zhang_crawl_bio/tests/mytest/news_paper_t.py

from newspaper import Article
import os

def main():
    # 本地 HTML 文件路径
    file_path = r"K:\code\upwork\zhang_crawl_bio\output\google_search\Acalypha martiana essential oil\all_page_html\3.html"
    
    # 读取本地 HTML 文件内容
    with open(file_path, 'r', encoding='utf-8') as file:
        html_content = file.read()

    # 创建一个 Article 对象
    first_article = Article(url='', language='en')
    
    # 手动设置 HTML 内容
    first_article.set_html(html_content)
    
    # 解析文章
    first_article.parse()

    # 打印文章标题和附加数据
    print(first_article.title)
    print(first_article.authors)
    print(first_article.additional_data)
    print(f"summary {first_article.summary}")
    print(f"url {first_article.url}")

if __name__ == "__main__":
    main()