Python striptags示例

示例#1

文件： html.py 项目： gdgkyoto/kyoto-gtug

def plaintext(text, keeplinebreaks=True):
    if isinstance(text, Fragment):
        text = text.generate().render('text', encoding=None)
    else:
        text = stripentities(striptags(text))
    if not keeplinebreaks:
        text = text.replace(u'\n', u' ')
    return text

示例#2

文件： html.py 项目： wiraqutra/photrackjp

def plaintext(text, keeplinebreaks=True):
    if isinstance(text, Fragment):
        text = text.generate().render('text', encoding=None)
    else:
        text = stripentities(striptags(text))
    if not keeplinebreaks:
        text = text.replace(u'\n', u' ')
    return text

示例#3

def plaintext(text, keeplinebreaks=True):
    """Extract the text elements from (X)HTML content

    :param text: `unicode` or `genshi.builder.Fragment`
    :param keeplinebreaks: optionally keep linebreaks
    """
    if isinstance(text, Fragment):
        text = text.generate().render('text', encoding=None)
    else:
        text = stripentities(striptags(text))
    if not keeplinebreaks:
        text = text.replace(u'\n', u' ')
    return text

示例#4

文件： html.py 项目： thimalk/bloodhound

def plaintext(text, keeplinebreaks=True):
    """Extract the text elements from (X)HTML content

    :param text: `unicode` or `genshi.builder.Fragment`
    :param keeplinebreaks: optionally keep linebreaks
    """
    if isinstance(text, Fragment):
        text = text.generate().render('text', encoding=None)
    else:
        text = stripentities(striptags(text))
    if not keeplinebreaks:
        text = text.replace(u'\n', u' ')
    return text