upplib 3.3.1__py3-none-any.whl → 3.3.9__py3-none-any.whl

upplib/__init__.py

@@ -3,12 +3,16 @@ from upplib.common_package import *
 
 # 引入自定义的全部的包
 from upplib.index import *
+from upplib.datetime_function import *
 # 引入通用的工具包
 from upplib.util import *
 
 # 有关文件操作类的包
-from upplib.file import *
-from upplib.file_text import *
+from upplib.file_function import *
+from upplib.file_to_text import *
+from upplib.text_to_file import *
+
+from upplib.clean_up_msg import *
 
 from upplib.config_data import *
 

upplib/config_data.py

@@ -1,6 +1,6 @@
 from upplib import *
 from upplib.common_package import *
-from upplib.file import *
+from upplib.file_function import *
 
 __CONFIG_PATH = '.upp.config'
 

upplib/datetime_function.py

@@ -0,0 +1,256 @@
+from upplib import *
+from datetime import datetime, timezone, timedelta
+from typing import Any, Optional, Union
+from upplib.common_package import *
+
+
+def get_tz(tz_info: Union[str, timezone]) -> timezone:
+    """将时区信息转换为timezone对象"""
+    if isinstance(tz_info, timezone):
+        return tz_info
+    if not isinstance(tz_info, str):
+        raise ValueError(f"无效的时区格式: {tz_info}")
+    tz_str = tz_info.upper()
+    if tz_str == "UTC":
+        return timezone.utc
+    # 处理纯偏移格式，如+07:00、-05:30
+    offset_match = re.match(r"^([+-])(\d{1,2}):(\d{2})$", tz_str)
+    if offset_match:
+        sign = offset_match.group(1)
+        hours = int(offset_match.group(2))
+        minutes = int(offset_match.group(3))
+        # 计算总偏移小时数
+        total_hours = hours + minutes / 60
+        if sign == "-":
+            total_hours = -total_hours
+        return timezone(timedelta(hours=total_hours))
+    # 处理GMT格式，如GMT+08:00或GMT-5
+    gmt_match = re.match(r"GMT([+-]\d{1,2})(:\d{2})?$", tz_str)
+    if gmt_match:
+        hours = int(gmt_match.group(1))
+        return timezone(timedelta(hours=hours))
+    # 处理UTC格式，如UTC+8或UTC-05:00
+    utc_match = re.match(r"UTC([+-]\d{1,2})(:\d{2})?$", tz_str)
+    if utc_match:
+        hours = int(utc_match.group(1))
+        return timezone(timedelta(hours=hours))
+    raise ValueError(f"不支持的时区格式: {tz_info}")
+
+
+def to_datetime(
+        s: Any = None,
+        pattern: str = None,
+        r_str: bool = False,
+        error_is_none: bool = False,
+        tz: Optional[Union[str, timezone]] = None,
+        default_tz: Union[str, timezone] = None
+) -> Union[datetime, str, None]:
+    """
+    将字符串或时间戳转换为 datetime 对象，支持时区处理。
+    error_is_none : 当发生错误的时候，是否返回 None
+    """
+    # 默认时区为 +08:00
+    default_tz = default_tz or '+08:00'
+
+    use_default_time = False
+    if s is None or s == '':
+        dt = datetime.now(get_tz(default_tz))
+    else:
+        s = str(s).strip()
+        dt = None
+
+        # 1. 尝试解析时间戳
+        if re.match(r"^\d{1,19}$", s):
+            timestamp = int(s)
+            if len(s) > 10:  # 毫秒级时间戳
+                timestamp = timestamp // 1000
+            # 先转为无时区的 datetime
+            dt = datetime.fromtimestamp(timestamp)
+            dt = dt.replace(tzinfo=get_tz(default_tz))
+
+        # 2. 尝试解析 ISO 8601 格式
+        if dt is None:
+            try:
+                dt = datetime.fromisoformat(s)
+            except ValueError:
+                pass
+
+        # 3. 尝试解析带GMT时区的格式，如'2025/09/16 17:32:17.896 GMT+08:00'
+        if dt is None:
+            gmt_pattern = r"^(\d{4})[/-](\d{2})[/-](\d{2}) (\d{2}):(\d{2}):(\d{2})(\.\d+)? (GMT[+-]\d{1,2}(:\d{2})?)$"
+            match = re.match(gmt_pattern, s)
+            if match:
+                try:
+                    # 提取日期时间部分
+                    year, month, day = map(int, match.group(1, 2, 3))
+                    hour, minute, second = map(int, match.group(4, 5, 6))
+                    microsecond = 0
+                    if match.group(7):
+                        # 处理毫秒/微秒部分
+                        microsecond = int(float(match.group(7)) * 1e6)
+
+                    # 创建datetime对象
+                    dt = datetime(year, month, day, hour, minute, second, microsecond)
+
+                    # 应用时区
+                    tz_info = get_tz(match.group(8))
+                    dt = dt.replace(tzinfo=tz_info)
+                except ValueError:
+                    pass
+
+        # 4. 使用指定的pattern解析
+        if dt is None and pattern is not None:
+            try:
+                # 移除可能的毫秒部分
+                s_without_ms = s.split('.')[0]
+                dt = datetime.strptime(s_without_ms, pattern)
+            except ValueError:
+                pass
+
+        # 5. 尝试解析YYYY-MM-DD HH:MM:SS或YYYY/MM/DD HH:MM:SS格式
+        if dt is None:
+            # 尝试处理不带时区的格式
+            formats = ["%Y-%m-%d %H:%M:%S", "%Y/%m/%d %H:%M:%S"]
+            for fmt in formats:
+                try:
+                    # 移除可能的毫秒和时区部分
