oafuncs 0.0.98.3__py3-none-any.whl → 0.0.98.5__py3-none-any.whl

oafuncs/oa_down/hycom_3hourly.py

@@ -13,7 +13,9 @@ SystemInfo: Windows 11
 Python Version: 3.12
 """
 
+import asyncio
 import datetime
+import logging
 import os
 import random
 import re
@@ -23,11 +25,11 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
 from pathlib import Path
 from threading import Lock
 
+import httpx
 import matplotlib.pyplot as plt
 import netCDF4 as nc
 import numpy as np
 import pandas as pd
-import requests
 import xarray as xr
 from rich import print
 from rich.progress import Progress
@@ -38,6 +40,9 @@ from oafuncs.oa_file import file_size
 from oafuncs.oa_nc import check as check_nc
 from oafuncs.oa_nc import modify as modify_nc
 
+logging.getLogger("httpx").setLevel(logging.WARNING)  # 关闭 httpx 的 INFO 日志，只显示 WARNING 及以上
+
+
 warnings.filterwarnings("ignore", category=RuntimeWarning, message="Engine '.*' loading failed:.*")
 
 __all__ = ["draw_time_range", "download"]
@@ -414,13 +419,13 @@ def _check_time_in_dataset_and_version(time_input, time_end=None):
                     trange_list.append(f"{time_s}-{time_e}")
                     have_data = True
 
-    # 输出结果
-    if match_time is None:
-        print(f"[bold red]{time_input_str} is in the following dataset and version:")
     if have_data:
         if match_time is None:
+            print(f"[bold red]Time {time_input_str} included in:")
+            dv_num = 1
             for d, v, trange in zip(d_list, v_list, trange_list):
-                print(f"[bold blue]{d} {v} {trange}")
+                print(f"{dv_num} -> [bold blue]{d} - {v} : {trange}")
+                dv_num += 1
         if is_single_time:
             return True
         else:
@@ -432,7 +437,7 @@ def _check_time_in_dataset_and_version(time_input, time_end=None):
                 print(f"[bold red]{time_start} to {time_end} is in different datasets or versions, so you can't download them together")
                 return False
     else:
-        print(f"[bold red]{time_input_str} is not in any dataset and version")
+        print(f"[bold red]Time {time_input_str} has no data")
         return False
 
 
@@ -507,7 +512,8 @@ def _direct_choose_dataset_and_version(time_input, time_end=None):
 
     if dataset_name_out is not None and version_name_out is not None:
         if match_time is None:
-            print(f"[bold purple]dataset: {dataset_name_out}, version: {version_name_out} is chosen")
+            # print(f"[bold purple]dataset: {dataset_name_out}, version: {version_name_out} is chosen")
+            print(f"[bold purple]Chosen dataset: {dataset_name_out} - {version_name_out}")
 
     # 如果没有找到匹配的数据集和版本，会返回 None
     return dataset_name_out, version_name_out
@@ -611,7 +617,7 @@ def _get_mean_size_move(same_file, current_file):
         size_difference_ratio = (current_file_size - fsize_dict[same_file]["mean_size"]) / fsize_dict[same_file]["mean_size"]
 
         if abs(size_difference_ratio) > tolerance_ratio:
-            if check_nc(current_file,print_messages=False):
+            if check_nc(current_file, print_messages=False):
                 fsize_dict[same_file]["size_list"] = [current_file_size]
                 fsize_dict[same_file]["mean_size"] = current_file_size
             else:
@@ -662,110 +668,122 @@ def _correct_time(nc_file):
     modify_nc(nc_file, "time", None, time_difference)
 
 
+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}
+
+    def user_agent(self):
+        return get_ua()
+
+    async def _download_one(self, url, save_path):
+        file_name = os.path.basename(save_path)
+        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:
+            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}) ...")
+                    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} ...")
+                    with open(save_path, "wb") as f:
+                        async for chunk in response.aiter_bytes(32 * 1024):
+                            f.write(chunk)
+
+                    elapsed = datetime.datetime.now() - start
+                    print(f"[#3dfc40]File [bold #dfff73]{file_name} [#3dfc40]downloaded, Time: [#39cbdd]{elapsed}")
+                    self.count["success"] += 1
+                    count_dict["success"] += 1
+                    return
+
+            except Exception as e:
+                print(f"[bold red]Failed ({type(e).__name__}): {e}")
+                if retry < self.max_retries:
+                    backoff = 2**retry
+                    print(f"[yellow]Retrying in {backoff:.1f}s ...")
+                    await asyncio.sleep(backoff)
+                    retry += 1
+                else:
+                    print(f"[red]Giving up on {file_name}")
+                    self.count["fail"] += 1
+                    count_dict["fail"] += 1
+                    return
+
+    async def run(self):
+        print(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']}")
+
+
 def _download_file(target_url, store_path, file_name, cover=False):
-    fname = Path(store_path) / file_name
+    save_path = Path(store_path) / file_name
     file_name_split = file_name.split("_")
     file_name_split = file_name_split[:-1]
     same_file = "_".join(file_name_split) + "*nc"
 
