crawlo 1.2.3__py3-none-any.whl → 1.2.5__py3-none-any.whl

crawlo/cleaners/text_cleaner.py

@@ -1,233 +1,233 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-# @Time    : 2025-09-10 22:00
-# @Author  : crawl-coder
-# @Desc    : 文本清洗工具
-"""
-import re
-import html
-from typing import Optional, Union, List
-import unicodedata
-
-
-class TextCleaner:
-    """
-    文本清洗工具类，提供各种文本清洗功能。
-    特别适用于爬虫中处理网页内容的清洗需求。
-    """
-
-    @staticmethod
-    def remove_html_tags(text: str) -> str:
-        """
-        移除HTML标签
-        
-        :param text: 包含HTML标签的文本
-        :return: 移除HTML标签后的文本
-        """
-        if not isinstance(text, str):
-            return str(text)
-        
-        # 使用正则表达式移除HTML标签
-        clean_text = re.sub(r'<[^>]+>', '', text)
-        return clean_text.strip()
-
-    @staticmethod
-    def decode_html_entities(text: str) -> str:
-        """
-        解码HTML实体字符
-        
-        :param text: 包含HTML实体字符的文本
-        :return: 解码后的文本
-        """
-        if not isinstance(text, str):
-            return str(text)
-        
-        return html.unescape(text)
-
-    @staticmethod
-    def remove_extra_whitespace(text: str) -> str:
-        """
-        移除多余的空白字符（包括空格、制表符、换行符等）
-        
-        :param text: 文本
-        :return: 清理后的文本
-        """
-        if not isinstance(text, str):
-            return str(text)
-        
-        # 将多个连续的空白字符替换为单个空格
-        clean_text = re.sub(r'\s+', ' ', text)
-        return clean_text.strip()
-
-    @staticmethod
-    def remove_special_chars(text: str, chars: str = '') -> str:
-        """
-        移除特殊字符
-        
-        :param text: 文本
-        :param chars: 要移除的特殊字符
-        :return: 清理后的文本
-        """
-        if not isinstance(text, str):
-            return str(text)
-        
-        # 移除常见的特殊字符
-        special_chars = r'[^\w\s\u4e00-\u9fff' + chars + r']'
-        clean_text = re.sub(special_chars, '', text)
-        return clean_text
-
-    @staticmethod
-    def normalize_unicode(text: str) -> str:
-        """
-        标准化Unicode字符
-        
-        :param text: 文本
-        :return: 标准化后的文本
-        """
-        if not isinstance(text, str):
-            return str(text)
-        
-        return unicodedata.normalize('NFKC', text)
-
-    @staticmethod
-    def clean_text(text: str, 
-                   remove_html: bool = True,
-                   decode_entities: bool = True,
-                   remove_whitespace: bool = True,
-                   remove_special: bool = False,
-                   normalize: bool = True) -> str:
-        """
-        综合文本清洗方法
-        
-        :param text: 原始文本
-        :param remove_html: 是否移除HTML标签
-        :param decode_entities: 是否解码HTML实体
-        :param remove_whitespace: 是否移除多余空白字符
-        :param remove_special: 是否移除特殊字符
-        :param normalize: 是否标准化Unicode字符
-        :return: 清洗后的文本
-        """
-        if not isinstance(text, str):
-            text = str(text)
-        
-        if not text:
-            return text
-            
-        # 按顺序进行清洗
-        if remove_html:
-            text = TextCleaner.remove_html_tags(text)
-        
-        if decode_entities:
-            text = TextCleaner.decode_html_entities(text)
-        
-        if normalize:
-            text = TextCleaner.normalize_unicode(text)
-        
-        if remove_whitespace:
-            text = TextCleaner.remove_extra_whitespace(text)
-        
-        if remove_special:
-            text = TextCleaner.remove_special_chars(text)
-        
-        return text
-
-    @staticmethod
-    def extract_numbers(text: str) -> List[str]:
-        """
-        从文本中提取数字
-        
-        :param text: 文本
-        :return: 数字列表
-        """
-        if not isinstance(text, str):
-            return []
-        
-        # 匹配整数和小数
-        numbers = re.findall(r'-?\d+\.?\d*', text)
-        return numbers
-
-    @staticmethod
-    def extract_emails(text: str) -> List[str]:
-        """
-        从文本中提取邮箱地址
-        
-        :param text: 文本
-        :return: 邮箱地址列表
-        """
-        if not isinstance(text, str):
-            return []
-        
-        # 匹配邮箱地址
-        emails = re.findall(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', text)
-        return emails
-
-    @staticmethod
-    def extract_urls(text: str) -> List[str]:
-        """
-        从文本中提取URL
-        
-        :param text: 文本
-        :return: URL列表
-        """
-        if not isinstance(text, str):
