From 20c6c6a023750e0537d4dbb854b33c26af5db11f Mon Sep 17 00:00:00 2001
From: Alexandre Dulaunoy <a@foo.be>
Date: Tue, 24 Jan 2012 22:53:20 +0100
Subject: [PATCH] Basic pydoc description added

---
 DomainClassifier/domainclassifier.py | 26 ++++++++++++++++++++++++++
 DomainClassifier/test.py             |  2 +-
 2 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/DomainClassifier/domainclassifier.py b/DomainClassifier/domainclassifier.py
index d874e74..fe635e0 100644
--- a/DomainClassifier/domainclassifier.py
+++ b/DomainClassifier/domainclassifier.py
@@ -15,12 +15,23 @@ __license__ = "AGPL version 3"
 __version__ = "0.0.1"
 
 
+
 class Extract:
+
+    """DomainClassifier Extract class is the base class for extracting domains
+    from a rawtext stream. When call, the rawtext parameter is a string
+    containing the raw data to be process."""
+
+
     def __init__(self, rawtext = None):
         self.rawtext = rawtext
         self.presolver = dns.resolver.Resolver()
         self.presolver.nameservers = ['149.13.33.69']
 
+    """__origin is a private function to the ASN lookup for an IP address via
+    the Team Cymru DNS interface. ipadd is a string contain the IP address in a
+    decimal form."""
+
     def __origin(self, ipaddr=None):
 
         if ipaddr:
@@ -32,6 +43,11 @@ class Extract:
             else:
                 return None
 
+    """domain method extracts potential domains matching any
+    string that is a serie of string with maximun 63 character separated by a
+    dot. The method used the rawtext defined at the instantiation of the class.
+    This return a list of a potential domain."""
+
     def domain(self):
         self.domain = []
         domain = re.compile(r'\b([a-zA-Z\d-]{,63}(\.[a-zA-Z\d-]{,63})+)\b')
@@ -41,6 +57,12 @@ class Extract:
 
         return self.domain
 
+    """validdomain method used the extracted domains from the domain method to
+    generate a list of valid domain (at least existing in the authoritative DNS
+    server". The records type used are A, AAAA, SOA, MX and CNAME records. This
+    returns a list of existing domain. If the extended flag is true, a set is
+    return with the associated DNS resources found."""
+
     def validdomain(self, rtype=['A','AAAA','SOA','MX','CNAME'], extended=True):
         if extended is False:
             self.validdomain = set()
@@ -59,6 +81,10 @@ class Extract:
                         self.validdomain.append((domain,dnstype,answers[0]))
         return self.validdomain
 
+    """localizedomain method use the validdomain list (in extended format) to
+    localize per country code the associated resources. The cc argument specifies the
+    country code in ISO 3166-1 alpha-2 format to check for."""
+
     def localizedomain(self, cc=None):
         self.localdom = []
 
diff --git a/DomainClassifier/test.py b/DomainClassifier/test.py
index e802349..f89b023 100644
--- a/DomainClassifier/test.py
+++ b/DomainClassifier/test.py
@@ -3,7 +3,7 @@ import domainclassifier
 c = domainclassifier.Extract( rawtext = "this is a text with a domain called test@foo.lu another test abc.lu something a.b.c.d.e end of 1.2.3.4 foo.be www.belnet.be http://www.cert.be/ www.public.lu www.allo.lu quuxtest www.eurodns.com something-broken-www.google.com www.google.lu trailing test")
 
 print c.domain()
-print c.validdomain(extended=False)
+print c.validdomain(extended=True)
 print "US:"
 print c.localizedomain(cc='US')
 print "LU:"