使用Python和BeautifulSoup从HTML页面高效提取H3标签文本

pip install requests beautifulsoup4 html5lib

import requests

# 替换为你要抓取的网页URL
url = 'https://example.com/your-page.html' # 实际使用时请替换为目标URL
try:
    response = requests.get(url)
    response.raise_for_status()  # 检查请求是否成功 (200 OK)
    response.encoding = 'utf-8'  # 明确指定编码，防止中文乱码
    html_content = response.text
    print("HTML内容获取成功！")
except requests.exceptions.RequestException as e:
    print(f"请求发生错误: {e}")
    html_content = None

# 如果你有一个本地HTML字符串，可以直接使用它进行测试
# html_content = """
# <h3 id="basics">1. Creating a Web Page</h3>
# <p>
# Once you've made your "home page" (index.html) you can add more pages to
# your site, and your home page can link to them.
# <h3 id="syntax">>2. HTML Syntax</h3>
# <p>Some other content...</p>
# <h3>3. Another Section Title</h3>
# """

from bs4 import BeautifulSoup

if html_content:
    # 使用BeautifulSoup和html5lib解析HTML
    soup = BeautifulSoup(html_content, "html5lib")
    print("HTML解析成功！")
else:
    print("无法解析HTML，因为未获取到内容。")
    soup = None

if soup:
    # 查找页面中所有的h3标签
    list_h3_tags = soup.find_all('h3')

    print("\n提取到的H3标签文本：")
    if list_h3_tags:
        for h3_tag in list_h3_tags:
            # .text 属性用于获取标签内部的纯文本内容
            print(h3_tag.text.strip()) # .strip() 用于移除文本两端的空白字符
    else:
        print("页面中未找到任何h3标签。")

import requests
from bs4 import BeautifulSoup

def extract_h3_text_from_url(url):
    """
    从指定URL的HTML页面中提取所有h3标签的文本内容。

    Args:
        url (str): 目标网页的URL。

    Returns:
        list: 包含所有h3标签文本的列表，如果获取或解析失败则返回空列表。
    """
    h3_texts = []
    try:
        # 1. 获取HTML内容
        response = requests.get(url, timeout=10) # 设置超时时间
        response.raise_for_status()  # 检查请求是否成功
        response.encoding = 'utf-8'  # 明确指定编码
        html_content = response.text
        print(f"成功获取URL: {url}")

        # 2. 使用BeautifulSoup解析HTML
        soup = BeautifulSoup(html_content, "html5lib")
        print("HTML解析成功。")

        # 3. 查找并提取H3标签文本
        list_h3_tags = soup.find_all('h3')

        if list_h3_tags:
            print("\n--- 提取到的H3标签文本 ---")
            for h3_tag in list_h3_tags:
                text = h3_tag.text.strip()
                h3_texts.append(text)
                print(text)
            print("--------------------------")
        else:
            print("页面中未找到任何h3标签。")

    except requests.exceptions.Timeout:
        print(f"请求超时: {url}")
    except requests.exceptions.RequestException as e:
        print(f"请求或网络错误: {e}")
    except Exception as e:
        print(f"发生未知错误: {e}")

    return h3_texts

# --- 运行示例 ---
if __name__ == "__main__":
    # 请替换为你要测试的实际URL
    target_url = 'https://www.example.com' # 这是一个通用示例，实际测试请用包含h3标签的页面
    # 模拟一个包含h3标签的HTML字符串进行测试
    # target_url = 'data:text/html;charset=utf-8,<h3 id="basics">1. Creating a Web Page</h3><p>Content.</p><h3 id="syntax">>2. HTML Syntax</h3><h3>3. Another Title</h3>'

    extracted_data = extract_h3_text_from_url(target_url)
    print(f"\n最终提取数据列表: {extracted_data}")