-            return []
-        
-        # 匹配URL
-        urls = re.findall(
-            r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+',
-            text
-        )
-        return urls
-
-
-# =======================对外接口=======================
-
-def remove_html_tags(text: str) -> str:
-    """移除HTML标签"""
-    return TextCleaner.remove_html_tags(text)
-
-
-def decode_html_entities(text: str) -> str:
-    """解码HTML实体字符"""
-    return TextCleaner.decode_html_entities(text)
-
-
-def remove_extra_whitespace(text: str) -> str:
-    """移除多余的空白字符"""
-    return TextCleaner.remove_extra_whitespace(text)
-
-
-def remove_special_chars(text: str, chars: str = '') -> str:
-    """移除特殊字符"""
-    return TextCleaner.remove_special_chars(text, chars)
-
-
-def normalize_unicode(text: str) -> str:
-    """标准化Unicode字符"""
-    return TextCleaner.normalize_unicode(text)
-
-
-def clean_text(text: str, 
-               remove_html: bool = True,
-               decode_entities: bool = True,
-               remove_whitespace: bool = True,
-               remove_special: bool = False,
-               normalize: bool = True) -> str:
-    """综合文本清洗"""
-    return TextCleaner.clean_text(text, remove_html, decode_entities, remove_whitespace, remove_special, normalize)
-
-
-def extract_numbers(text: str) -> List[str]:
-    """提取数字"""
-    return TextCleaner.extract_numbers(text)
-
-
-def extract_emails(text: str) -> List[str]:
-    """提取邮箱地址"""
-    return TextCleaner.extract_emails(text)
-
-
-def extract_urls(text: str) -> List[str]:
-    """提取URL"""
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+# @Time    : 2025-09-10 22:00
+# @Author  : crawl-coder
+# @Desc    : 文本清洗工具
+"""
+import re
+import html
+from typing import Optional, Union, List
+import unicodedata
+
+
+class TextCleaner:
+    """
+    文本清洗工具类，提供各种文本清洗功能。
+    特别适用于爬虫中处理网页内容的清洗需求。
+    """
+
+    @staticmethod
+    def remove_html_tags(text: str) -> str:
+        """
+        移除HTML标签
+        
+        :param text: 包含HTML标签的文本
+        :return: 移除HTML标签后的文本
+        """
+        if not isinstance(text, str):
+            return str(text)
+        
+        # 使用正则表达式移除HTML标签
+        clean_text = re.sub(r'<[^>]+>', '', text)
+        return clean_text.strip()
+
+    @staticmethod
+    def decode_html_entities(text: str) -> str:
+        """
+        解码HTML实体字符
+        
+        :param text: 包含HTML实体字符的文本
+        :return: 解码后的文本
+        """
+        if not isinstance(text, str):
+            return str(text)
+        
+        return html.unescape(text)
+
+    @staticmethod
+    def remove_extra_whitespace(text: str) -> str:
+        """
+        移除多余的空白字符（包括空格、制表符、换行符等）
+        
+        :param text: 文本
+        :return: 清理后的文本
+        """
+        if not isinstance(text, str):
+            return str(text)
+        
+        # 将多个连续的空白字符替换为单个空格
+        clean_text = re.sub(r'\s+', ' ', text)
+        return clean_text.strip()
+
+    @staticmethod
+    def remove_special_chars(text: str, chars: str = '') -> str:
+        """
+        移除特殊字符
+        
+        :param text: 文本
+        :param chars: 要移除的特殊字符
+        :return: 清理后的文本
+        """
+        if not isinstance(text, str):
+            return str(text)
+        
+        # 移除常见的特殊字符
+        special_chars = r'[^\w\s\u4e00-\u9fff' + chars + r']'
+        clean_text = re.sub(special_chars, '', text)
+        return clean_text
+
+    @staticmethod
+    def normalize_unicode(text: str) -> str:
+        """
+        标准化Unicode字符
+        
+        :param text: 文本
+        :return: 标准化后的文本
+        """
+        if not isinstance(text, str):
+            return str(text)
+        
+        return unicodedata.normalize('NFKC', text)
+
+    @staticmethod
+    def clean_text(text: str, 
+                   remove_html: bool = True,
+                   decode_entities: bool = True,
+                   remove_whitespace: bool = True,
+                   remove_special: bool = False,
+                   normalize: bool = True) -> str:
+        """
+        综合文本清洗方法
+        
+        :param text: 原始文本
+        :param remove_html: 是否移除HTML标签
+        :param decode_entities: 是否解码HTML实体
+        :param remove_whitespace: 是否移除多余空白字符
+        :param remove_special: 是否移除特殊字符
+        :param normalize: 是否标准化Unicode字符
+        :return: 清洗后的文本
+        """
+        if not isinstance(text, str):
+            text = str(text)
+        
+        if not text:
+            return text
+            
