oafuncs 0.0.98.44__py3-none-any.whl → 0.0.98.46__py3-none-any.whl

oafuncs/__init__.py

@@ -42,4 +42,6 @@ from .oa_tool import *
 from .oa_date import *
 # ------------------- 2025-03-27 16:56:57 -------------------
 from .oa_geo import *
-# ------------------- 2025-09-04 14:08:26 -------------------
+# ------------------- 2025-09-04 14:08:26 -------------------
+from .oa_linux import *
+# ------------------- 2025-09-14 12:30:00 -------------------

oafuncs/_script/email.py

@@ -1,14 +1,9 @@
-import random
-import smtplib
-from email.header import Header
-from email.mime.multipart import MIMEMultipart
-from email.mime.text import MIMEText
-
 from rich import print
 
 __all__ = ["send"]
 
 def _email_info():
+    import random
     email_dict = {
         "liukun0312@vip.qq.com": [4, 13, -10, 2, -10, 4, -7, -8, 8, -1, 3, -2, -11, -6, -9, -7],
         "756866877@qq.com": [4, -2, -3, 13, 12, 8, -6, 9, -12, 13, -10, -12, -11, -12, -4, -11],
@@ -26,6 +21,10 @@ def _decode_password(password):
 
 
 def _send_message(title, content, msg_to):
+    from email.header import Header
+    from email.mime.multipart import MIMEMultipart
+    from email.mime.text import MIMEText
+    import smtplib
     # 1. 连接邮箱服务器
     con = smtplib.SMTP_SSL("smtp.qq.com", 465)
 

oafuncs/oa_cmap.py

@@ -271,6 +271,9 @@ def get(colormap_name: Optional[str] = None, show_available: bool = False) -> Op
         "diverging_4": ["#5DADE2", "#A2D9F7", "#D6EAF8", "#F2F3F4", "#FADBD8", "#F1948A", "#E74C3C"],
         # ----------------------------------------------------------------------------
         "colorful_1": ["#6d00db", "#9800cb", "#F2003C", "#ff4500", "#ff7f00", "#FE28A2", "#FFC0CB", "#DDA0DD", "#40E0D0", "#1a66f2", "#00f7fb", "#8fff88", "#E3FF00"],
+        # ----------------------------------------------------------------------------
+        "increasing_1": ["#FFFFFF", "#E6F7FF", "#A5E6F8", "#049CD4", "#11B5A3", "#04BC4C", "#74CC54", "#D9DD5C", "#FB922E", "#FC2224", "#E51C18", "#8B0000"],
+        # ----------------------------------------------------------------------------
     }
 
     if show_available:

oafuncs/oa_down/literature.py

@@ -2,6 +2,7 @@ import os
 import re
 import time
 from pathlib import Path
+from urllib.parse import urljoin
 
 import pandas as pd
 import requests
@@ -11,7 +12,7 @@ from oafuncs.oa_down.user_agent import get_ua
 from oafuncs.oa_file import remove
 from oafuncs.oa_data import ensure_list
 
-__all__ = ["download5doi"]
+__all__ = ["download5doi", "download5doi_via_unpaywall"]
 
 
 def _get_file_size(file_path, unit="KB"):
@@ -46,75 +47,142 @@ class _Downloader:
     根据doi下载文献pdf
     """
 
