本次使用的是python語(yǔ)言

源碼:

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

# 創(chuàng)建事件處理函數(shù)

def crawl_website():

? ? url = url_entry.get()

? ? filename = filename_entry.get()

? ??

? ? feedback_text = "開(kāi)始爬取網(wǎng)頁(yè)..."

? ? update_status_bar(feedback_text)

? ? time.sleep(2)

? ??

? ? feedback_text = "完成頁(yè)面爬取."

? ? update_status_bar(feedback_text)

? ? time.sleep(2)

? ??

? ? # 發(fā)送GET請(qǐng)求并獲取網(wǎng)頁(yè)源代碼（忽略SSL證書(shū)驗(yàn)證錯(cuò)誤）

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

? ? html_content = response.text

? ??

? ? time.sleep(1)

? ??

? ? # 如果文件名不包含后綴，則添加默認(rèn)后綴

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

? ? ? ? filename += '.html'

? ? ? ??

? ? # 將網(wǎng)頁(yè)源代碼保存到文件中

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

? ? ? ? file.write(html_content)

? ??

? ? feedback_text = f"網(wǎng)頁(yè)爬取成功并保存到文件: {filename}"

? ? update_status_bar(feedback_text)

# 創(chuàng)建主窗口

window = tk.Tk()

window.title("網(wǎng)站源代碼爬取器")

window.geometry("400x300")

# 創(chuàng)建標(biāo)簽和輸入框

tk.Label(window, text="網(wǎng)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)

# 創(chuàng)建開(kāi)始按鈕

start_button = ttk.Button(window, text="開(kāi)始", command=crawl_website)

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

# 狀態(tài)欄

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?tīng)顟B(tài)欄

def update_status_bar(text):

? ? status_var.set(text)

? ? status_bar.update()

window.mainloop()

如有問(wèn)題私信UP