+        # 按顺序进行清洗
+        if remove_html:
+            text = TextCleaner.remove_html_tags(text)
+        
+        if decode_entities:
+            text = TextCleaner.decode_html_entities(text)
+        
+        if normalize:
+            text = TextCleaner.normalize_unicode(text)
+        
+        if remove_whitespace:
+            text = TextCleaner.remove_extra_whitespace(text)
+        
+        if remove_special:
+            text = TextCleaner.remove_special_chars(text)
+        
+        return text
+
+    @staticmethod
+    def extract_numbers(text: str) -> List[str]:
+        """
+        从文本中提取数字
+        
+        :param text: 文本
+        :return: 数字列表
+        """
+        if not isinstance(text, str):
+            return []
+        
+        # 匹配整数和小数
+        numbers = re.findall(r'-?\d+\.?\d*', text)
+        return numbers
+
+    @staticmethod
+    def extract_emails(text: str) -> List[str]:
+        """
+        从文本中提取邮箱地址
+        
+        :param text: 文本
+        :return: 邮箱地址列表
+        """
+        if not isinstance(text, str):
+            return []
+        
+        # 匹配邮箱地址
+        emails = re.findall(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', text)
+        return emails
+
+    @staticmethod
+    def extract_urls(text: str) -> List[str]:
+        """
+        从文本中提取URL
+        
+        :param text: 文本
+        :return: URL列表
+        """
+        if not isinstance(text, str):
+            return []
+        
+        # 匹配URL
+        urls = re.findall(
+            r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+',
+            text
+        )
+        return urls
+
+
+# =======================对外接口=======================
+
+def remove_html_tags(text: str) -> str:
+    """移除HTML标签"""
+    return TextCleaner.remove_html_tags(text)
+
+
+def decode_html_entities(text: str) -> str:
+    """解码HTML实体字符"""
+    return TextCleaner.decode_html_entities(text)
+
+
+def remove_extra_whitespace(text: str) -> str:
+    """移除多余的空白字符"""
+    return TextCleaner.remove_extra_whitespace(text)
+
+
+def remove_special_chars(text: str, chars: str = '') -> str:
+    """移除特殊字符"""
+    return TextCleaner.remove_special_chars(text, chars)
+
+
+def normalize_unicode(text: str) -> str:
+    """标准化Unicode字符"""
+    return TextCleaner.normalize_unicode(text)
+
+
+def clean_text(text: str, 
+               remove_html: bool = True,
+               decode_entities: bool = True,
+               remove_whitespace: bool = True,
+               remove_special: bool = False,
+               normalize: bool = True) -> str:
+    """综合文本清洗"""
+    return TextCleaner.clean_text(text, remove_html, decode_entities, remove_whitespace, remove_special, normalize)
+
+
+def extract_numbers(text: str) -> List[str]:
+    """提取数字"""
+    return TextCleaner.extract_numbers(text)
+
+
+def extract_emails(text: str) -> List[str]:
+    """提取邮箱地址"""
+    return TextCleaner.extract_emails(text)
+
+
+def extract_urls(text: str) -> List[str]:
+    """提取URL"""
     return TextCleaner.extract_urls(text)

crawlo/cli.py

@@ -1,82 +1,89 @@
-# crawlo/cli.py
-# !/usr/bin/python
-# -*- coding: UTF-8 -*-
-import sys
-import argparse
-import os
-from crawlo.commands import get_commands
-
-
-def main():
-    # 获取框架版本号
-    version_file = os.path.join(os.path.dirname(__file__), '__version__.py')
-    if os.path.exists(version_file):
-        with open(version_file, 'r') as f:
-            exec(f.read())
-        VERSION = locals().get('__version__', '1.0.0')
-    else:
-        VERSION = '1.0.0'
-
-    # 获取所有可用命令
-    commands = get_commands()
-
-    # 创建主解析器
-    parser = argparse.ArgumentParser(
-        description="Crawlo: A lightweight web crawler framework.",
-        usage="crawlo <command> [options]",
-        add_help=False  # 禁用默认帮助，我们自己处理
-    )
-    
-    # 添加帮助参数
-    parser.add_argument('-h', '--help', action='store_true', help='显示帮助信息')
-    parser.add_argument('-v', '--version', action='store_true', help='显示版本信息')
-    parser.add_argument('command', nargs='?', help='可用命令: ' + ', '.join(commands.keys()))
-    
-    # 解析已知参数
-    args, unknown = parser.parse_known_args()
-
-    # 处理版本参数
-    if args.version:
-        print(f"Crawlo {VERSION}")
-        sys.exit(0)
-
-    # 处理帮助参数
-    if args.help or (args.command is None and not unknown):
-        # 导入并运行帮助命令
-        try:
-            module = __import__(commands['help'], fromlist=['main'])
-            sys.exit(module.main([]))
-        except ImportError as e:
