import os

from article_analyzer import ArticleAnalyzer

def read_html_files(folder_path):
    html_contents = {}
    for root, _, files in os.walk(folder_path):
        for file in files:
            if file.endswith(".html"):
                file_path = os.path.join(root, file)
                with open(file_path, "r", encoding="utf-8") as f:
                    html_contents[file_path] = f.read()
    return html_contents


if __name__ == "__main__":
    analyzer = ArticleAnalyzer()

    html_files = read_html_files("./data")
    print(f"Parsed {len(html_files)} html files")

    for file, content in html_files.items():
        result = analyzer.classify_article(content)
        print(f"article [{file}] - analyzed as [{result}]\n")