(time_list)}")
-            else:
-                with ThreadPoolExecutor(max_workers=num_workers) as executor:
-                    futures = [executor.submit(_download_task, var, time_str, None, lon_min, lon_max, lat_min, lat_max, depth, level, store_path, dataset_name, version_name, cover) for time_str in time_list]
-                    for feature in as_completed(futures):
-                        _done_callback(feature, progress, task, len(time_list), counter_lock)
+        # with Progress() as progress:
+            # task = progress.add_task(f"[cyan]{bar_desc}", total=len(time_list))
+        if num_workers is None or num_workers <= 1:
+            for i, time_str in pbar(enumerate(time_list), description=f"{bar_desc}", total=len(time_list), cmap='colorful_1', next_line=True):
+                _prepare_url_to_download(var, lon_min, lon_max, lat_min, lat_max, time_str, None, depth, level, store_path, dataset_name, version_name, cover)
+                # progress.update(task, advance=1, description=f"[cyan]{bar_desc} {i + 1}/{len(time_list)}")
+        else:
+            with ThreadPoolExecutor(max_workers=num_workers) as executor:
+                futures = [executor.submit(_download_task, var, time_str, None, lon_min, lon_max, lat_min, lat_max, depth, level, store_path, dataset_name, version_name, cover) for time_str in time_list]
+                """ for feature in as_completed(futures):
+                    _done_callback(feature, progress, task, len(time_list), counter_lock) """
+                for _ in pbar(as_completed(futures),description=f"{bar_desc}", total=len(futures),cmap='colorful_1',next_line=True):
+                    pass
     else:
         print("[bold red]Please ensure the time_s is no more than time_e")
 
@@ -1032,7 +1061,6 @@ def download(
         interval_hours=3,
         )
     """
-    from oafuncs.oa_tool import pbar
 
     _get_initial_data()
 
@@ -1093,10 +1121,10 @@ def download(
         workers = 1
         given_idm_engine = idm_path
         idm_download_list = []
-        bar_desc = "Submitting to IDM ..."
+        bar_desc = "Submitting to IDM ->"
     else:
         use_idm = False
-        bar_desc = "Downloading ..."
+        bar_desc = "Downloading ->"
 
     global match_time
     match_time = validate_time
@@ -1108,7 +1136,7 @@ def download(
         workers = 1
         print("*" * mark_len)
         print("[bold red]Only checking the time of existing files.")
-        bar_desc = "Checking time ..."
+        bar_desc = "Checking time ->"
 
     _download_hourly_func(
         variables,
@@ -1134,7 +1162,7 @@ def download(
         print("[bold #ecdbfe]*" * mark_len)
         if idm_download_list:
             remain_list = idm_download_list.copy()
-            for _ in pbar(range(len(idm_download_list)), cmap="diverging_1", description="Downloading: "):
+            for _ in pbar(range(len(idm_download_list)), cmap="diverging_1", description="Downloading ->"):
                 success = False
                 while not success:
                     for f in remain_list:
@@ -1190,6 +1218,7 @@ if __name__ == "__main__":
         "validate_time": None,
         # "idm_path": r"D:\Programs\Internet Download Manager\IDMan.exe",
         "interval_hours": 24,
+        "proxy_txt": None,
     }
 
     if single_var: