@@ -1,20 +1,32 @@ class Rules(list): """A list of rules for identifying effective top-level domains. - >>> tlds = Rules(['com', '*.org']) - >>> 'example.com' in tlds - False + Rules are formatted as described by the `Public Suffix List`_. + + >>> tlds = Rules() + + Add rules to the list using the ``Rules.load`` method: + + >>> tlds.load(['com', '*.org']) >>> 'com' in tlds True + >>> 'example.com' in tlds + False >>> 'example.org' in tlds True - >>> tlds.append('!example.org') - >>> 'example.org' in tlds - False - See the `Public Suffix List`__ for more information. + ``Rules.load`` will ignore comments and empty rules. This allows the + `Public Suffix List`_ to be loaded unmodified. - __ http://publicsuffix.org/ + >>> tlds.load(['// comment', '', '*.net']) + >>> '// comment' in tlds + False + >>> '' in tlds + False + >>> 'example.net' in tlds + True + + .. _`Public Suffix List`: http://publicsuffix.org/ """ @@ -29,6 +41,17 @@ class Rules(list): wildcard = '*.%s' % '.'.join(domain.split('.')[1:]) return super(Rules, self).__contains__(wildcard) + def load(self, rules): + if isinstance(rules, basestring): + rules = [rules] + new_rules = [] + for rule in rules: + rule = rule.strip() + if not rule or rule.startswith('//'): continue + rule = rule.split()[0] # read only to the first white space + new_rules.append(rule) + self.extend(new_rules) + if __name__ == '__main__': import doctest effectivetlds.py 14e0b8bccb6795611fc28a80efd99351cf58108d Joel Watts joel@joelwatts.com http://github.com/jpwatts/effectivetlds/commit/74aef8f30ba4bf534b15f6f76ca51b1ce33641b0 74aef8f30ba4bf534b15f6f76ca51b1ce33641b0 2008-11-19T22:32:43-08:00 2008-11-19T22:32:43-08:00 Added ``Rules.load`` method. 10b07f9ca136925c139fe88c4c8b4bae4a19a80f Joel Watts joel@joelwatts.com