Python实现百度搜索爬虫: 支持图片展示和随机延迟

以下是经过修改的完整代码：

import requests
from bs4 import BeautifulSoup
import time
import tkinter as tk
import webbrowser
from PIL import ImageTk, Image
import random

def crawl_baidu(keyword):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
    }
    url = f'https://www.baidu.com/s?wd={keyword}'

    # 添加随机延迟
    delay = random.uniform(0.5, 1.5)
    time.sleep(delay)

    response = requests.get(url, headers=headers)
    soup = BeautifulSoup(response.text, 'html.parser')

    results = []
    for result in soup.find_all('div', class_='result'):
        result_title = result.find('h3').get_text()
        result_url = result.find('a')['href']
        result_image = result.find('img')

        if result_image:
            result_image_url = result_image['src']
        else:
            result_image_url = None

        results.append((result_title, result_url, result_image_url))

    return results

def open_url(url):
    webbrowser.open(url)

def show_image(image_url):
    image_response = requests.get(image_url)
    image_data = image_response.content
    image = Image.open(io.BytesIO(image_data))
    image.show()

def search():
    keyword = entry.get()
    search_results = crawl_baidu(keyword)
    if len(search_results) > 0:
        for index, (title, url, image_url) in enumerate(search_results, start=1):
            result_text.insert(tk.END, f'{index}. ', 'index')
            result_text.insert(tk.END, f'{title}
', 'title')
            result_text.insert(tk.END, url, 'link')
            result_text.tag_configure('link', foreground='blue', underline=True)
            result_text.tag_bind('link', '<Button-1>', lambda event, url=url: open_url(url))
            result_text.insert(tk.END, '
')

            if image_url:
                result_text.image_create(tk.END, image=image_url, padx=10, pady=10)
                result_text.tag_bind('img', '<Button-1>', lambda event, image_url=image_url: show_image(image_url))
                result_text.insert(tk.END, '
')

        result_text.insert(tk.END, '
')
    else:
        result_text.insert(tk.END, '没有搜索结果
')

# 创建UI界面
window = tk.Tk()
window.title('百度搜索')
window.geometry('800x600')

label = tk.Label(window, text='请输入关键词:')
label.pack()

entry = tk.Entry(window)
entry.pack()

search_button = tk.Button(window, text='搜索', command=search)
search_button.pack()

scrollbar = tk.Scrollbar(window)
scrollbar.pack(side=tk.RIGHT, fill=tk.Y)

result_text = tk.Text(window, yscrollcommand=scrollbar.set)
result_text.pack(fill=tk.BOTH)

scrollbar.config(command=result_text.yview)

window.mainloop()

该代码实现了以下功能：

• 爬取百度搜索结果的标题、链接和图片。
• 在结果列表中展示图片，点击图片可以查看大图。
• 加入随机延迟功能，模拟真实用户行为，避免被网站封禁。

希望这个代码能够帮助你了解如何编写Python爬虫程序。