Python 爬虫入门：用 requests + BeautifulSoup 抓取网页标题

pip install requests beautifulsoup4

import requests
from bs4 import BeautifulSoup

def fetch_page(url: str) -> str:
    """获取网页 HTML 内容"""
    headers = {
        "User-Agent": "Mozilla/5.0 (compatible; PythonLearningBot/1.0)"
    }
    response = requests.get(url, headers=headers, timeout=10)
    response.encoding = response.apparent_encoding
    response.raise_for_status()
    return response.text

def parse_page(html: str):
    """解析网页标题和链接"""
    soup = BeautifulSoup(html, "html.parser")

    title = soup.title.string if soup.title else "未找到标题"

    links = []
    for a in soup.find_all("a", href=True):
        text = a.get_text(strip=True)
        href = a["href"]
        if text and href:
            links.append({"text": text, "href": href})

    return title, links

def save_to_txt(title: str, links: list, filename: str = "result.txt"):
    """将结果保存到文本文件"""
    with open(filename, "w", encoding="utf-8") as f:
        f.write(f"页面标题：{title}\n")
        f.write("=" * 40 + "\n")
        for i, link in enumerate(links, 1):
            f.write(f"{i}. {link['text']} | {link['href']}\n")

def main():
    url = "https://wlt.nz826.com/"  # 示例练习网站
    print(f"正在抓取：{url}")

    html = fetch_page(url)
    title, links = parse_page(html)

    print(f"页面标题：{title}")
    print(f"共找到 {len(links)} 个链接")

    save_to_txt(title, links)
    print("结果已保存到 result.txt")

if __name__ == "__main__":
    main()

def main():
    url = "https://wlt.nz826.com/"
    try:
        print(f"正在抓取：{url}")
        html = fetch_page(url)
        title, links = parse_page(html)

        print(f"页面标题：{title}")
        print(f"共找到 {len(links)} 个链接")

        save_to_txt(title, links)
        print("结果已保存到 result.txt")
    except requests.exceptions.RequestException as e:
        print(f"请求失败：{e}")
    except Exception as e:
        print(f"运行出错：{e}")