python 实现博客园文章导出为word文档

确保安装了以下Python库：

pip install requests beautifulsoup4 python-doc

 

import requests
from bs4 import BeautifulSoup
from docx import Document
from docx.shared import Inches
from urllib.parse import urljoin
import os

def get_article_content(url):
    response = requests.get(url)
    response.raise_for_status()
    soup = BeautifulSoup(response.content, 'html.parser')

    title = soup.find('h1').get_text()
    article_body = soup.find('div', {'id': 'cnblogs_post_body'})  # 根据实际情况调整选择器

    return title, article_body

def add_text_to_doc(doc, text):
    doc.add_paragraph(text)

def add_image_to_doc(doc, image_url):
    response = requests.get(image_url)
    response.raise_for_status()
    with open('temp_image', 'wb') as file:
        file.write(response.content)
    doc.add_picture('temp_image', width=Inches(6))
    os.remove('temp_image')  # 删除临时图片文件

def process_article_to_word(article_url, output_filename):
    title, content = get_article_content(article_url)
    doc = Document()
    doc.add_heading(title, level=1)

    for element in content.descendants:
        if element.name == 'p':
            add_text_to_doc(doc, element.get_text())
        elif element.name == 'img':
            img_url = urljoin(article_url, element['src'])
            add_image_to_doc(doc, img_url)

    doc.save(output_filename)
    print(f'Article saved to {output_filename}')

if __name__ == '__main__':
    article_url = 'https://www.cnblogs.com/2022-yang/p/18236357'  # 替换为实际的博客园文章 URL
    output_filename = 'bo.docx'
    process_article_to_word(article_url, output_filename)

 

 主要注意的是：

1

 # 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

2

# 生成Word文档
output_filename = 'bo.docx'

bo.docx为word文档名称

唯一的就是只能一篇一篇的导,好像确实没有必要。