Python 综合实战项目

20.1 项目一：通讯录管理系统

功能需求

• 添加联系人
• 删除联系人
• 查询联系人
• 显示所有联系人
• 保存到文件

实现代码

import json
import os

class ContactManager:
    def __init__(self, filename="contacts.json"):
        self.filename = filename
        self.contacts = self.load_contacts()
    
    def load_contacts(self):
        if os.path.exists(self.filename):
            with open(self.filename, "r") as f:
                return json.load(f)
        return {}
    
    def save_contacts(self):
        with open(self.filename, "w") as f:
            json.dump(self.contacts, f, indent=2, ensure_ascii=False)
    
    def add_contact(self, name, phone, email):
        if name in self.contacts:
            print(f"联系人 {name} 已存在")
            return
        self.contacts[name] = {"phone": phone, "email": email}
        self.save_contacts()
        print(f"已添加: {name}")
    
    def delete_contact(self, name):
        if name in self.contacts:
            del self.contacts[name]
            self.save_contacts()
            print(f"已删除: {name}")
        else:
            print(f"联系人 {name} 不存在")
    
    def search_contact(self, name):
        if name in self.contacts:
            info = self.contacts[name]
            print(f"姓名: {name}")
            print(f"电话: {info['phone']}")
            print(f"邮箱: {info['email']}")
        else:
            print(f"未找到: {name}")
    
    def show_all(self):
        if not self.contacts:
            print("通讯录为空")
            return
        for name, info in self.contacts.items():
            print(f"{name}: {info['phone']}, {info['email']}")

# 使用示例
manager = ContactManager()
manager.add_contact("Alice", "13800138000", "alice@example.com")
manager.add_contact("Bob", "13900139000", "bob@example.com")
manager.show_all()
manager.search_contact("Alice")

---

20.2 项目二：简易网页爬虫

功能需求

• 获取网页内容
• 提取所有链接
• 提取所有图片
• 保存结果

实现代码

import requests
import re
from urllib.parse import urljoin

class SimpleCrawler:
    def __init__(self, url):
        self.url = url
        self.html = self.fetch_page()
    
    def fetch_page(self):
        try:
            response = requests.get(self.url, timeout=10)
            response.raise_for_status()
            return response.text
        except requests.RequestException as e:
            print(f"请求失败: {e}")
            return ""
    
    def extract_links(self):
        pattern = r'href=["\'](.*?)["\']'
        links = re.findall(pattern, self.html)
        return [urljoin(self.url, link) for link in links]
    
    def extract_images(self):
        pattern = r'src=["\'](.*?\.(?:jpg|jpeg|png|gif))["\']'
        images = re.findall(pattern, self.html, re.IGNORECASE)
        return [urljoin(self.url, img) for img in images]
    
    def save_results(self, filename="results.txt"):
        links = self.extract_links()
        images = self.extract_images()
        
        with open(filename, "w") as f:
            f.write(f"页面: {self.url}\n\n")
            f.write(f"链接 ({len(links)} 个):\n")
            for link in links:
                f.write(f"  {link}\n")
            f.write(f"\n图片 ({len(images)} 个):\n")
            for img in images:
                f.write(f"  {img}\n")
        
        print(f"结果已保存到 {filename}")

# 使用示例
# crawler = SimpleCrawler("https://example.com")
# crawler.save_results()

---

20.3 项目三：数据分析小工具

功能需求

• 读取 CSV 文件
• 统计基本信息
• 计算平均值、最大值、最小值
• 生成简单报告

实现代码

import csv
from collections import defaultdict

class DataAnalyzer:
    def __init__(self, filename):
        self.filename = filename
        self.data = self.load_data()
    
    def load_data(self):
        data = []
        with open(self.filename, "r", encoding="utf-8") as f:
            reader = csv.DictReader(f)
            for row in reader:
                data.append(row)
        return data
    
    def get_column(self, column_name):
        return [row[column_name] for row in self.data if column_name in row]
    
