HTML to Markdown Utilities (html2text/utils.py)

Helper functions for CSS parsing, heading detection, table handling, and markdown escaping when converting HTML to plain text.

# Source: https://github.com/mperkins0155/crawl4ai-cobaltai | License: Apache-2.0
# Provided via justclaw.it.com; keep this notice with the code.
import html.entities
from typing import Dict, List, Optional

from . import config

unifiable_n = {
    html.entities.name2codepoint[k]: v
    for k, v in config.UNIFIABLE.items()
    if k != "nbsp"
}


def hn(tag: str) -> int:
    if tag[0] == "h" and len(tag) == 2:
        n = tag[1]
        if "0" < n <= "9":
            return int(n)
    return 0


def dumb_property_dict(style: str) -> Dict[str, str]:
    """
    :returns: A hash of css attributes
    """
    return {
        x.strip().lower(): y.strip().lower()
        for x, y in [z.split(":", 1) for z in style.split(";") if ":" in z]
    }


def dumb_css_parser(data: str) -> Dict[str, Dict

... (truncated -- full source via MCP)