python爬取网页信息并保存为word文件

我们需要requests BeautifulSoup python-docx库：

pip install requests
pip install beautifulsoup4
pip install python-docx

import requests
from bs4 import BeautifulSoup
from docx import Document

def get_webpage_text(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    paragraphs = soup.find_all('p')  # 根据网页结构调整选择器，提取文章段落
    text_content = ''
    for paragraph in paragraphs:
        text_content += paragraph.get_text() + '\n'
    return text_content

def save_as_word(text_content, output_path):
    doc