-    def __init__(self, doi, store_path):
+    # 进程级缓存：首次探测后的可用镜像列表，后续复用
+    _alive_mirrors_cache: list[str] | None = None
+
+    def __init__(self, doi, store_path, *, min_size_kb=50, timeout_html=15, timeout_pdf=30, sleep_secs=5, tries_each_url=3, debug=False):
         self.url_list = [
             r"https://sci-hub.se",
             r"https://sci-hub.ren",
             r"https://sci-hub.st",
-            r"https://sci-hub.ru", # 最好用的一个网站
+            r"https://sci-hub.ru",  # 最好用的一个网站
             # ------------------------------------- 以下网站没验证
-            r"https://sci-hub.wf",
-            r"https://sci-hub.yt",
-            r"https://sci-hub.ee",
-            r"https://sci-hub.cat",
             r"https://sci-hub.in",
-            r"https://www.pismin.com",
-            r"https://sci-hub.vkif.top",
-            r"https://www.bothonce.com",
-            r"https://sci-hub.et-fine.com",
-            r"https://sci-hub.hkvisa.net",
-            # r"https://sci-hub.3800808.com", # 这个只能手动保存
-            r"https://sci-hub.zidianzhan.net",
-            r"https://sci-hub.usualwant.com",
+            r"https://sci-hub.hlgczx.com/",
         ]
         self.base_url = None
         self.url = None
         self.doi = doi
         self.pdf_url = None
         self.pdf_path = None
-        self.headers = {"User-Agent": get_ua().encode("utf-8")}
+        # requests 期望 header 值为 str，这里确保 UA 是字符串而不是 bytes
+        self.headers = {"User-Agent": str(get_ua())}
         # 10.1175/1520-0493(1997)125<0742:IODAOO>2.0.CO;2.pdf
         # self.fname = doi.replace(r'/', '_') + '.pdf'
         self.fname = re.sub(r'[/<>:"?*|]', "_", doi) + ".pdf"
         self.store_path = Path(store_path)
         self.fpath = self.store_path / self.fname
         self.wrong_record_file = self.store_path / "wrong_record.txt"
-        self.sleep = 5
+        self.sleep = sleep_secs
         self.cookies = None
-        self.check_size = 50
+        self.check_size = max(1, int(min_size_kb))
         self.url_index = 0
-        self.try_times_each_url_max = 3
+        self.try_times_each_url_max = max(1, int(tries_each_url))
         self.try_times = 0
+        self.timeout_html = max(5, int(timeout_html))
+        self.timeout_pdf = max(5, int(timeout_pdf))
+        self.debug = bool(debug)
+
+    # ---------------- 镜像可用性探测 ----------------
+    def _is_mirror_alive(self, base_url: str) -> bool:
+        """
+        仅检测镜像根路径是否可连通（HTTP 200 即认为可用）。
+        不访问具体 DOI，避免被动触发风控；只做连通性筛查。
+        """
+        try:
+            r = requests.get(base_url + "/", headers=self.headers, timeout=8, allow_redirects=True)
+            return 200 <= r.status_code < 400
+        except Exception:
+            return False
+
+    def _ensure_alive_mirrors(self):
+        # 若已经有进程级缓存，直接复用
+        if _Downloader._alive_mirrors_cache is not None:
+            self.url_list = list(_Downloader._alive_mirrors_cache)
+            return
+
+        print(f"[bold cyan]Probing mirrors connectivity (first run)...")
+        alive = []
+        for base in self.url_list:
+            ok = self._is_mirror_alive(base)
+            status = "OK" if ok else "DOWN"
+            print(f"  [{status}] {base}")
+            if ok:
+                alive.append(base)
+        if alive:
+            _Downloader._alive_mirrors_cache = alive
+            self.url_list = alive
+            print(f"[bold cyan]Alive mirrors: {len(alive)}; pruned {len(set(self.url_list)) - len(alive) if self.url_list else 0}.")
+        else:
+            print("[bold yellow]No mirror passed probe; keep original list for fallback attempts.")
+
+    def _extract_pdf_url_from_html(self, html: str) -> str | None:
+        """
+        从 Sci-Hub 页面 HTML 中尽可能稳健地提取 PDF 链接。
+
+        兼容多种模式：
+        - onclick="location.href='...pdf?download=true'"
+        - <iframe id="pdf" src="...pdf?...">
+        - <a ... href="...pdf?...">
+        - 其他出现 .pdf 的 src/href 场景
+
+        返回绝对 URL；若找不到返回 None。
+        """
+        text = html
+
+        # 先尝试常见 onclick 跳转
+        patterns = [
+            # onclick="location.href='...pdf?...'" 或 document.location
+            r"onclick\s*=\s*[\"']\s*(?:document\.)?location\.href\s*=\s*[\"']([^\"']+?\.pdf(?:[?#][^\"']*)?)[\"']",
+            # iframe id="pdf" src="...pdf?..."
+            r"<iframe[^>]+id\s*=\s*[\"']pdf[\"'][^>]+src\s*=\s*[\"']([^\"']+?\.pdf(?:[?#][^\"']*)?)[\"']",
+            # 通用 a 标签 href
+            r"<a[^>]+href\s*=\s*[\"']([^\"']+?\.pdf(?:[?#][^\"']*)?)[\"']",
+            # 通用任意 src/href
+            r"(?:src|href)\s*=\s*[\"']([^\"']+?\.pdf(?:[?#][^\"']*)?)[\"']",
+        ]
+
+        for pat in patterns:
+            m = re.search(pat, text, flags=re.IGNORECASE | re.DOTALL)
+            if m:
+                got_url = m.group(1)
+                # 规范化为绝对 URL
+                if got_url.startswith("//"):
+                    return "https:" + got_url
+                if got_url.startswith("http://") or got_url.startswith("https://"):
+                    return got_url
+                # 其余按相对路径处理
+                return urljoin(self.base_url + "/", got_url.lstrip("/"))
+
+        return None
 
