2.5《Python3 网络爬虫开发实战》学习之实例实战1

import requests
from bs4 import BeautifulSoup

# 获取网页内容的函数
def get_html_content(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        else:
            return "网页获取失败，状态码：" + str(response.status_code)
    except requests.exceptions.RequestException:
        return "请求异常"

# 解析网页并提取标题的函数
def parse_html_extract_title(html_content):
    soup = BeautifulSoup(html_content, 'html.parser')
    title = soup.find('title')
    if title:
        return title.string
    else:
        return "未找到标题"

# 主函数
def main():
    url = "https://www.python.org"
    html_content = get_html_content(url)
    print(parse_html_extract_title(html_content))

# 如果这个脚本被直接运行，则执行main函数
if __name__ == "__main__":
    main()