MeUtils 2024.3.4.13.4.45__py3-none-any.whl → 2025.1.16.17.15.52__py3-none-any.whl

meutils/str_utils/regular_expression.py

@@ -6,16 +6,41 @@
 # @Author       : yuanjie
 # @WeChat       : meutils
 # @Software     : PyCharm
-# @Description  : 
+# @Description  :
+import json
 
 from meutils.pipe import *
+from urllib.parse import unquote, unquote_plus
 
 zh = re.compile('[a-zA-Z\u4e00-\u9fa5]+')  # 中文 + 字母
 nozh = re.compile('[^a-zA-Z\u4e00-\u9fa5]+')  # 中文 + 字母
 
+HTML_PARSER = re.compile(r'```html(.*?)```', re.DOTALL)
+
 
 # re.sub(r'=(.+)', r'=123','s=xxxxx')
 
+@lru_cache()
+def remove_date_suffix(filename):
+    """
+    # 测试示例
+    filenames = [
+        "claude-3-5-haiku-20241022",
+        "o1-mini-2024-09-12",
+        "gpt-3.5-turbo-0125"
+    ]
+
+    # 输出结果
+    for fname in filenames:
+        print(remove_date_suffix(fname))
+    :param filename:
+    :return:
+    """
+    # 匹配日期格式（YYYYMMDD 或 YYYY-MM-DD）
+    pattern = r'(-\d{8}|-\d{4}-\d{2}-\d{2}|-\d+)$'
+    # 使用正则表达式替换日期后缀
+    return re.sub(pattern, '', filename)
+
 
 def get_parse_and_index(text, pattern):
     """
@@ -33,17 +58,58 @@ def get_parse_and_index(text, pattern):
         yield match.start(), match.end(), match.group()
 
 
-@lru_cache
-def parse_url(text: str):
+@lru_cache()
+def parse_url(text: str, for_image=False):
     # url_pattern = r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'
     url_pattern = r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+|#]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'
-    # url_pattern = 'https?://(?:[-\w.]|(?:%[\da-fA-F]{2}))+'
-    url = re.findall(url_pattern, str(text))
 
-    return url
+    # url_pattern = r"((https?|ftp|www\\.)?:\\/\\/)?([a-zA-Z0-9.-]+\\.[a-zA-Z]{2,})(:[0-9]+)?(\\/[^\\s]*)?"
+
+    if for_image:
+        text = unquote_plus(text)
+        # suffix = [
+        #     ".jpg",
+        #     ".jpeg",
+        #     ".png",
+        #     ".gif",
+        #     ".bmp",
+        #     ".tiff",
+        #     ".psd",
+        #     ".ai",
+        #     ".svg",
+        #     ".webp",
+        #     ".ico",
+        #     ".raw",
+        #     ".dng"
+        # ]
+        # url_pattern = r'https?://[\w\-\.]+/\S+\.(?:png|jpg|jpeg|gif)'
+        url_pattern = r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[#]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+\.(?:jpg|jpeg|png|gif|svg|webp)'
+
+    urls = re.findall(url_pattern, text)
+
+    valid_urls = []
+    for url in urls:
+        url = url.strip(r"\n")
+        valid_urls.append(url)
+
+    return valid_urls
+
+
+def parse_url_from_json():
+    pass
 
 
 if __name__ == '__main__':
+    # from urllib.parse import urlparse
+    #
+    #
+    # def is_valid_url(url):
+    #     try:
+    #         result = urlparse(url)
+    #         return all([result.scheme, result.netloc])
+    #     except:
+    #         return False
+
     text = """7个正规url
     这是一段包含URL的文本，https://www.google.com 是一个URL，另一个URL是http://www.baidu.com
     解读这个文本https://www.url1.com
@@ -51,12 +117,38 @@ if __name__ == '__main__':
     http://www.url2.com 解读这个文本
 
     https://www.url2.com解读这个文本
-    
+
     总结 waptianqi.2345.com/wea_history/58238.html
-    
+
     总结 https://waptianqi.2345.com/wea_history/58238.htm
+    解释下这张照片 https://img-home.csdnimg.cn/images/20201124032511.png
+        解释下这张https://img-home.csdnimg.cn/images/x.png
+
+        img-home.csdnimg.cn/images/20201124032511.png
+
+
+    https://oss.ffire.cc/files/百炼系列手机产品介绍.docx
+    
+    https://mj101-1317487292.cos.ap-shanghai.myqcloud.com/ai/test.pdf\n\n文档里说了什么？
+
+    
+        https://oss.ffire.cc/files/%E6%8B%9B%E6%A0%87%E6%96%87%E4%BB%B6%E5%A4%87%E6%A1%88%E8%A1%A8%EF%BC%88%E7%AC%AC%E4%BA%8C%E6%AC%A1%EF%BC%89.pdf 这个文件讲了什么？
+
     """
+    # https://oss.ffire.cc/files/%E6%8B%9B%E6%A0%87%E6%96%87%E4%BB%B6%E5%A4%87%E6%A1%88%E8%A1%A8%EF%BC%88%E7%AC%AC%E4%BA%8C%E6%AC%A1%EF%BC%89.pdf 正则匹配会卡死
+    # from urllib3.util import parse_url
+    # text = "@firebot /换衣 https://oss.ffire.cc/files/try-on.png"
+    # text = "@firebot /换衣 https://oss.ffire.cc/files/try-on.pn"
+
+    # print(parse_url(text))
+    # print(parse_url(text, for_image=True))
+    print(parse_url(text, for_image=False))
+
+    d = {"url": "https://mj101-1317487292.cos.ap-shanghai.myqcloud.com/ai/test.pdf\n\n总结下"}
+    print(parse_url(str(d)))
+
+    print('https://mj101-1317487292.cos.ap-shanghai.myqcloud.com/ai/test.pdf\\n\\n'.strip(r"\n"))
 
