python 实现博客园文章导出为word文档

确保安装了以下Python库：

import requests
from bs4 import BeautifulSoup
from docx import Document
from docx.shared import Pt
from docx.oxml.ns import qn


# 函数：获取博客园文章内容
def get_blog_article(url):
    headers = {
        'User-Agent': 'Your User Agent'  # 替换为你的浏览器User-Agent
    }
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        return response.text
    else:
        print(f"Failed to retrieve article. Status code: {response.status_code}")
        return None


# 函数：解析HTML内容，提取标题和正文
def parse_article(html):
    soup = BeautifulSoup(html, 'html.parser')
    title = soup.find('a', id='cb_post_title_url').text.strip()
    content_tag = soup.find('div', id='cnblogs_post_body')
    paragraphs = content_tag.find_all('p')
    content = '\n'.join([p.get_text(strip=True) for p in paragraphs])
    return title, content


# 函数：生成Word文档
def create_word_document(title, content, filename):
    doc = Document()
    # 设置文档标题
    doc.add_heading(title, level=1).alignment = 1  # 标题居中
    # 添加正文内容
    paragraph = doc.add_paragraph(content)
    # 设置正文字体样式
    run = paragraph.add_run()
    run.font.size = Pt(12)
    run.font.name = '宋体'
    run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')  # 设置中文字体

    # 保存文档
    doc.save(filename)
    print(f"Word document '{filename}' created successfully.")


# 主函数
if __name__ == "__main__":
    # 示例博客园文章链接
    blog_url = 'https://www.cnblogs.com/your-article-url'

    # 获取文章内容
    html_content = get_blog_article(blog_url)
    if html_content:
        # 解析文章
        article_title, article_content = parse_article(html_content)

        # 生成Word文档
        output_filename = 'blog_article.docx'
        create_word_document(article_title, article_content, output_filename)
    else:
        print("Failed to fetch article content.")

 主要注意的是：

1.'User-Agent': 'Your User Agent'  # 替换为你的浏览器User-Agent
打开任意浏览器，在网址上输入about://version，按回车。（即可查看你自己浏览器的用户代理）

一些示例用户代理字符串：

• Chrome浏览器：Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36
• Firefox浏览器：Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:93.0) Gecko/20100101 Firefox/93.0
• Safari浏览器：Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.3 Safari/605.1.15

 2.

 # 示例博客园文章链接
    blog_url = 'https://www.cnblogs.com/your-article-url'
示例：我的其中一篇博客url:https://www.cnblogs.com/2022-yang/p/18252952

 # 生成Word文档
output_filename = 'blog_article.docx'

blog_article.docx为word文档名称

唯一的就是只能一篇一篇的导。