url.py 文件源码

def detect_language(html) :
    """
    Detect the language of the text content of a page.
    """
    # handle string, need bytes
    try :
        html = html.decode("utf8")
    except :
        try :
            html = html.decode("latin1")
        except :
            pass
    h = html2text.HTML2Text()
    return langdetect.detect(h.handle(html))