     def get_pdf_url(self):
         print("[bold #E6E6FA]-" * 120)
         print(f"DOI: {self.doi}")
         print(f"Requesting: {self.url}...")
         try:
-            response = requests.get(self.url, headers=self.headers)
+            # 使用较小的超时时间避免长时间阻塞
+            response = requests.get(self.url, headers=self.headers, timeout=self.timeout_html)
             if response.status_code == 200:
                 self.cookies = response.cookies
-                text = response.text.replace("\\", "")
-                # text = text.replace(' ', '')  # It is important to remove the space
-                # print(text)
-                pattern = re.compile(r'onclick = "location.href=\'(.*?\.pdf\?download=true)\'"')
-                match = pattern.search(text)
-                if match:
-                    got_url = match.group(1)
-                    if r"http" not in got_url:
-                        if got_url[:2] == "//":
-                            self.pdf_url = "https:" + got_url
-                        else:
-                            self.pdf_url = self.base_url + got_url
+                text = response.text
+                # 去除转义反斜杠，提升正则匹配成功率
+                text = text.replace("\\", "")
+
+                self.pdf_url = self._extract_pdf_url_from_html(text)
+                if self.pdf_url:
+                    if self.debug:
+                        print(f"Found PDF link: {self.pdf_url}")
                     else:
-                        self.pdf_url = got_url
-                    print(f"URL: {self.pdf_url}")
+                        print(f"Found PDF link (masked): .../{Path(self.pdf_url).name}")
                 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]} does not expose a detectable PDF link (pattern mismatch)."
+                    )
                     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"[bold #AFEEEE]The website {self.url_list[self.url_index]} do not include the PDF file (HTTP error).")
                 self.try_times = self.try_times_each_url_max + 1
         except Exception as e:
             print(f"Failed to retrieve the webpage. Error: {e}")
@@ -178,7 +246,7 @@ 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, timeout=self.timeout_pdf)
                 if response.status_code == 200:
                     with open(self.fpath, "wb") as f:
                         f.write(response.content)
@@ -224,7 +292,22 @@ def _read_txt(file):
     return lines
 
