📋 功能说明

• 自动化百度搜索
• 批量关键词查询
• 搜索结果数据采集

💻 源代码

import requests
from bs4 import BeautifulSoup
import urllib.parse

def baidu_search(keyword, num=10):
    """百度搜索"""
    headers = {
        'User-Agent': 'Mozilla/5.0 Chrome/91.0.4472.124'
    }
    
    results = []
    for i in range(0, num, 10):
        url = f'https://www.baidu.com/s?wd={urllib.parse.quote(keyword)}&pn={i}'
        res = requests.get(url, headers=headers)
        soup = BeautifulSoup(res.text, 'html.parser')
        
        for item in soup.select('.result'):
            title = item.select_one('h3 a')
            if title:
                results.append({
                    'title': title.text,
                    'url': title['href'],
                    'abstract': item.select_one('.c-abstract').text if item.select_one('.c-abstract') else ''
                })
        
        if i >= 50:  # 最多5页
            break
            
    return results

def get_baidu_suggest(keyword):
    """获取百度联想词"""
    url = f'https://suggestion.baidu.com/su?wd={urllib.parse.quote(keyword)}&cb='
    headers = {'User-Agent': 'Mozilla/5.0'}
    res = requests.get(url, headers=headers)
    # 解析JSONP响应
    return res.text

# 示例
results = baidu_search('Python教程', 30)
for r in results[:10]:
    print(f"标题: {r['title']}")

📦 运行环境

pip install requests beautifulsoup4

---

功能特点

• ✅ 多页采集
• ✅ 联想词获取
• ✅ 结果去重