脚本如何实现文件内容透视分析

wen 实用脚本 2026-07-10 2

本文目录导读：

脚本如何实现文件内容透视分析

Python实现方案
Bash脚本实现（Linux/Unix）
高级分析：代码质量透视
多媒体文件透视
使用示例

透视分析的方法。

Python实现方案

基础文本分析脚本

#!/usr/bin/env python3
"""透视分析工具
"""
import os
import sys
import re
from collections import Counter
from pathlib import Path
class FileAnalyzer:
    def __init__(self, filepath):
        self.filepath = Path(filepath)
        self.content = ""
        self.stats = {}
    def read_file(self):
        """读取文件内容"""
        try:
            with open(self.filepath, 'r', encoding='utf-8') as f:
                self.content = f.read()
            return True
        except Exception as e:
            print(f"读取文件失败: {e}")
            return False
    def analyze_structure(self):
        """分析文件结构"""
        lines = self.content.split('\n')
        self.stats['total_lines'] = len(lines)
        self.stats['empty_lines'] = lines.count('')
        self.stats['code_lines'] = self.stats['total_lines'] - self.stats['empty_lines']
        # 分析缩进层次
        indent_levels = []
        for line in lines:
            if line.strip():
                indent = len(line) - len(line.lstrip())
                indent_levels.append(indent)
        if indent_levels:
            self.stats['avg_indent'] = sum(indent_levels) // len(indent_levels)
            self.stats['max_indent'] = max(indent_levels)
    def analyze_content(self):
        """分析内容特征"""
        # 单词频率
        words = re.findall(r'\w+', self.content.lower())
        self.stats['total_words'] = len(words)
        self.stats['unique_words'] = len(set(words))
        self.stats['word_frequency'] = Counter(words).most_common(10)
        # 字符统计
        self.stats['total_chars'] = len(self.content)
        self.stats['char_no_space'] = len(self.content.replace(' ', '').replace('\n', ''))
        # 特殊字符
        special_chars = re.findall(r'[^\w\s]', self.content)
        self.stats['special_chars_count'] = len(special_chars)
    def detect_file_type(self):
        """检测文件类型"""
        extension = self.filepath.suffix.lower()
        type_map = {
            '.py': 'Python',
            '.js': 'JavaScript',
            '.html': 'HTML',
            '.css': 'CSS',
            '.json': 'JSON',
            '.xml': 'XML',
            '.csv': 'CSV',
            '.txt': '文本文件',
            '.md': 'Markdown',
        }
        return type_map.get(extension, '未知类型')
    def generate_report(self):
        """生成分析报告"""
        report = f"""
╔══════════════════════════════════════╗
║       文件内容透视分析报告            ║
╚══════════════════════════════════════╝
📁 文件信息
   文件路径: {self.filepath}
   文件大小: {os.path.getsize(self.filepath):,} bytes
   文件类型: {self.detect_file_type()}
📊 结构分析
   总行数: {self.stats.get('total_lines', 0):,}
   代码行数: {self.stats.get('code_lines', 0):,}
   空行数: {self.stats.get('empty_lines', 0):,}
   平均缩进: {self.stats.get('avg_indent', 0)}
   最大缩进: {self.stats.get('max_indent', 0)}
分析
   总字符数: {self.stats.get('total_chars', 0):,}
   非空格字符: {self.stats.get('char_no_space', 0):,}
   总词汇数: {self.stats.get('total_words', 0):,}
   唯一词汇: {self.stats.get('unique_words', 0):,}
   特殊字符: {self.stats.get('special_chars_count', 0):,}
🏆 高频词汇 (Top 10):
"""
        for word, count in self.stats.get('word_frequency', []):
            report += f"   {word}: {count}次\n"
        return report
def main():
    if len(sys.argv) != 2:
        print("用法: python file_analyzer.py <文件路径>")
        sys.exit(1)
    analyzer = FileAnalyzer(sys.argv[1])
    if analyzer.read_file():
        analyzer.analyze_structure()
        analyzer.analyze_content()
        print(analyzer.generate_report())
    else:
        sys.exit(1)
if __name__ == "__main__":
    main()