-    print(parse_url(text))
+    # print(parse_url("http://154.3.0.117:39666/docs#/default/get_content_preview_spider_playwright_get"))
 
-    print(parse_url("http://154.3.0.117:39666/docs#/default/get_content_preview_spider_playwright_get"))
+    # print(parse_url(text, True))

meutils/templates/xx.html

@@ -0,0 +1,21 @@
+<style> h1 {
+    text-align: center;
+    font-size: 24px;
+    margin-bottom: 10px;
+}
+
+table {
+    border-collapse: collapse;
+    width: 100%;
+}
+
+th, td {
+    border: 1px solid black;
+    padding: 8px;
+    text-align: center;
+}
+
+th {
+    background-color: #f2f2f2;
+}  </style>
+<head><title>2023年胡润百富榜</title></head><h1>2023年胡润百富榜</h1>

meutils/templates/xxx.html

@@ -0,0 +1,117 @@
+<head>
+    <meta charset="utf-8">
+    <STYLE TYPE="text/css" MEDIA=screen>
+
+        table.dataframe {
+            border-collapse: collapse;
+            border: 2px solid #a19da2;
+            /*居中显示整个表格*/
+            margin: auto;
+        }
+
+        table.dataframe thead {
+            border: 2px solid #91c6e1;
+            background: #f1f1f1;
+            padding: 10px 10px 10px 10px;
+            color: #333333;
+        }
+
+        table.dataframe tbody {
+            border: 2px solid #91c6e1;
+            padding: 10px 10px 10px 10px;
+        }
+
+        table.dataframe tr {
+
+        }
+
+        table.dataframe th {
+            vertical-align: top;
+            font-size: 14px;
+            padding: 10px 10px 10px 10px;
+            color: #105de3;
+            font-family: arial;
+            text-align: center;
+        }
+
+        table.dataframe td {
+            text-align: center;
+            padding: 10px 10px 10px 10px;
+        }
+
+        body {
+            font-family: 宋体;
+        }
+
+        h1 {
+            color: #5db446
+        }
+
+        div.header h2 {
+            color: #0002e3;
+            font-family: 黑体;
+        }
+
+        div.content h2 {
+            text-align: center;
+            font-size: 28px;
+            text-shadow: 2px 2px 1px #de4040;
+            color: #fff;
+            font-weight: bold;
+            background-color: #008eb7;
+            line-height: 1.5;
+            margin: 20px 0;
+            box-shadow: 10px 10px 5px #888888;
+            border-radius: 5px;
+        }
+
+        h3 {
+            font-size: 22px;
+            background-color: rgba(0, 2, 227, 0.71);
+            text-shadow: 2px 2px 1px #de4040;
+            color: rgba(239, 241, 234, 0.99);
+            line-height: 1.5;
+        }
+
+        h4 {
+            color: #e10092;
+            font-family: 楷体;
+            font-size: 20px;
+            text-align: center;
+        }
+
+        td img {
+            /*width: 60px;*/
+            max-width: 300px;
+            max-height: 300px;
+        }
+
+    </STYLE>
+</head>
+
+<body>
+
+<div align="center" class="header">
+    <!--标题部分的信息-->
+    <h1 align="center">{{ title }}</h1>
+    <h2 align="center">{{ subtitle }}</h2>
+</div>
+
+<hr>
+
+<div class="content">
+    <!--正文内容-->
+    <h2></h2>
+
+    <div>
+        <h4></h4>
+        {{ df_to_html }}
+
+    </div>
+
+    <hr>
+
+    <p style="text-align: center">
+
+    </p>
+</body>

meutils/todo.py

@@ -19,3 +19,15 @@ print(parsed_url.netloc)  # www.example.com
 print(parsed_url.path)  # /path/to/something
 print(parsed_url.query)  # a=1&b=2
 print(parsed_url.fragment)  # fragment
+
+
+@timer('1')
+@timer('2')
+def f():
+    pass
+
+
+
+if __name__ == '__main__':
+    f()
+    print(get_name())

meutils/tools/token_monitor.py

@@ -0,0 +1,33 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# @Project      : AI.  @by PyCharm
+# @File         : token_monitor
+# @Time         : 2024/4/22 14:50
+# @Author       : betterme
+# @WeChat       : meutils
+# @Software     : PyCharm
+# @Description  : refresh_token key 鉴权 /token/check
+# /v1/token/kimi_xxxxx # kimi_sk-...
+# /v1/token/glm_xxxxx
+# 从配置中心读取 keys
+# 定时监测，失效剔除【飞书告警】
+# 提供get接口，客户端定时拉取【统计使用频次，均匀采样】
+# 检测接口 并且加入轮询库 借助配置中心
+# 最原始检测逻辑
+#######核心：检查token加入轮询配置中，15分钟检查一下
+
+import httpx
+
+# 无效的令牌 401 403
+
+from meutils.pipe import *
+from meutils.async_utils import arequest, arun
+
+base_url = "http://154.3.0.117:39002"
+
+payload = {
+    "token": "eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9...",
+    "base_url": ""
+}
+
+print(arun(arequest(url='/token/check', method='post', base_url=base_url, payload=payload)).json())