Python文本处理：正则表达式实战提取链接和邮箱

运行效果

实例简介

使用 re 模块从文本中批量提取 URL 链接和邮箱地址，支持多种格式匹配。基于 Tkinter 的图形界面，输入文本后一键提取，结果清晰展示。

核心代码

import tkinter as tk
from tkinter import ttk, scrolledtext
import re
import platform

# 设置中文字体
CHINESE_FONT = "WenQuanYi Zen Hei" if platform.system() == "Linux" else "Microsoft YaHei"

class RegexExtractorApp:
    def __init__(self, root):
        self.root = root
        root.title("正则表达式提取工具")
        root.geometry("700x600")
        root.configure(bg="#f5f5f5")
        
        # 标题
        title_label = tk.Label(root, text="正则表达式实战：批量提取链接和邮箱", 
                              font=(CHINESE_FONT, 18, "bold"), bg="#f5f5f5", fg="#2c3e50")
        title_label.pack(pady=15)
        
        # 输入区域
        input_frame = tk.Frame(root, bg="#f5f5f5")
        input_frame.pack(padx=20, pady=10, fill="both", expand=True)
        
        tk.Label(input_frame, text="请输入待提取文本：", 
                font=(CHINESE_FONT, 12, "bold"), bg="#f5f5f5", fg="#34495e").pack(anchor="w", pady=5)
        
        self.text_input = scrolledtext.ScrolledText(input_frame, height=8, 
                                                     font=(CHINESE_FONT, 11), wrap=tk.WORD)
        self.text_input.pack(fill="both", expand=True, pady=5)
        
        # 示例文本
        sample_text = """联系我：test@example.com 或 admin@51python.com
访问网站：https://www.haolizi.com 和 http://blog.example.org
我的邮箱是 user.name@domain.cn，官网：https://api.mysite.com/v1
"""
        self.text_input.insert("1.0", sample_text)
        
        # 按钮区域
        btn_frame = tk.Frame(root, bg="#f5f5f5")
        btn_frame.pack(pady=10)
        
        extract_btn = tk.Button(btn_frame, text="提取链接和邮箱", 
                               font=(CHINESE_FONT, 12, "bold"),
                               bg="#3498db", fg="white", padx=20, pady=10,
                               command=self.extract_content, cursor="hand2")
        extract_btn.pack(side="left", padx=10)
        
        clear_btn = tk.Button(btn_frame, text="清空", 
                             font=(CHINESE_FONT, 12),
                             bg="#95a5a6", fg="white", padx=20, pady=10,
                             command=self.clear_results, cursor="hand2")
        clear_btn.pack(side="left", padx=10)
        
        # 结果区域
        result_frame = tk.Frame(root, bg="#f5f5f5")
        result_frame.pack(padx=20, pady=10, fill="both", expand=True)
        
        tk.Label(result_frame, text="提取结果：", 
                font=(CHINESE_FONT, 12, "bold"), bg="#f5f5f5", fg="#34495e").pack(anchor="w", pady=5)
        
        self.result_text = scrolledtext.ScrolledText(result_frame, height=6, 
                                                      font=(CHINESE_FONT, 11), wrap=tk.WORD,
                                                      bg="#ecf0f1")
        self.result_text.pack(fill="both", expand=True, pady=5)
        
        # 统计信息
        self.stats_label = tk.Label(root, text="等待提取...", 
                                   font=(CHINESE_FONT, 11), bg="#f5f5f5", fg="#7f8c8d")
        self.stats_label.pack(pady=10)
    
    def extract_content(self):
        """提取链接和邮箱"""
        text = self.text_input.get("1.0", tk.END)
        
        # 正则表达式
        url_pattern = r'https?://[^\s<>"]+|www\.[^\s<>"]+'
        email_pattern = r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}'
        
        urls = re.findall(url_pattern, text)
        emails = re.findall(email_pattern, text)
        
        # 去重
        urls = list(dict.fromkeys(urls))
        emails = list(dict.fromkeys(emails))
        
        # 显示结果
        result = "【提取的链接】\n"
        for i, url in enumerate(urls, 1):
            result += f"{i}. {url}\n"
        
        result += "\n【提取的邮箱】\n"
        for i, email in enumerate(emails, 1):
            result += f"{i}. {email}\n"
        
        self.result_text.delete("1.0", tk.END)
        self.result_text.insert("1.0", result)
        
        # 更新统计
        self.stats_label.config(
            text=f"✅ 提取完成：找到 {len(urls)} 个链接，{len(emails)} 个邮箱",
            fg="#27ae60"
        )
    
    def clear_results(self):
        """清空结果"""
        self.result_text.delete("1.0", tk.END)
        self.stats_label.config(text="等待提取...", fg="#7f8c8d")

def create_gui():
    root = tk.Tk()
    app = RegexExtractorApp(root)
    root.mainloop()

if __name__ == "__main__":
    create_gui()

适用场景

数据清洗、信息采集、日志分析、文本处理