 
-def download5doi(store_path=None, doi_list=None, txt_file=None, excel_file=None, col_name=r"DOI"):
+def download5doi(
+    store_path=None,
+    doi_list=None,
+    txt_file=None,
+    excel_file=None,
+    col_name=r"DOI",
+    *,
+    probe_mirrors: bool = True,
+    min_size_kb: int = 50,
+    timeout_html: int = 15,
+    timeout_pdf: int = 30,
+    tries_each_url: int = 3,
+    sleep_secs: int = 5,
+    force: bool = False,
+    debug: bool = False,
+):
     """
     Description:
         Download PDF files by DOI.
@@ -260,11 +343,152 @@ def download5doi(store_path=None, doi_list=None, txt_file=None, excel_file=None,
         doi_list = _read_txt(txt_file)
     if excel_file:
         doi_list = _read_excel(excel_file, col_name)
-    remove(Path(store_path) / "wrong_record.txt")
+    # 去重并清洗
+    doi_list = [str(x).strip() for x in doi_list if str(x).strip()]
+    doi_list = list(dict.fromkeys(doi_list))  # 保序去重
+
+    # 只有在不是追加下载的场景下再清除 wrong_record
+    if not force:
+        remove(Path(store_path) / "wrong_record.txt")
     print(f"Downloading {len(doi_list)} PDF files...")
     for doi in track(doi_list, description="Downloading..."):
-        download = _Downloader(doi, store_path)
-        download.download_pdf()
+        dl = _Downloader(
+            doi,
+            store_path,
+            min_size_kb=min_size_kb,
+            timeout_html=timeout_html,
+            timeout_pdf=timeout_pdf,
+            sleep_secs=sleep_secs,
+            tries_each_url=tries_each_url,
+            debug=debug,
+        )
+        # 是否进行镜像探测
+        if probe_mirrors:
+            dl._ensure_alive_mirrors()
+        dl.download_pdf()
+
+
+# ------------------------------- 合规替代方案（Open Access 优先） -------------------------------
+def _get_oa_pdf_url_from_unpaywall(doi: str, email: str | None) -> str | None:
+    """
+    通过 Unpaywall 获取可开放访问的 PDF 链接（若存在）。
+    需要提供 email（Unpaywall 要求标识邮件）。
+    返回 PDF URL 或 None。
+    """
+    if not email:
+        print("[bold yellow]Unpaywall 需要 email 参数；请提供 email 以查询 OA 链接。")
+        return None
+    api = f"https://api.unpaywall.org/v2/{doi}?email={email}"
+    try:
+        r = requests.get(api, timeout=15)
+        if r.status_code != 200:
+            print(f"[bold yellow]Unpaywall 查询失败: HTTP {r.status_code}")
+            return None
+        data = r.json()
+        loc = data.get("best_oa_location") or {}
+        url_for_pdf = loc.get("url_for_pdf") or loc.get("url")
+        if url_for_pdf and url_for_pdf.lower().endswith(".pdf"):
+            return url_for_pdf
+        # 有些 OA 链接是落在 landing page，再尝试从记录的所有位置挑选 pdf
+        for k in ("oa_locations", "oa_location"):
+            entries = data.get(k) or []
+            if isinstance(entries, dict):
+                entries = [entries]
+            for e in entries:
+                u = e.get("url_for_pdf") or e.get("url")
+                if u and ".pdf" in u.lower():
+                    return u
+    except Exception as e:
+        print(f"[bold yellow]Unpaywall 查询异常: {e}")
+    return None
+
+
+def _download_pdf_from_url(url: str, dest_path: Path, headers: dict | None = None) -> bool:
+    """
+    给定合法的 PDF 下载 URL，下载保存到 dest_path。
+    返回 True/False 表示是否成功。
+    """
+    headers = headers or {"User-Agent": str(get_ua()), "Accept": "application/pdf"}
+    try:
+        with requests.get(url, headers=headers, stream=True, timeout=30) as r:
+            if r.status_code != 200 or "application/pdf" not in r.headers.get("Content-Type", "").lower():
+                # 仍可能是 PDF（某些服务器未正确设置头），尝试保存但标注提示
+                if r.status_code != 200:
+                    print(f"[bold yellow]下载失败: HTTP {r.status_code}")
+                    return False
+            dest_path.parent.mkdir(parents=True, exist_ok=True)
+            with open(dest_path, "wb") as f:
+                for chunk in r.iter_content(chunk_size=8192):
+                    if chunk:
+                        f.write(chunk)
+        return True
+    except Exception as e:
+        print(f"[bold yellow]下载异常: {e}")
+        return False
+
+
+def download5doi_via_unpaywall(
+    store_path=None,
+    doi_list=None,
+    txt_file=None,
+    excel_file=None,
+    col_name=r"DOI",
+    email: str | None = None,
+):
+    """
+    优先使用 Unpaywall 获取开放访问（OA）的 PDF 并下载，避免非合规站点。
+
+    参数：
+        store_path: 保存目录
+        doi_list/txt_file/excel_file/col_name: 同 download5doi
+        email: 用于访问 Unpaywall API 的邮箱（必填，否则无法查询）
+    """
+    if not store_path:
+        store_path = Path.cwd()
+    else:
+        store_path = Path(str(store_path))
+    store_path.mkdir(parents=True, exist_ok=True)
+
+    if doi_list:
+        doi_list = ensure_list(doi_list)
+    if txt_file:
+        doi_list = _read_txt(txt_file)
+    if excel_file:
+        doi_list = _read_excel(excel_file, col_name)
+
+    if not doi_list:
+        print("[bold yellow]未提供 DOI 列表。")
+        return
+
+    print(f"[bold cyan]通过 Unpaywall 尝试下载 {len(doi_list)} 篇 OA PDF...")
+    ok, miss = 0, 0
+    for doi in track(doi_list, description="OA downloading..."):
+        # 规范化文件名
+        fname = re.sub(r'[/<>:"?*|]', "_", str(doi)) + ".pdf"
+        dest = store_path / fname
+        if dest.exists() and _get_file_size(dest, unit="KB") > 10:
+            ok += 1
+            continue
+
+        pdf_url = _get_oa_pdf_url_from_unpaywall(str(doi), email=email)
+        if not pdf_url:
+            miss += 1
+            print(f"[bold yellow]未找到 OA PDF: {doi}")
+            continue
+
+        if _download_pdf_from_url(pdf_url, dest):
+            size_kb = _get_file_size(dest, unit="KB")
+            if isinstance(size_kb, (int, float)) and size_kb < 10:
+                dest.unlink(missing_ok=True)
+                miss += 1
+                print(f"[bold yellow]文件过小，疑似异常，已删除: {dest}")
+            else:
+                ok += 1
+                print(f"[bold green]已下载: {dest}")
+        else:
+            miss += 1
+
+    print(f"[bold]完成。成功 {ok} 篇，未获取 {miss} 篇（可能无 OA 版本或需机构访问）。")
 
 
 if __name__ == "__main__":

oafuncs/oa_file.py

@@ -9,13 +9,14 @@ from rich import print
 __all__ = ["find_file", "link_file", "copy_file", "rename_file", "move_file", "clear_folder", "remove_empty_folder", "remove", "file_size", "mean_size", "make_dir", "replace_content"]
 
 
-def find_file(parent_dir: Union[str, os.PathLike], file_pattern: str, return_mode: str = "path") -> List[str]:
+def find_file(parent_dir: Union[str, os.PathLike], file_pattern: str, return_mode: str = "path", deep_find: bool = False) -> List[str]:
     """Finds files matching a specified pattern.
 