+                    s_clean = re.sub(r"(\.\d+)|[TZ]|GMT.*$", " ", s).strip()
+                    dt = datetime.strptime(s_clean, fmt)
+                    break
+                except ValueError:
+                    continue
+
+            if dt is None:
+                use_default_time = True
+                dt = datetime.now()
+
+        # 确保无时区时附加默认时区
+        if dt.tzinfo is None:
+            dt = dt.replace(tzinfo=get_tz(default_tz))
+
+    # 转换为目标时区
+    if tz is not None:
+        dt = dt.astimezone(get_tz(tz))
+
+    if error_is_none and use_default_time:
+        return None
+
+    return dt.isoformat() if r_str else dt
+
+
+# 将字符串 s 转化成 datetime, 然后再次转化成 str
+def to_datetime_str(s: Any = None,
+                    pattern: str = None,
+                    pattern_str: str = None,
+                    tz: Optional[Union[str, timezone]] = None,
+                    default_tz: Union[str, timezone] = None) -> datetime | str:
+    """
+    将 s 先转成 datetime, 然后再转成字符串
+
+    :param s: 输入值（可以是字符串或其他类型）
+    """
+    r_s = to_datetime(s, pattern=pattern, tz=tz, r_str=False, default_tz=default_tz)
+    if pattern_str is None:
+        iso_str = r_s.isoformat()
+        if '.' not in iso_str:
+            # '2025-10-09T10:52:41+08:00'
+            return iso_str
+        parts = iso_str.split('.')
+        time_zone_part = parts[1]
+        time_zone_str = tz
+        millisecond_part = time_zone_part[:3]
+        for a in ['+', '-']:
+            if a in time_zone_part:
+                time_zone_str = a + time_zone_part.split(a)[-1]
+        return parts[0] + '.' + millisecond_part + time_zone_str
+    else:
+        return r_s.strftime(pattern_str)
+
+
+def to_datetime_format(s: Any = None,
+                       pattern_str: str = "%Y-%m-%d %H:%M:%S") -> datetime | str:
+    return to_datetime_str(s, pattern=None, pattern_str=pattern_str, tz=None)
+
+
+def to_datetime_format__6(s: Any = None,
+                          pattern_str: str = "%Y-%m-%d %H:%M:%S") -> datetime | str:
+    return to_datetime_str(s, pattern=None, pattern_str=pattern_str, tz='-06:00')
+
+
+def to_datetime_format_7(s: Any = None,
+                         pattern_str: str = "%Y-%m-%d %H:%M:%S") -> datetime | str:
+    return to_datetime_str(s, pattern=None, pattern_str=pattern_str, tz='+07:00')
+
+
+def to_datetime_format_8(s: Any = None,
+                         pattern_str: str = "%Y-%m-%d %H:%M:%S") -> datetime | str:
+    return to_datetime_str(s, pattern=None, pattern_str=pattern_str, tz='+08:00')
+
+
+# 时间加减
+def to_datetime_add(s: Any = None,
+                    days: int = 0,
+                    seconds: int = 0,
+                    microseconds: int = 0,
+                    milliseconds: int = 0,
+                    minutes: int = 0,
+                    hours: int = 0,
+                    weeks: int = 0) -> datetime:
+    return to_datetime(s) + timedelta(days=days, seconds=seconds, microseconds=microseconds,
+                                      milliseconds=milliseconds, minutes=minutes, hours=hours,
+                                      weeks=weeks)
+
+
+# 将字符串 s 转化成 date 例如: 2021-02-03
+def to_date(s: Any = None) -> str:
+    return str(to_datetime(s))[0:10]
+
+
+# 将字符串 s 转化成 date 例如: 20210203
+def to_date_number(s: Any = None) -> str:
+    return str(to_datetime(s))[0:10].replace('-', '')
+
+
+def get_timestamp(s: Any = None) -> int:
+    """获取 Unix 秒级时间戳"""
+    return int(to_datetime(s).timestamp())
+
+
+def get_datetime_number_str(s: Any = None,
+                            length: int = None,
+                            remove_dz: bool = True,
+                            ) -> str:
+    """获取 datetime , 然后转成字符串, 然后, 只保留数字
+        Args:
+            s: 输入值，可以是任何类型，如果是None则使用当前时间
+            length: 可选参数，指定返回字符串的长度
+            remove_dz: 是否去掉时区
+        Returns:
+            str: 只包含数字的字符串
+        """
+    s1 = to_datetime(s)
+    digits_only = re.sub(r'\D', '', str(s1))
+    # 如果指定了长度，取最后length位
+    if length is not None and length > 0:
+        return digits_only[-length:] if len(digits_only) > length else digits_only
+    if len(digits_only) > 4 and remove_dz:
+        digits_only = digits_only[:-4]
+    return digits_only
+
+
+def get_timestamp_ms(s: Any = None) -> int:
+    """获取 Unix 毫秒级时间戳"""
+    return int(to_datetime(s).timestamp() * 1000)
+
+
+# 时间加减
+def to_date_add(s: Any = None,
+                days: int = 0,
+                seconds: int = 0,
+                microseconds: int = 0,
+                milliseconds: int = 0,
+                minutes: int = 0,
+                hours: int = 0,
+                weeks: int = 0) -> str:
+    return str(to_datetime_add(s=s, days=days, seconds=seconds, microseconds=microseconds,
+                               milliseconds=milliseconds, minutes=minutes, hours=hours, weeks=weeks))[0:10]

