#!python
# -*- mode: python; Encoding: utf-8; coding: utf-8 -*-
# Last updated: <2025/04/03 20:39:21 +0900>
"""
HTML parse sample by BeautifulSoup4

Usage: python htmlparse01.py <html_file_path> [sjis|shift_jis|utf8|utf-8]

pip install beautifulsoup4

Windows10 x64 22H2 + Python 3.10.10 64bit
"""

import sys
import re
from bs4 import BeautifulSoup


usage_mes = "Usage: python htmlparse01.py <html_file_path> [sjis|shift_jis|utf8|utf-8]"


def extract_all_file_paths(html_file, charset):
    """
    ローカルHTMLファイルを読み込んで、
    href, img src, script src, CSS内ファイルパスを抽出する。

    Args:
        html_file (str): HTMLファイルのパス。
        charset (str): utf-8 or shift_jis

    Returns:
        tuple: href, img src, script src, CSS内ファイルパスのリストをタプルで返す
    """
    try:
        html = ""
        with open(html_file, "r", encoding=charset) as f:
            html = f.read()

        soup = BeautifulSoup(html, "html.parser")

        hrefs = [a["href"] for a in soup.find_all("a", href=True)]
        image_srcs = [img["src"] for img in soup.find_all("img", src=True)]
        script_srcs = [script["src"] for script in soup.find_all("script", src=True)]

        # スタイルシートファイルパスを抽出
        stylesheet_paths = []
        for link in soup.find_all("link", rel="stylesheet", href=True):
            stylesheet_paths.append(link["href"])

        for style in soup.find_all("style"):
            # styleタグ内のurl()関数で指定されたファイルパスを抽出
            urls = re.findall(r"url\(['\"]?([^'\")]+)['\"]?\)", style.text)
            stylesheet_paths.extend(urls)

        return hrefs, image_srcs, script_srcs, stylesheet_paths

    except FileNotFoundError:
        print(f"Error : Not found {html_file}")
        return [], [], [], []
    except Exception as e:
        print(f"Error : {e}")
        return [], [], [], []


def main():
    if len(sys.argv) == 2:
        html_file = sys.argv[1]
        charset = "utf-8"
    elif len(sys.argv) == 3:
        html_file = sys.argv[1]
        charset = sys.argv[2]
    else:
        print(usage_mes)
        sys.exit(1)

    if charset == "sjis":
        charset = "shift_jis"
    elif charset == "utf8":
        charset = "utf-8"

    hrefs, img_srcs, script_srcs, css_paths = extract_all_file_paths(html_file, charset)

    print("# href=")
    for href in sorted(list(set(hrefs))):
        print(href)

    print("# img src=")
    for src in sorted(list(set(img_srcs))):
        print(src)

    print("# script src=")
    for src in sorted(list(set(script_srcs))):
        print(src)

    print("# style src=")
    for path in sorted(list(set(css_paths))):
        print(path)


if __name__ == "__main__":
    main()