     Args:
         parent_dir: The parent directory where to search for files
         file_pattern: The file name pattern to search for
         return_mode: Return mode, 'path' to return full file paths, 'file' to return only file names. Defaults to 'path'
+        deep_find: Whether to search recursively in subdirectories. Defaults to False
 
     Returns:
         A list of file paths or file names if files are found, otherwise an empty list
@@ -24,9 +25,12 @@ def find_file(parent_dir: Union[str, os.PathLike], file_pattern: str, return_mod
     def natural_sort_key(s: str) -> List[Union[int, str]]:
         """Generate a key for natural sorting."""
         return [int(text) if text.isdigit() else text.lower() for text in re.split("([0-9]+)", s)]
-
-    search_pattern = os.path.join(str(parent_dir), file_pattern)
-    matched_files = glob.glob(search_pattern)
+    
+    if deep_find:
+        search_pattern = os.path.join(str(parent_dir), "**", file_pattern)
+    else:
+        search_pattern = os.path.join(str(parent_dir), file_pattern)
+    matched_files = glob.glob(search_pattern, recursive=deep_find)
 
     if not matched_files:
         return []

oafuncs/oa_geo.py

@@ -135,14 +135,64 @@ def mask_land_ocean(
     """
     mask = _land_sea_mask(lon, lat, keep)
 
-    # 用 apply_ufunc 自动对齐并广播掩膜
-    return xr.apply_ufunc(
-        lambda x, m: x.where(m),
-        data,
-        xr.DataArray(mask, dims=("lat", "lon")),
-        dask="parallelized",
-        keep_attrs=True,
-    )
+    # 将布尔掩膜转换为 xarray.DataArray
+    mask_da = xr.DataArray(mask, dims=("lat", "lon"))
+
+    # 如果输入已经是 xarray 对象，直接使用 where
+    if isinstance(data, (xr.DataArray, xr.Dataset)):
+        return data.where(mask_da)
+
+    # 如果输入是 numpy 数组，则假定最后两个维度是 (lat, lon)
+    if isinstance(data, np.ndarray):
+        arr = data
+        if arr.ndim < 2:
+            raise ValueError("numpy array 数据至少应包含 2 个维度 (lat, lon)")
+
+        if arr.ndim == 2:
+            lat_arr = np.asarray(lat)
+            lon_arr = np.asarray(lon)
+            # 支持 lat/lon 为 1D 或 2D
+            if lat_arr.ndim == 1 and lon_arr.ndim == 1:
+                da = xr.DataArray(arr, dims=("lat", "lon"), coords={"lat": lat_arr, "lon": lon_arr})
+            elif lat_arr.ndim == 2 and lon_arr.ndim == 2:
+                if lat_arr.shape != arr.shape or lon_arr.shape != arr.shape:
+                    raise ValueError("提供的二维经纬度数组形状必须匹配数据的 (lat, lon) 维度")
+                da = xr.DataArray(arr, dims=("lat", "lon"), coords={"lat": (("lat", "lon"), lat_arr), "lon": (("lat", "lon"), lon_arr)})
+            else:
+                raise ValueError("lat/lon 必须同时为 1D 或同时为 2D")
+        else:
+            # 为前面的维度生成占位名称，例如 dim_0, dim_1, ...
+            leading_dims = [f"dim_{i}" for i in range(arr.ndim - 2)]
+            dims = leading_dims + ["lat", "lon"]
+            coords = {f"dim_{i}": np.arange(arr.shape[i]) for i in range(arr.ndim - 2)}
+
+            lat_arr = np.asarray(lat)
+            lon_arr = np.asarray(lon)
+            # 如果 lat/lon 为 1D
+            if lat_arr.ndim == 1 and lon_arr.ndim == 1:
+                if lat_arr.shape[0] != arr.shape[-2] or lon_arr.shape[0] != arr.shape[-1]:
+                    raise ValueError("一维 lat/lon 长度必须匹配数据的最后两个维度")
+                coords.update({"lat": lat_arr, "lon": lon_arr})
+            # 如果 lat/lon 为 2D，要求其形状与数据最后两个维度一致
+            elif lat_arr.ndim == 2 and lon_arr.ndim == 2:
+                if lat_arr.shape != (arr.shape[-2], arr.shape[-1]) or lon_arr.shape != (arr.shape[-2], arr.shape[-1]):
+                    raise ValueError("二维 lat/lon 的形状必须匹配数据的最后两个维度")
+                coords.update({"lat": (("lat", "lon"), lat_arr), "lon": (("lat", "lon"), lon_arr)})
+            else:
+                raise ValueError("lat/lon 必须同时为 1D 或同时为 2D")
+
+            da = xr.DataArray(arr, dims=dims, coords=coords)
+
+        masked = da.where(mask_da)
+        # 返回与输入相同的类型：numpy -> numpy
+        return masked.values
+
+    # 其他类型尝试转换为 DataArray
+    try:
+        da = xr.DataArray(data)
+        return da.where(mask_da)
+    except Exception:
+        raise TypeError("data must be xr.DataArray, xr.Dataset, or numpy.ndarray")
 
