Skip to main content
added 5 characters in body
Source Link
Fedor
  • 24.3k
  • 43
  • 59
  • 185

def url_validator(url: str) -> bool: """ use this func to filter out the urls to follow only valid urls :param: url :type: str :return: True if the passed url is valid otherwise return false :rtype: bool """

def url_validator(url: str) -> bool:
    """
    use this func to filter out the urls to follow only valid urls
    :param: url
    :type: str
    :return: True if the passed url is valid otherwise return false
    :rtype: bool
    """

    #the following regex is copied from Django source code 
    # to validate a url using regax
    
    regex = re.compile(
        r"^(?:http|ftp)s?://"  # http:// or https://
        r"(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+(?:[A-Z]{2,6}\.?|[A-Z0-9-]{2,}\.?)|"  # domain...
        r"localhost|"  # localhost...
        r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})"  # ...or ip
        r"(?::\d+)?"  # optional port
        r"(?:/?|[/?]\S+)$",
        re.IGNORECASE,
    )


    blocked_sites: list[str] = []

    for site in blocked_sites:
        if site in url or site == url:
            return False

    # if none of the above then ensure that the url is valid and then return True otherwise return False
    if re.match(regex, url):
        return True

    return False

def url_validator(url: str) -> bool: """ use this func to filter out the urls to follow only valid urls :param: url :type: str :return: True if the passed url is valid otherwise return false :rtype: bool """

#the following regex is copied from Django source code 
# to validate a url using regax

regex = re.compile(
    r"^(?:http|ftp)s?://"  # http:// or https://
    r"(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+(?:[A-Z]{2,6}\.?|[A-Z0-9-]{2,}\.?)|"  # domain...
    r"localhost|"  # localhost...
    r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})"  # ...or ip
    r"(?::\d+)?"  # optional port
    r"(?:/?|[/?]\S+)$",
    re.IGNORECASE,
)


blocked_sites: list[str] = []

for site in blocked_sites:
    if site in url or site == url:
        return False

# if none of the above then ensure that the url is valid and then return True otherwise return False
if re.match(regex, url):
    return True

return False
def url_validator(url: str) -> bool:
    """
    use this func to filter out the urls to follow only valid urls
    :param: url
    :type: str
    :return: True if the passed url is valid otherwise return false
    :rtype: bool
    """

    #the following regex is copied from Django source code 
    # to validate a url using regax
    
    regex = re.compile(
        r"^(?:http|ftp)s?://"  # http:// or https://
        r"(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+(?:[A-Z]{2,6}\.?|[A-Z0-9-]{2,}\.?)|"  # domain...
        r"localhost|"  # localhost...
        r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})"  # ...or ip
        r"(?::\d+)?"  # optional port
        r"(?:/?|[/?]\S+)$",
        re.IGNORECASE,
    )


    blocked_sites: list[str] = []

    for site in blocked_sites:
        if site in url or site == url:
            return False

    # if none of the above then ensure that the url is valid and then return True otherwise return False
    if re.match(regex, url):
        return True

    return False
Source Link

def url_validator(url: str) -> bool: """ use this func to filter out the urls to follow only valid urls :param: url :type: str :return: True if the passed url is valid otherwise return false :rtype: bool """

#the following regex is copied from Django source code 
# to validate a url using regax

regex = re.compile(
    r"^(?:http|ftp)s?://"  # http:// or https://
    r"(?:(?:[A-Z0-9](?:[A-Z0-9-]{0,61}[A-Z0-9])?\.)+(?:[A-Z]{2,6}\.?|[A-Z0-9-]{2,}\.?)|"  # domain...
    r"localhost|"  # localhost...
    r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})"  # ...or ip
    r"(?::\d+)?"  # optional port
    r"(?:/?|[/?]\S+)$",
    re.IGNORECASE,
)


blocked_sites: list[str] = []

for site in blocked_sites:
    if site in url or site == url:
        return False

# if none of the above then ensure that the url is valid and then return True otherwise return False
if re.match(regex, url):
    return True

return False