     if match_time is not None:
-        if check_nc(fname, print_messages=False):
-            if not _check_ftime(fname, if_print=True):
+        if check_nc(save_path, print_messages=False):
+            if not _check_ftime(save_path, if_print=True):
                 if match_time:
-                    _correct_time(fname)
+                    _correct_time(save_path)
                     count_dict["skip"] += 1
                 else:
-                    _clear_existing_file(fname)
+                    _clear_existing_file(save_path)
                     count_dict["no_data"] += 1
             else:
                 count_dict["skip"] += 1
                 print(f"[bold green]{file_name} is correct")
         return
 
-    if not cover and os.path.exists(fname):
-        print(f"[bold #FFA54F]{fname} exists, skipping ...")
+    if not cover and os.path.exists(save_path):
+        print(f"[bold #FFA54F]{save_path} exists, skipping ...")
         count_dict["skip"] += 1
         return
 
     if same_file not in fsize_dict.keys():
-        check_nc(fname, delete_if_invalid=True, print_messages=False)
+        check_nc(save_path, delete_if_invalid=True, print_messages=False)
 
-    get_mean_size = _get_mean_size_move(same_file, fname)
+    get_mean_size = _get_mean_size_move(same_file, save_path)
 
-    if _check_existing_file(fname, get_mean_size):
+    if _check_existing_file(save_path, get_mean_size):
         count_dict["skip"] += 1
         return
 
-    _clear_existing_file(fname)
+    _clear_existing_file(save_path)
 
     if not use_idm:
-        print(f"[bold #f0f6d0]Requesting {file_name} ...")
-        s = requests.Session()
-        download_success = False
-        request_times = 0
-
-        def calculate_wait_time(time_str, target_url):
-            time_pattern = r"\d{10}"
-            times_in_str = re.findall(time_pattern, time_str)
-            num_times_str = len(times_in_str)
-
-            if num_times_str > 1:
-                delta_t = datetime.datetime.strptime(times_in_str[1], "%Y%m%d%H") - datetime.datetime.strptime(times_in_str[0], "%Y%m%d%H")
-                delta_t = delta_t.total_seconds() / 3600
-                delta_t = delta_t / 3 + 1
-            else:
-                delta_t = 1
-            num_var = int(target_url.count("var="))
-            if num_var <= 0:
-                num_var = 1
-            return int(delta_t * 5 * 60 * num_var)
-
-        max_timeout = calculate_wait_time(file_name, target_url)
-        print(f"[bold #912dbc]Max timeout: {max_timeout} seconds")
-
-        download_time_s = datetime.datetime.now()
-        order_list = ["1st", "2nd", "3rd", "4th", "5th", "6th", "7th", "8th", "9th", "10th"]
-        while not download_success:
-            if request_times >= 10:
-                print(f"[bold #ffe5c0]Download failed after {request_times} times\nYou can skip it and try again later")
-                count_dict["fail"] += 1
-                break
-            if request_times > 0:
-                print(f"[bold #ffe5c0]Retrying the {order_list[request_times - 1]} time...")
-            try:
-                headers = {"User-Agent": get_ua()}
-                response = s.get(target_url, headers=headers, stream=True, timeout=random.randint(5, max_timeout))
-                response.raise_for_status()
-                with open(fname, "wb") as f:
-                    print(f"[bold #96cbd7]Downloading {file_name} ...")
-                    for chunk in response.iter_content(chunk_size=1024):
-                        if chunk:
-                            f.write(chunk)
-
-                f.close()
-
-                if os.path.exists(fname):
-                    download_success = True
-                    download_time_e = datetime.datetime.now()
-                    download_delta = download_time_e - download_time_s
-                    print(f"[#3dfc40]File [bold #dfff73]{fname} [#3dfc40]has been downloaded successfully, Time: [#39cbdd]{download_delta}")
-                    count_dict["success"] += 1
-
-            except requests.exceptions.HTTPError as errh:
-                print(f"Http Error: {errh}")
-            except requests.exceptions.ConnectionError as errc:
-                print(f"Error Connecting: {errc}")
-            except requests.exceptions.Timeout as errt:
-                print(f"Timeout Error: {errt}")
-            except requests.exceptions.RequestException as err:
-                print(f"OOps: Something Else: {err}")
-
-            time.sleep(3)
-            request_times += 1
+        python_downloader = _HycomDownloader([(target_url, save_path)])
+        asyncio.run(python_downloader.run())
+        time.sleep(3 + random.uniform(0, 10))
     else:
         idm_downloader(target_url, store_path, file_name, given_idm_engine)
-        idm_download_list.append(fname)
-        print(f"[bold #3dfc40]File [bold #dfff73]{fname} [#3dfc40]has been submit to IDM for downloading")
+        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))
 