 if __name__ == "__main__":
     pass

oafuncs/oa_linux.py

@@ -0,0 +1,108 @@
+from rich import print
+import time
+import os
+
+__all__ = ["os_command", "get_queue_node", "query_queue", "running_jobs", "submit_job"]
+
+
+# 负责执行命令并返回输出
+def os_command(cmd):
+    import subprocess
+    print(f'🔍 执行命令: {cmd}')
+    result = subprocess.run(
+        cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True
+    )
+    # 打印错误信息（若有，方便排查问题）
+    if result.stderr:
+        print(f'❌ 错误输出: {result.stderr.strip()}')
+    # 检查命令是否执行成功（非0为失败）
+    if result.returncode != 0:
+        print(f'❌ 命令执行失败，退出码: {result.returncode}')
+        return None
+    return result.stdout
+
+# 返回“队列名:节点数”的字典
+def get_queue_node():
+    import re
+    # 执行 sinfo | grep "idle" 获取空闲队列数据
+    cmd = 'sinfo | grep "idle"'
+    output = os_command(cmd)
+    if not output:  # 命令执行失败或无输出，返回空字典
+        return {}
+    
+    # 初始化结果字典：键=队列名，值=节点数
+    queue_node_dict = {}
+    # 按行解析命令输出
+    for line in output.strip().split('\n'):
+        line = line.strip()
+        if not line:  # 跳过空行
+            continue
+        
+        # 正则匹配：仅捕获“队列名”（第1组）和“节点数”（第2组）
+        # 末尾用 .* 忽略节点列表，不影响匹配
+        pattern = r"^(\S+)\s+\S+\s+\S+\s+(\d+)\s+idle\s+.*$"
+        match = re.match(pattern, line)
+        
+        if match:
+            queue_name = match.group(1)    # 提取队列名作为字典的键
+            node_count = int(match.group(2))# 提取节点数作为字典的值（转为整数）
+            queue_node_dict[queue_name] = node_count  # 存入字典
+    
+    return queue_node_dict
+
+def query_queue(need_node=1, queue_list =['dcu','bigmem','cpu_parallel','cpu_single']):
+    queue_dict = get_queue_node()
+    hs = None
+    for my_queue in queue_list:
+        if my_queue in queue_dict and queue_dict[my_queue] >= need_node:
+            # slurm_file = f'../run.slurm.{my_queue}'
+            hs = my_queue
+            break
+    return hs
+
+def running_jobs():
+    # 通过qstat判断任务状态，是否还在进行中
+    # status = os.popen('qstat').read()
+    status = os.popen('squeue').read()
+    Jobs = status.split('\n')[1:]
+    ids = [job.split()[0] for job in Jobs if job != '']
+    return ids
+
+def submit_job(working_dir, script_tmp='run.slurm', script_run='run.slurm', need_node=1, queue_tmp='<queue_name>', queue_list=['dcu', 'bigmem', 'cpu_parallel', 'cpu_single'], max_job=38):
+    from .oa_file import replace_content
+    import datetime
+    os.chdir(working_dir)
+    print(f'切换工作目录到: {working_dir}')
+    while True:
+        running_job = running_jobs()
+        if not running_job or len(running_job) < max_job:
+            queue = query_queue(need_node=need_node, queue_list=queue_list)
+            if queue:
+                replace_content(script_tmp, {f'{queue_tmp}': f"{queue}"}, False, f'{working_dir}', script_run)
+                print(f'找到计算资源，提交任务，队列：{queue}')
+                print(f'Time: {datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")}')
+                content_sub = os_command(f"sbatch {script_run}")
+                # 避免在 None 上使用 'in' 导致 TypeError：os_command 在失败时会返回 None
+                if not content_sub:
+                    print('提交任务命令没有返回输出或返回了错误，等待30秒后重试！')
+                    time.sleep(30)
+                else:
+                    content_sub_lower = content_sub.lower()
+                    if 'error' in content_sub_lower or 'failed' in content_sub_lower:
+                        print('提交任务时出现错误（从输出检测到 error/failed），等待30秒后重试！')
+                        print(f'命令输出: {content_sub.strip()}')
+                        time.sleep(30)
+                    else:
+                        print(f'提交任务成功，{content_sub.strip()}')
+                        break
+            else:
+                print('没有足够的计算资源，等待30秒后重试！')
+                time.sleep(30)
+        else:
+            print(f'当前系统任务数：{len(running_job)}，等待60秒后重试！')
+            time.sleep(60)
+    print(f'等待10秒后，继续检查任务状态！')
+    time.sleep(10)
+
+if __name__ == "__main__":
+    pass