-            print(f"Failed to load help command: {e}")
-            sys.exit(1)
-        except Exception as e:
-            print(f"Help command failed: {e}")
-            sys.exit(1)
-
-    # 检查命令是否存在
-    if args.command not in commands:
-        print(f"Unknown command: {args.command}")
-        print(f"Available commands: {', '.join(commands.keys())}")
-        # 显示帮助信息
-        try:
-            module = __import__(commands['help'], fromlist=['main'])
-            module.main([])
-        except:
-            pass
-        sys.exit(1)
-
-    # 动态导入并执行命令
-    try:
-        module = __import__(commands[args.command], fromlist=['main'])
-        # 将未知参数传递给子命令
-        sys.exit(module.main(unknown))
-    except ImportError as e:
-        print(f"Failed to load command '{args.command}': {e}")
-        sys.exit(1)
-    except Exception as e:
-        print(f"Command '{args.command}' failed: {e}")
-        sys.exit(1)
-
-
-if __name__ == '__main__':
+# crawlo/cli.py
+# !/usr/bin/python
+# -*- coding: UTF-8 -*-
+import sys
+import argparse
+import os
+from crawlo.commands import get_commands
+
+
+def main():
+    # 获取框架版本号
+    version_file = os.path.join(os.path.dirname(__file__), '__version__.py')
+    VERSION = '1.0.0'  # 默认版本号
+    if os.path.exists(version_file):
+        try:
+            with open(version_file, 'r') as f:
+                content = f.read()
+                # 使用正则表达式提取版本号
+                import re
+                version_match = re.search(r"__version__\s*=\s*['\"]([^'\"]*)['\"]", content)
+                if version_match:
+                    VERSION = version_match.group(1)
+        except Exception:
+            # 如果读取失败，使用默认版本号
+            pass
+
+    # 获取所有可用命令
+    commands = get_commands()
+
+    # 创建主解析器
+    parser = argparse.ArgumentParser(
+        description="Crawlo: A lightweight web crawler framework.",
+        usage="crawlo <command> [options]",
+        add_help=False  # 禁用默认帮助，我们自己处理
+    )
+    
+    # 添加帮助参数
+    parser.add_argument('-h', '--help', action='store_true', help='显示帮助信息')
+    parser.add_argument('-v', '--version', action='store_true', help='显示版本信息')
+    parser.add_argument('command', nargs='?', help='可用命令: ' + ', '.join(commands.keys()))
+    
+    # 解析已知参数
+    args, unknown = parser.parse_known_args()
+
+    # 处理版本参数
+    if args.version:
+        print(f"Crawlo {VERSION}")
+        sys.exit(0)
+
+    # 处理帮助参数
+    if args.help or (args.command is None and not unknown):
+        # 导入并运行帮助命令
+        try:
+            module = __import__(commands['help'], fromlist=['main'])
+            sys.exit(module.main([]))
+        except ImportError as e:
+            print(f"Failed to load help command: {e}")
+            sys.exit(1)
+        except Exception as e:
+            print(f"Help command failed: {e}")
+            sys.exit(1)
+
+    # 检查命令是否存在
+    if args.command not in commands:
+        print(f"Unknown command: {args.command}")
+        print(f"Available commands: {', '.join(commands.keys())}")
+        # 显示帮助信息
+        try:
+            module = __import__(commands['help'], fromlist=['main'])
+            module.main([])
+        except:
+            pass
+        sys.exit(1)
+
+    # 动态导入并执行命令
+    try:
+        module = __import__(commands[args.command], fromlist=['main'])
+        # 将未知参数传递给子命令
+        sys.exit(module.main(unknown))
+    except ImportError as e:
+        print(f"Failed to load command '{args.command}': {e}")
+        sys.exit(1)
+    except Exception as e:
+        print(f"Command '{args.command}' failed: {e}")
+        sys.exit(1)
+
+
+if __name__ == '__main__':
     main()

crawlo/commands/__init__.py

@@ -1,15 +1,15 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-
-_commands = {
-    'startproject': 'crawlo.commands.startproject',
-    'genspider': 'crawlo.commands.genspider',
-    'run': 'crawlo.commands.run',
-    'check': 'crawlo.commands.check',
-    'list': 'crawlo.commands.list',
-    'stats': 'crawlo.commands.stats',
-    'help': 'crawlo.commands.help'
-}
-
-def get_commands():
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+
+_commands = {
+    'startproject': 'crawlo.commands.startproject',
+    'genspider': 'crawlo.commands.genspider',
+    'run': 'crawlo.commands.run',
+    'check': 'crawlo.commands.check',
+    'list': 'crawlo.commands.list',
+    'stats': 'crawlo.commands.stats',
+    'help': 'crawlo.commands.help'
+}
+
+def get_commands():
     return _commands