 
 def _check_hour_is_valid(ymdh_str):
@@ -992,7 +1010,7 @@ def download(
 
     Returns:
         None
-    
+
     Example:
         >>> download(
         variables='u',
@@ -1088,7 +1106,7 @@ def download(
 
     if validate_time is not None:
         workers = 1
-        print('*' * mark_len)
+        print("*" * mark_len)
         print("[bold red]Only checking the time of existing files.")
         bar_desc = "Checking time ..."
 
@@ -1158,20 +1176,20 @@ if __name__ == "__main__":
 
     options = {
         "variables": var_list,
-        "start_time": "2025010300",
-        "end_time": "2025010309",
-        "output_dir": r"I:\Data\HYCOM\3hourly_test",
+        "start_time": "2018010100",
+        "end_time": "2019063000",
+        "output_dir": r"G:\Data\HYCOM\china_sea\hourly_24",
         "lon_min": 105,
-        "lon_max": 130,
-        "lat_min": 15,
+        "lon_max": 135,
+        "lat_min": 10,
         "lat_max": 45,
         "workers": 1,
         "overwrite": False,
         "depth": None,
         "level": None,
-        "validate_time": True,
-        "idm_path": r'D:\Programs\Internet Download Manager\IDMan.exe',
-        "interval_hours": 3,
+        "validate_time": None,
+        # "idm_path": r"D:\Programs\Internet Download Manager\IDMan.exe",
+        "interval_hours": 24,
     }
 
     if single_var:

oafuncs/oa_down/test_ua.py

@@ -1,151 +1,40 @@
-#!/usr/bin/env python
-# coding=utf-8
-"""
-Author: Liu Kun && 16031215@qq.com
-Date: 2024-12-01 19:32:25
-LastEditors: Liu Kun && 16031215@qq.com
-LastEditTime: 2024-12-10 11:16:36
-FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\oa_down\\test.py
-Description:
-EditPlatform: vscode
-ComputerInfo: XPS 15 9510
-SystemInfo: Windows 11
-Python Version: 3.12
-"""
-
-import os
-import random
 import re
 
 
-def is_valid_user_agent(user_agent):
-    # 简单的正则表达式来检查User Agent的格式
-    # 这个正则表达式检查User Agent是否包含常见的浏览器信息格式
+def is_valid_ua(ua):
+    # 更宽松的 UA 验证规则
     pattern = re.compile(
-        r"^(?:(?:Mozilla|Opera|Chrome|Safari|Edg|OPR)/[\d.]+)"
-        r"(?:\s(?:\(.*?\)))?"
-        r"(?:\s(?:Gecko|AppleWebKit|KHTML, like Gecko|Version|Edge|OPR)/[\d.]+)?"
-        r"(?:\s.*?(?:rv:|Version/|Ubuntu|Macintosh|Windows|X11|Linux|CrOS|FreeBSD|OpenBSD|NetBSD|iPhone|iPad|iPod|Android|BlackBerry|BB10|Mobile|Symbian|Windows Phone|IEMobile|Opera Mini|Opera Mobi|UCBrowser|MQQBrowser|baiduboxapp|baidubrowser|Safari|Firefox|MSIE|Trident|Edge|EdgA|Chrome|CriOS|Vivaldi|Sleipnir|Midori|ELinks|Lynx|w3m|Arora|Epiphany|Konqueror|Dillo|Netscape|SeaMonkey|K-Meleon|Camino|Iceape|Galeon|GranParadiso|Iceweasel|Firefox|Fennec|Conkeror|PaleMoon|Uzbl|QupZilla|Otter|Waterfox|Basilisk|Cyberfox|PaleMoon|GNU IceCat|GNU IceWeasel|IceCat|IceWeasel|Seamonkey|Iceape|Firefox|Epiphany|Web|Safari|Android|Mobile|BlackBerry|BB10|Tablet|Silk|Kindle|FxiOS|Focus|SamsungBrowser|browser|AppleWebKit|Puffin|DuckDuckGo|YaBrowser|Yandex|Amigo|NokiaBrowser|OviBrowser|OneBrowser|Chrome|Firefox|Safari|OPR|Coast|Mercury|Silk|Skyfire|IEMobile|Bolt|Jasmine|NativeHost|Crosswalk|TizenBrowser|SailfishBrowser|SamsungBrowser|Silk-Accelerated|UCBrowser|Quark|XiaoMi|OnePlus|Vivo|Oppo|Realme|Meizu|Lenovo|Huawei|ZTE|Alcatel|Sony|Nokia|LG|HTC|Asus|Acer|Motorola|Samsung)/[\d.]+)?$"
+        r"""
+        ^Mozilla/(4\.0|5\.0)          # 必须以 Mozilla/4.0 或 5.0 开头
+        \s+                          # 空格
+        \(.*?\)                      # 操作系统信息
+        \s+                          # 空格
+        (AppleWebKit/|Gecko/|Trident/|Version/|Edge/)?  # 浏览器引擎或版本标识（可选）
+        \d+(\.\d+)*                  # 至少一个版本号（小数部分可选）
+        .*                           # 允许后续扩展信息
+        $                            # 行尾
+    """,
+        re.VERBOSE,
     )
+    return re.match(pattern, ua.strip()) is not None
 
