本次使用的是python语言

源码:

import tkinter as tk

from tkinter import ttk

import requests

import urllib3

import time

import random

urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)  # 禁用InsecureRequestWarning警告

# 创建事件处理函数

def crawl_website():

    url = url_entry.get()

    filename = filename_entry.get()

    

    feedback_text = "开始爬取网页..."

    update_status_bar(feedback_text)

    time.sleep(2)

    

    feedback_text = "完成页面爬取."

    update_status_bar(feedback_text)

    time.sleep(2)

    

    # 发送GET请求并获取网页源代码（忽略SSL证书验证错误）

    response = requests.get(url, verify=False)

    html_content = response.text

    

    time.sleep(1)

    

    # 如果文件名不包含后缀，则添加默认后缀

    if not filename.lower().endswith('.html'):

        filename += '.html'

        

    # 将网页源代码保存到文件中

    with open(filename, 'w', encoding='utf-8') as file:

        file.write(html_content)

    

    feedback_text = f"网页爬取成功并保存到文件: {filename}"

    update_status_bar(feedback_text)

# 创建主窗口

window = tk.Tk()

window.title("网站源代码爬取器")

window.geometry("400x300")

# 创建标签和输入框

tk.Label(window, text="网址:").grid(row=0, column=0, padx=10, pady=10)

url_entry = tk.Entry(window, width=30)

url_entry.grid(row=0, column=1, padx=10, pady=10)

tk.Label(window, text="保存文件名:").grid(row=1, column=0, padx=10, pady=10)

filename_entry = tk.Entry(window, width=30)

filename_entry.grid(row=1, column=1, padx=10, pady=10)

# 创建开始按钮

start_button = ttk.Button(window, text="开始", command=crawl_website)

start_button.grid(row=2, column=0, columnspan=2, padx=10, pady=10)

# 状态栏

status_var = tk.StringVar()

status_bar = ttk.Label(window, textvariable=status_var, anchor=tk.W)

status_bar.grid(row=3, column=0, columnspan=2, sticky=tk.W+tk.E)

# 更新状态栏

def update_status_bar(text):

    status_var.set(text)

    status_bar.update()

window.mainloop()

如有问题私信UP