def process_html(cls, text: str, environment: TypographEnvironment = None, encoding: str = 'utf-8',
autolink: bool = True) -> str:
"""
:param text: html text
:param environment: TypographSettings
:param encoding: text endocing
:param autolink: convert all in-text url adress into links
:return:
"""
if environment is None:
environment = get_default_environment()
node = html.fromstring(text)
cls._process_node(node, environment)
if autolink:
clean.autolink(node, [cls.AUTOLINK_REGEX], avoid_hosts=[])
text_processed = html.tostring(node, encoding=encoding).decode(encoding)
return text_processed.replace(cls.VERBATIM, '&')
def _to_python(self, value, state):
try:
from lxml.html.clean import Cleaner, autolink, word_break
from lxml.html import fragment_fromstring
from lxml.etree import tostring
allowed_attributes = ['href', 'target', 'rel', 'name', 'title', 'src', 'width', 'height', 'alt']
cleaner = Cleaner(style=True, add_nofollow=True, allow_tags=['div', 'p', 'br', 'a', 'strong', 'b', 'blockquote', 'em', 'i', 'img', 'u', 's', 'del'], remove_unknown_tags=False)
fragment = fragment_fromstring(value.replace("\r\n", "<br>").replace("\n", "<br>").replace("\r", "<br>"), create_parent='div')
for element in fragment.xpath('//*[@*]'):
for ek in element.attrib.iterkeys():
if ek not in allowed_attributes:
del element.attrib[ek]
cleaner(fragment)
autolink(fragment)
word_break(fragment)
return tostring(fragment)
except:
raise formencode.Invalid(self.message('invalidHTML', state), value, state)
def fix_links(doc):
autolink(doc)
for link in doc.xpath('//a[@href]'):
link.attrib['target'] = '_blank'
return doc
def autolink(doc):
"""Replace http:// strings (texts) with HTML links.
See http://lxml.de/lxmlhtml.html, section autolink."""
clean.autolink(doc)
return doc
def autolink(doc):
"""Replace http:// strings (texts) with HTML links.
See http://lxml.de/lxmlhtml.html, section autolink."""
clean.autolink(doc)
return doc
