"""
HTML extractor using markdownify.
"""

from pathlib import Path

from markitect.proxy.extractors.base import BaseExtractor
from markitect.proxy.models import ExtractionResult
from markitect.proxy.exceptions import DependencyMissingError


class HtmlExtractor(BaseExtractor):
    """Converts HTML files to Markdown via markdownify."""

    name = "html"
    version = "1.0"
    extensions = (".html", ".htm")

    def check_dependencies(self) -> bool:
        try:
            import markdownify  # noqa: F401
            return True
        except ImportError:
            return False

    def dependency_hint(self) -> str:
        return 'pip install "markitect[proxy-html]"  (or: pip install markdownify)'

    def extract(self, source_path: Path) -> ExtractionResult:
        if not self.check_dependencies():
            raise DependencyMissingError(
                "markdownify is required to extract HTML files.",
                package="markdownify",
                install_hint=self.dependency_hint(),
            )

        import markdownify

        html_content = source_path.read_text(encoding="utf-8")
        md_text = markdownify.markdownify(html_content, heading_style="ATX")
        return ExtractionResult(
            content=md_text,
            extractor=self.name,
            extractor_version=self.version,
        )