html2md.py 文件源码

def html_to_markdown(html):
    """convert html to markdown.
    this will try and convert span styling
    to the proper tags as well.

    e.g. `<span style='font-weight:bold;'>foo</span>`
    will become `<strong>foo</strong>`.
    """
    h = fromstring(html)

    clean_highlighted_code(h)
    for span in h.findall('.//span') + h.findall('.//font'):
        convert_span(span)

    html = tostring(h).decode('utf-8')

    # not ideal but works in a pinch
    html = html.replace('<mark>', '==')
    html = html.replace('</mark>', '==')

    md = to_md(html)

    # sometimes html2text returns a ton of extra whitespace.
    # clean up lines with only whitespace.
    # condense line break streaks of 3 or more.
    md = re.sub(r'\n([\s\*_]+)\n', '\n\n', md)
    md = re.sub(r'\n{3,}', '\n\n', md)

    return md