utils.py 文件源码

def parse_html(html_file):
    """
    Read the HTML file using lxml's HTML parser, but convert to Unicode
    using Beautiful Soup's UnicodeDammit class.

    Can raise LxmlError or TypeError if the file can't be opened or
    parsed.
    """
    unicode_html = UnicodeDammit(html_file, smart_quotes_to="html",
                                 is_html=True)
    if unicode_html.unicode_markup is None:
        raise ValueError("no HTML provided")
    if not unicode_html.unicode_markup:
        raise ValueError("could not detect character encoding")
    return lxml.html.fromstring(unicode_html.unicode_markup)