Bash脚本实现（Linux/Unix）

#!/bin/bash
# file_perspective.sh - 文件透视分析
FILE=$1
if [ ! -f "$FILE" ]; then
    echo "文件不存在: $FILE"
    exit 1
fi
echo "╔══════════════════════════════════════╗"
echo "║       文件内容透视分析报表            ║"
echo "╚══════════════════════════════════════╝"
echo ""
# 基本文件信息
echo "📁 文件信息"
echo "   文件名: $(basename $FILE)"
echo "   大小: $(stat -f%z $FILE 2>/dev/null || stat -c%s $FILE) bytes"
echo "   权限: $(stat -f%Sp $FILE 2>/dev/null || stat -c%a $FILE)"
echo ""
# 行统计
TOTAL_LINES=$(wc -l < "$FILE")
EMPTY_LINES=$(grep -c '^$' "$FILE" 2>/dev/null || echo 0)
CODE_LINES=$((TOTAL_LINES - EMPTY_LINES))
echo "📊 行分析"
echo "   总行数: $TOTAL_LINES"
echo "   非空行: $CODE_LINES"
echo "   空行数: $EMPTY_LINES"
echo "   最大行长度: $(awk '{ if (length > max) max = length } END { print max }' $FILE)"
echo ""
# 字符分析
echo "📝 字符分析"
echo "   总字符数: $(wc -c < $FILE)"
echo "   单词数: $(wc -w < $FILE)"
echo "   唯一单词数: $(tr ' ' '\n' < $FILE | sort -u | wc -l)"
echo ""
模式分析
echo "🔍 特殊模式"
# 查找URL
echo "   URL数量: $(grep -c 'https\?://' "$FILE" 2>/dev/null || echo 0)"
# 查找邮件
echo "   邮箱数量: $(grep -c '[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]' "$FILE" 2>/dev/null || echo 0)"
# 查找数字
echo "   数字数量: $(grep -c '[0-9]' "$FILE" 2>/dev/null || echo 0)"
echo ""
# 高频词分析
echo "🏆 高频词 (Top 10):"
tr -c '[:alnum:]' '[\n*]' < "$FILE" | \
    grep -v '^$' | \
    sort | \
    uniq -c | \
    sort -rn | \
    head -10 | \
    awk '{printf "   %s: %d次\n", $2, $1}'

高级分析：代码质量透视

#!/usr/bin/env python3
"""
代码质量透视分析器
"""
import ast
import re
from pathlib import Path
class CodeQualityAnalyzer:
    def __init__(self, filepath):
        self.filepath = Path(filepath)
        self.issues = []
    def analyze_python_code(self):
        """分析Python代码质量"""
        with open(self.filepath, 'r', encoding='utf-8') as f:
            code = f.read()
        try:
            tree = ast.parse(code)
            # 分析函数复杂度
            functions = [node for node in ast.walk(tree) 
                        if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef))]
            print(f"📊 函数分析")
            print(f"   函数总数: {len(functions)}")
            for func in functions:
                complexity = self._calculate_complexity(func)
                if complexity > 10:
                    print(f"   ⚠️ 函数 {func.name}: 复杂度 {complexity} (建议重构)")
            # 分析类和导入
            classes = [node for node in ast.walk(tree) 
                      if isinstance(node, ast.ClassDef)]
            imports = [node for node in ast.walk(tree) 
                      if isinstance(node, (ast.Import, ast.ImportFrom))]
            print(f"   类定义: {len(classes)}")
            print(f"   导入语句: {len(imports)}")
        except SyntaxError as e:
            print(f"❌ 语法错误: {e}")
    def _calculate_complexity(self, func_node):
        """计算循环复杂度"""
        complexity = 1
        for node in ast.walk(func_node):
            if isinstance(node, (ast.If, ast.While, ast.For, 
                               ast.ExceptHandler, ast.With)):
                complexity += 1
            elif isinstance(node, ast.BoolOp):
                complexity += len(node.values) - 1
        return complexity
    def analyze_comments_ratio(self):
        """分析注释比例"""
        with open(self.filepath, 'r', encoding='utf-8') as f:
            lines = f.readlines()
        comment_lines = 0
        docstring_lines = 0
        code_lines = 0
        for line in lines:
            stripped = line.strip()
            if stripped.startswith('#'):
                comment_lines += 1
            elif stripped.startswith('"""') or stripped.startswith("'''"):
                docstring_lines += 1
            elif stripped:
                code_lines += 1
        total = code_lines + comment_lines + docstring_lines
        print(f"\n📈 注释分析")
        print(f"   代码行: {code_lines} ({code_lines/total*100:.1f}%)")
        print(f"   注释行: {comment_lines} ({comment_lines/total*100:.1f}%)")
        print(f"   文档字符串: {docstring_lines} ({docstring_lines/total*100:.1f}%)")
        if comment_lines / code_lines < 0.1:
            print("   ⚠️ 建议: 注释比例偏低，建议增加注释")