{oafuncs-0.0.98.44.dist-info → oafuncs-0.0.98.46.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: oafuncs
-Version: 0.0.98.44
+Version: 0.0.98.46
 Summary: Oceanic and Atmospheric Functions
 Home-page: https://github.com/Industry-Pays/OAFuncs
 Author: Kun Liu
@@ -187,4 +187,4 @@ query()
 <img title="OAFuncs" src="https://raw.githubusercontent.com/Industry-Pays/OAFuncs/main/oafuncs/_data/oafuncs.png" alt="OAFuncs">
 
 ## Wiki
-更多内容，查看[wiki](https://opendeep.wiki/Industry-Pays/OAFuncs/introduction)
+更多内容，查看[wiki_old](https://opendeep.wiki/Industry-Pays/OAFuncs/introduction) or [wiki_new](https://deepwiki.com/Industry-Pays/OAFuncs)

{oafuncs-0.0.98.44.dist-info → oafuncs-0.0.98.46.dist-info}/RECORD

@@ -1,11 +1,12 @@
-oafuncs/__init__.py,sha256=7630YgWbWGClu4Us1H2SAq-_eh9WzFHGxXkIXMcxRu0,1542
-oafuncs/oa_cmap.py,sha256=JwZMJ36uNwiCnzXqEtH2_PpeLtEaRaXP9YeGSl0PJSU,13886
+oafuncs/__init__.py,sha256=G523BFVPxmODwq8j_88NYEiKbCzdQ3jfy51cmLeh7kM,1630
+oafuncs/oa_cmap.py,sha256=Mru5XvvBTfYNq8xjsBAGWppI7RGKzSh94glxP2SXomc,14221
 oafuncs/oa_data.py,sha256=CG2YHY_R6MFrPw3UznT4T8BE8yXdgBMnmdUAEdh9GAo,6506
 oafuncs/oa_date.py,sha256=aU2wVIWXyWoRiSQ9dg8sHvShFTxw86RrgbV3Q6tDjD4,6841
 oafuncs/oa_draw.py,sha256=zal0Y3RPpN0TCGN4Gw9qLtjQdT6V0ZqpSUBFVOPL0x4,13952
-oafuncs/oa_file.py,sha256=l9HTAK8iC1Bp_K7Mk3AX1UKuTFZZ-2yq5Hq71hnigbo,17299
-oafuncs/oa_geo.py,sha256=BWkvV6nW_c-UKqbgaoy4U1YQYUMzAQOJlK--XppNIms,4371
+oafuncs/oa_file.py,sha256=j9NOjxPOeAJsD5Zk4ODmFdVSSgr1CHVPvM1IHXy9RQA,17546
+oafuncs/oa_geo.py,sha256=UbzvUqgT2QP_9B7XSJRL1HDmGu0HnLC5nSP6ZrA5WH4,7177
 oafuncs/oa_help.py,sha256=0J5VaZX-cB0c090KxgmktQJBc0o00FsY-4wB8l5y00k,4178
+oafuncs/oa_linux.py,sha256=eijpxTopzL3GpE5AIzis9vdrbm-A7QBeQesA-divBjE,4627
 oafuncs/oa_nc.py,sha256=j501NlTuvrDIwNLXbMfE7nPPXdbbL7u9PGDj2l5AtnI,16277
 oafuncs/oa_python.py,sha256=xYMQnM0cGq9xUCtcoMpnN0LG5Rc_s94tai5nC6CNJ3E,4831
 oafuncs/oa_tool.py,sha256=VHx15VqpbzNlVXh0-3nJqcDgLVaECMD1FvxJ_CrV39E,8046
@@ -13,7 +14,7 @@ oafuncs/_data/hycom.png,sha256=MadKs6Gyj5n9-TOu7L4atQfTXtF9dvN9w-tdU9IfygI,10945
 oafuncs/_data/oafuncs.png,sha256=o3VD7wm-kwDea5E98JqxXl04_78cBX7VcdUt7uQXGiU,3679898
 oafuncs/_script/cprogressbar.py,sha256=BZi3MzF4q2Yl6fdZcLnW8MdpgpLeldI5NvnWMr-ZS94,16023
 oafuncs/_script/data_interp.py,sha256=gr1coA2N1mxzS4iv6S0C4lZpEQbuuHHNW-08RrhgPAA,4774
