schema.py 文件源码

def get_title(html):
        """
            Get the title element from a HTML document

            :param str html: The html to parse

            :Example:

            >>> Link.get_title("xxxx<title>Title</title>xxxx")
            'Title'

            >>> print(Link.get_title("xxxx<>Title</title>xxxx"))
            None
        """
        bs = BeautifulSoup(html, 'html.parser', parse_only=SoupStrainer('title'))

        title = bs.find("title")
        if not title:
            return None

        if not title.string:
            return None

        return title.string.strip().replace('\n', ' ')