upplib/{file.py → file_function.py}

@@ -38,6 +38,38 @@ def get_file(file_path: str = None,
     return r_list
 
 
+def get_latest_file(file_path: str = None,
+                    path_startswith: str = None,
+                    startswith: str = None,
+                    path_contain: str = None,
+                    contain: str = None,
+                    path_endswith: str = None,
+                    endswith: str = None,
+                    full_path: bool = None) -> None | tuple[str, str] | str:
+    """
+    按照文件名字排序，获得最新的一个文件
+    full_path: 是否返回完整的路径
+    """
+    html_list = get_file(file_path=file_path,
+                         path_startswith=path_startswith,
+                         startswith=startswith,
+                         path_contain=path_contain,
+                         contain=contain,
+                         sort_asc=False,
+                         path_endswith=path_endswith,
+                         endswith=endswith)
+    r1 = html_list[-1] if len(html_list) > 0 else None
+    if r1 is None:
+        return None
+    r1_short = r1
+    file_sep = '\\' if is_win() else '/'
+    if file_sep in r1:
+        r1_short = r1.split(file_sep)[-1]
+    if full_path is None:
+        return r1_short, r1
+    return r1 if full_path else r1_short
+
+
 def get_file_folder(file_name_one: str = None) -> str:
     """
     返回这个文件的文件夹路径
@@ -213,6 +245,22 @@ def find_file_by_content(file_path: str = '',
             to_log(one_file, e)
             continue
 
+
+def check_file(file_name: str = None) -> None:
+    r"""
+    检查文件夹是否存在,不存在,就创建新的
+    支持多级目录 , 例如: C:\Users\yangpu\Desktop\study\a\b\c\d\e\f
+    """
+    if file_name is None or file_name == '':
+        return
+    file_sep = '\\' if is_win() else '/'
+    f_n = file_name.split(file_sep)
+    for i in range(1, len(f_n) + 1):
+        # C:\Users\yangpu\Desktop\study\p.t
+        p_n = file_sep.join(f_n[0:i])
+        if p_n and not os.path.exists(p_n):
+            os.mkdir(p_n)
+
 # print(get_file_data_line(r'D:\notepad_file\202306\a.txt', 'payout', from_last=False))
 
 # file_all = get_file(r'C:\Users\yang\Desktop\ticket\no.use', path_contain='03')