-oafuncs/_script/email.py,sha256=l5xDgdVj8O5V0J2SwjsHKdUuxOH2jZvwdMO_P0dImHU,2684
+oafuncs/_script/email.py,sha256=57jhRflm5QsyIshGMqtlfC6qn3b86GyiL4RQxdCOgxU,2702
 oafuncs/_script/netcdf_merge.py,sha256=tM9ePqLiEsE7eIsNM5XjEYeXwxjYOdNz5ejnEuI7xKw,6066
 oafuncs/_script/netcdf_modify.py,sha256=XDlAEToe_lwfAetkBSENqU5df-wnH7MGuxNTjG1gwHY,4178
 oafuncs/_script/netcdf_write.py,sha256=EDNycnhlrW1c6zcpmpObQeszDRX_lRxjTL-j0G4HqjI,17420
@@ -25,7 +26,7 @@ oafuncs/oa_down/User_Agent-list.txt,sha256=pHaMlElMvZ8TG4vf4BqkZYKqe0JIGkr4kCN0l
 oafuncs/oa_down/__init__.py,sha256=IT6oTqaxuV_mC6AwBut0HtkmnVtEu1MyX0x0oS7TKoA,218
 oafuncs/oa_down/hycom_3hourly.py,sha256=dFXSC_5o-Dic616KrLXir4tEHvCiZt8vGKPEYpXFMmA,57356
 oafuncs/oa_down/idm.py,sha256=vAhRjt_Sb-rKhzFShmSf29QcFTqsHpHXCvTSD1uSXyQ,1455
-oafuncs/oa_down/literature.py,sha256=7Qy5OphcjdRwY2uZ5hmmgK36U_QtVmEUSW0vQaxihC8,10960
+oafuncs/oa_down/literature.py,sha256=umz8bqYoVJiFkFviK970iOL7sfwbVWuqHPgRs3a199I,19806
 oafuncs/oa_down/read_proxy.py,sha256=HQpr-Mwn0Z8ICAuf63NUUY9p05E_uNWyWmOK46-73Ec,2866
 oafuncs/oa_down/test_ua.py,sha256=l8MCD6yU2W75zRPTDKUZTJhCWNF9lfk-MiSFqAqKH1M,1398
 oafuncs/oa_down/user_agent.py,sha256=LCVQUA60ukUqeJXgLktDHB2sh-ngk7AiX4sKj8w-X4A,416
@@ -38,8 +39,8 @@ oafuncs/oa_sign/__init__.py,sha256=JSx1fcWpmNhQBvX_Bmq3xysfSkkFMrjbJASxV_V6aqE,1
 oafuncs/oa_sign/meteorological.py,sha256=3MSjy7HTcvz2zsITkjUMr_0Y027Gas1LFE9pk99990k,6110
 oafuncs/oa_sign/ocean.py,sha256=3uYEzaq-27yVy23IQoqy-clhWu1I_fhPFBAQyT-OF4M,5562
 oafuncs/oa_sign/scientific.py,sha256=moIl2MEY4uitbXoD596JmXookXGQtQsS-8_1NBBTx84,4689
-oafuncs-0.0.98.44.dist-info/licenses/LICENSE.txt,sha256=rMtLpVg8sKiSlwClfR9w_Dd_5WubTQgoOzE2PDFxzs4,1074
-oafuncs-0.0.98.44.dist-info/METADATA,sha256=yWxBsUGF1rlJBn42pXZyCUrgqhXWpyqc-l_CTyBEnSk,4384
-oafuncs-0.0.98.44.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-oafuncs-0.0.98.44.dist-info/top_level.txt,sha256=bgC35QkXbN4EmPHEveg_xGIZ5i9NNPYWqtJqaKqTPsQ,8
-oafuncs-0.0.98.44.dist-info/RECORD,,
+oafuncs-0.0.98.46.dist-info/licenses/LICENSE.txt,sha256=rMtLpVg8sKiSlwClfR9w_Dd_5WubTQgoOzE2PDFxzs4,1074
+oafuncs-0.0.98.46.dist-info/METADATA,sha256=ZeQYycohu3zboTLafN-CHlEwkhmixvmazKaLAADhFpI,4446
+oafuncs-0.0.98.46.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+oafuncs-0.0.98.46.dist-info/top_level.txt,sha256=bgC35QkXbN4EmPHEveg_xGIZ5i9NNPYWqtJqaKqTPsQ,8
+oafuncs-0.0.98.46.dist-info/RECORD,,