    def numeric_stats(self, column_name):
        values = [float(x) for x in self.get_column(column_name) if x]
        if not values:
            return None
        return {
            "count": len(values),
            "sum": sum(values),
            "mean": sum(values) / len(values),
            "max": max(values),
            "min": min(values)
        }
    
    def category_count(self, column_name):
        values = self.get_column(column_name)
        counter = defaultdict(int)
        for v in values:
            counter[v] += 1
        return dict(counter)
    
    def generate_report(self):
        print(f"数据文件: {self.filename}")
        print(f"总记录数: {len(self.data)}\n")
        
        if self.data:
            print("列名:", ", ".join(self.data[0].keys()))
            print()
            
            for column in self.data[0].keys():
                stats = self.numeric_stats(column)
                if stats:
                    print(f"{column} 统计:")
                    print(f"  数量: {stats['count']}")
                    print(f"  总和: {stats['sum']:.2f}")
                    print(f"  平均: {stats['mean']:.2f}")
                    print(f"  最大: {stats['max']:.2f}")
                    print(f"  最小: {stats['min']:.2f}")
                else:
                    counts = self.category_count(column)
                    print(f"{column} 分类:")
                    for k, v in counts.items():
                        print(f"  {k}: {v}")
                print()

# 使用示例
# analyzer = DataAnalyzer("students.csv")
# analyzer.generate_report()

---

20.4 项目四：日志分析器

功能需求

• 读取日志文件
• 统计错误数量
• 按级别分类
• 提取时间范围

实现代码

import re
from collections import Counter
from datetime import datetime

class LogAnalyzer:
    def __init__(self, filename):
        self.filename = filename
        self.logs = self.load_logs()
    
    def load_logs(self):
        logs = []
        pattern = r"(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}) \[(\w+)\] (.+)"
        
        with open(self.filename, "r") as f:
            for line in f:
                match = re.match(pattern, line.strip())
                if match:
                    logs.append({
                        "time": match.group(1),
                        "level": match.group(2),
                        "message": match.group(3)
                    })
        return logs
    
    def count_by_level(self):
        counter = Counter(log["level"] for log in self.logs)
        return dict(counter)
    
    def get_errors(self):
        return [log for log in self.logs if log["level"] == "ERROR"]
    
    def get_time_range(self):
        if not self.logs:
            return None, None
        times = [log["time"] for log in self.logs]
        return times[0], times[-1]
    
    def generate_report(self):
        print(f"日志文件: {self.filename}")
        print(f"总日志数: {len(self.logs)}\n")
        
        start, end = self.get_time_range()
        print(f"时间范围: {start} 至 {end}\n")
        
        counts = self.count_by_level()
        print("日志级别统计:")
        for level, count in sorted(counts.items()):
            print(f"  {level}: {count}")
        
        errors = self.get_errors()
        if errors:
            print(f"\n错误日志 ({len(errors)} 条):")
            for error in errors[:5]:
                print(f"  [{error['time']}] {error['message']}")
            if len(errors) > 5:
                print(f"  ... 还有 {len(errors) - 5} 条错误")

# 使用示例
# analyzer = LogAnalyzer("app.log")
# analyzer.generate_report()

---

20.5 本章小结

• 综合运用文件操作、JSON/CSV 处理、正则表达式
• 面向对象设计提高代码组织性
• 异常处理保证程序健壮性
• 模块化设计便于扩展

后续学习建议

• Web 开发：Flask、Django、FastAPI
• 数据分析：Pandas、NumPy、Matplotlib
• 自动化：Requests、Selenium、BeautifulSoup
• 人工智能：TensorFlow、PyTorch、Scikit-learn
• 数据库：SQLite、SQLAlchemy、MongoDB

练习题

1. 扩展通讯录系统，支持模糊搜索
2. 为爬虫添加深度爬取功能
3. 为数据分析工具添加导出图表功能
4. 为日志分析器添加按日期过滤功能