多媒体文件透视

#!/usr/bin/env python3
"""
二进制文件透视分析
"""
import struct
import hashlib
class BinaryFileAnalyzer:
    def __init__(self, filepath):
        self.filepath = filepath
    def analyze_header(self):
        """分析文件头信息"""
        with open(self.filepath, 'rb') as f:
            header = f.read(16)
        # 文件签名识别
        signatures = {
            b'\x89PNG': 'PNG图片',
            b'\xff\xd8\xff': 'JPEG图片',
            b'GIF8': 'GIF图片',
            b'%PDF': 'PDF文档',
            b'PK\x03\x04': 'ZIP/Office文档',
            b'\x7fELF': 'ELF可执行文件',
        }
        print("📋 文件签名分析:")
        for sig, desc in signatures.items():
            if header.startswith(sig):
                print(f"   ✅ 检测到: {desc}")
                break
        else:
            print(f"   ℹ️ 未知文件类型")
            print(f"   文件头(HEX): {header.hex()}")
    def calculate_entropy(self):
        """计算文件熵值"""
        with open(self.filepath, 'rb') as f:
            data = f.read()
        # 计算字节频率
        freq = {}
        for byte in data:
            freq[byte] = freq.get(byte, 0) + 1
        # 计算熵值
        import math
        entropy = 0
        for count in freq.values():
            prob = count / len(data)
            entropy -= prob * math.log2(prob)
        print(f"\n📊 熵值分析:")
        print(f"   文件熵值: {entropy:.2f} (理论最大值: 8.0)")
        if entropy > 7:
            print("   状态: 高熵值 (可能已加密或压缩)")
        elif entropy > 5:
            print("   状态: 中等熵值 (正常数据)")
        else:
            print("   状态: 低熵值 (高度结构化数据)")
    def get_file_hash(self):
        """计算文件哈希值"""
        with open(self.filepath, 'rb') as f:
            data = f.read()
        print(f"\n🔐 文件哈希值:")
        print(f"   MD5: {hashlib.md5(data).hexdigest()}")
        print(f"   SHA1: {hashlib.sha1(data).hexdigest()}")
        print(f"   SHA256: {hashlib.sha256(data).hexdigest()}")

使用示例

# 使用Python脚本分析文本文件
python file_analyzer.py example.txt
# 使用Bash脚本
chmod +x file_perspective.sh
./file_perspective.sh example.txt
# 分析Python代码质量
python -c "
from file_analyzer import CodeQualityAnalyzer
analyzer = CodeQualityAnalyzer('example.py')
analyzer.analyze_python_code()
analyzer.analyze_comments_ratio()
"

这些脚本提供了文件内容的深度透视功能,可以根据具体需求选择合适的方案或组合使用。