def clean_text(
self,
text: str,
fuzzy: bool = False,
format: Optional[str] = None,
proxy: Optional["EntityProxy"] = None,
) -> Optional[str]:
"""Parse and normalize an email address.
Returns None if this is not an email address.
"""
email = strip_quotes(text)
if email is None or not self.REGEX.match(email):
return None
mailbox, domain = email.rsplit("@", 1)
# TODO: https://pypi.python.org/pypi/publicsuffix/
# handle URLs by extracting the domain name
domain = urlparse(domain).hostname or domain
domain = domain.lower()
domain = domain.rstrip(".")
# handle unicode
domain = domain.encode("idna").decode("ascii")
if domain is not None and mailbox is not None:
return "@".join((mailbox, domain))
return None
def clean_text(
self,
text: str,
fuzzy: bool = False,
format: Optional[str] = None,
proxy: Optional["EntityProxy"] = None,
) -> Optional[str]:
"""Basic clean-up."""
name = strip_quotes(text)
return collapse_spaces(name)
def clean_text(self, email, **kwargs):
"""Parse and normalize an email address.
Returns None if this is not an email address.
"""
email = strip_quotes(email)
if not self.EMAIL_REGEX.match(email):
return None
mailbox, domain = email.rsplit('@', 1)
domain = self.domains.clean(domain, **kwargs)
if domain is not None and mailbox is not None:
return '@'.join((mailbox, domain))
def clean_text(self, name, **kwargs):
"""Basic clean-up."""
name = strip_quotes(name)
name = collapse_spaces(name)
return name
