🐍 三步流程

# ========================================
# 示例：爬虫三步骨架
# 说明：伪代码展示流程
# ========================================
import requests
import re
import json

# 1. 下载
url = 'https://httpbin.org/html'
r = requests.get(url, timeout=10)
html = r.text

# 2. 解析（正则提取 h1 文字）
titles = re.findall(r'<h1>(.*?)</h1>', html)

# 3. 存储
with open('result.json', 'w', encoding='utf-8') as f:
    json.dump({'titles': titles}, f, ensure_ascii=False)
print('完成', titles)