utils to clean html

html.py

# coding: utf-8
# bleach==1.2.2
# beautifulsoup4==4.3.2


from bleach import clean
from bs4 import BeautifulSoup


ALLOWED_TAGS = [
    'font', 'del', 'br', 'a', 'p', 'img', 'blockquote',
    'span', 'strong', 'em', 'pre', 'code', 'ul', 'ol',
    'li', 'iframe', 'strong', 'i', 'hr', 'h1', 'h2',
    'h3', 'h4', 'h5', 'h6', 'table', 'tbody', 'th', 'tr', 'td'
]

ALLOWED_STYLES = [
    'background',
    'background-color',
    'background-image',
    'background-position',
    'background-repeat',
    'background-size',
    'border',
    'border-bottom',
    'border-bottom-color',
    'border-bottom-left-radius',
    'border-bottom-right-radius',
    'border-bottom-style',
    'border-bottom-width',
    'border-collapse',
    'border-color',
    'border-left',
    'border-left-color',
    'border-left-style',
    'border-left-width',
    'border-radius',
    'border-right',
    'border-right-color',
    'border-right-style',
    'border-right-width',
    'border-spacing',
    'border-style',
    'border-top',
    'border-top-color',
    'border-top-left-radius',
    'border-top-right-radius',
    'border-top-style',
    'border-top-width',
    'border-width',
    'bottom',
    'box-shadow',
    'clear',
    'color',
    'content',
    'cursor',
    'display',
    'float',
    'font',
    'font-family',
    'font-size',
    'font-size-adjust',
    'font-stretch',
    'font-style',
    'font-variant',
    'font-weight',
    'height',
    'left',
    'line-height',
    'list-style',
    'list-style-image',
    'list-style-position',
    'list-style-type',
    'margin',
    'margin-bottom',
    'margin-left',
    'margin-right',
    'margin-top',
    'max-height',
    'max-width',
    'min-height',
    'min-width',
    'opacity',
    'outline',
    'outline-color',
    'outline-offset',
    'outline-style',
    'outline-width',
    'overflow',
    'overflow-style',
    'overflow-x',
    'overflow-y',
    'padding',
    'padding-bottom',
    'padding-left',
    'padding-right',
    'padding-top',
    'position',
    'quotes',
    'resize',
    'right',
    'text-align',
    'text-align-last',
    'text-decoration',
    'text-emphasis',
    'text-height',
    'text-indent',
    'text-justify',
    'text-outline',
    'text-overflow',
    'text-shadow',
    'text-transform',
    'text-wrap',
    'top',
    'vertical-align',
    'visibility',
    'white-space',
    'white-space-collapse',
    'width',
    'word-break',
    'word-spacing',
    'word-wrap',
    'z-index'
]

ALLOWED_ATTRIBUTES = [
    'href', 'style', 'target', 'title', 'width', 'height', 'src', 'frameborder', 'allowfullscreen',
    'webkitAllowFullScreen', 'mozallowfullscreen', 'color'
]


def clean_html(html):

    return clean(
        html,
        tags=ALLOWED_TAGS,
        attributes=ALLOWED_ATTRIBUTES,
        styles=ALLOWED_STYLES,
        strip=False,
        strip_comments=True
    )


def split_by_separator(content, separator):
    if separator not in content:
        return content
    return content.split(separator, 1)[0]


def prettify_html(content):
    tree = BeautifulSoup(content, "html.parser")
    return tree.prettify()