-    # 使用正则表达式匹配User Agent字符串
-    if pattern.match(user_agent):
-        return True
-    else:
-        return False
-
-
-def get_ua():
-    current_dir = os.path.dirname(os.path.abspath(__file__))
-    ua_file_txt = os.path.join(current_dir, "User_Agent-list.txt")
-
-    with open(ua_file_txt, "r") as f:
-        ua_list = f.readlines()
-        # 去掉换行符和空行
-        ua_list = [line.strip() for line in ua_list if line.strip()]
 
-    return random.choice(ua_list)
+def main():
+    input_file = r"E:\Code\Python\My_Funcs\OAFuncs\oafuncs\oa_down\User_Agent-list-old.txt"
+    output_file = r"E:\Code\Python\My_Funcs\OAFuncs\oafuncs\oa_down\User_Agent-list.txt"
 
+    valid_uas = []
+    with open(input_file, "r", encoding="utf-8") as f:
+        for line in f:
+            line = line.strip()
+            if line and is_valid_ua(line):
+                valid_uas.append(line)
 
-def get_ua_org():
-    ua_list = [
-        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36 OPR/26.0.1656.60",
-        "Opera/8.0 (Windows NT 5.1; U; en)",
-        "Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50",
-        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; en) Opera 9.50",
-        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
-        "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
-        "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
-        "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0",
-        "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
-        "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",
-        "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",
-        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36",
-        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
-        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16",
-        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
-        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36",
-        "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko",
-        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
-        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
-        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
-        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
-        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
-        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
-        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
-        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0",
-        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0)",
-        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
-        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.3.4000 Chrome/30.0.1599.101 Safari/537.36",
-        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
-        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 UBrowser/4.0.3214.0 Safari/537.36",
-        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4094.1 Safari/537.36",
-        "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 (iPod; 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_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 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",
-        "Mozilla/5.0 (Linux; U; Android 2.2.1; zh-cn; HTC_Wildfire_A3333 Build/FRG83D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
-        "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
-        "MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
-        "Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
-        "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
-        "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
-        "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
-        "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;",
-        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
-        "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
-        "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
-        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
-        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
-        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
-        "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
-        "Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
-        "Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
-        "Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
-        "UCWEB7.0.2.37/28/999",
-        "NOKIA5700/UCWEB7.0.2.37/28/999",
-        "Openwave/UCWEB7.0.2.37/28/999",
-        "Openwave/UCWEB7.0.2.37/28/999",
-    ]
-    with open(newtxtfile, "w") as f:
-        for line in ua_list:
-            f.write(line + "\n")
-    # print(f'Using User-Agent: {ua}')
-    ua = random.choice(ua_list)
-    return ua
+    with open(output_file, "w", encoding="utf-8") as f:
+        f.write("\n".join(valid_uas))
 
+    print(f"[Linux 兼容模式] 有效UA已保存到 {output_file}，共 {len(valid_uas)} 条")
 
-# get_ua_org()
 
 if __name__ == "__main__":
-    txtfile = r"E:\Code\Python\My_Funcs\OAFuncs\oafuncs\oa_down\User_Agent-list.txt"
-
-    with open(txtfile, "r") as f:
-        lines = f.readlines()
-        # 去掉换行符和空行
-        lines = [line.strip() for line in lines if line.strip()]
-    """ new_line = []
-    for i in range(len(lines)):
-        if '/' in lines[i]:
-            new_line.append(lines[i])
-        else:
-            print(lines[i]) """
-
-    new_line = []
-    for line in lines:
-        if is_valid_user_agent(line):
-            # print(line)
-            new_line.append(line)
-        else:
-            print(f"Invalid User-Agent: {line}")
-
-    newtxtfile = r"E:\Code\Python\My_Funcs\OAFuncs\oafuncs\oa_down\ua_list_new.txt"
-    with open(newtxtfile, "w") as f:
-        for line in new_line:
-            f.write(line + "\n")
+    main()