From 7ac88bb12829688f3256e772ca09047cb11d4793 Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Mon, 26 Sep 2011 16:41:01 +0200
Subject: [PATCH 01/17] first commit

---
 README | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 create mode 100644 README

diff --git a/README b/README
new file mode 100644
index 0000000..e69de29

From c7e1f822d4c4910708b39180512bbd56dc3d20ef Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Tue, 27 Sep 2011 16:41:18 +0200
Subject: [PATCH 02/17] Delete a folder when a file is moved (use carefully,
 not fully tested yet) and adds some unittests to the project.

---
 .gitignore                         |   9 ++
 CHANGES.txt                        |   0
 LICENCE.txt                        |   0
 MANIFEST.in                        |   2 +
 pigeonhole/__init__.py             |   0
 pigeonhole/config.py               |  14 +++
 pigeonhole/pigeonhole.py           | 132 +++++++++++++++++++++++++++++
 pigeonhole/test/__init__.py        |   0
 pigeonhole/test/test_pigeonhole.py |  76 +++++++++++++++++
 setup.py                           |  15 ++++
 10 files changed, 248 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 CHANGES.txt
 create mode 100644 LICENCE.txt
 create mode 100644 MANIFEST.in
 create mode 100644 pigeonhole/__init__.py
 create mode 100644 pigeonhole/config.py
 create mode 100644 pigeonhole/pigeonhole.py
 create mode 100644 pigeonhole/test/__init__.py
 create mode 100644 pigeonhole/test/test_pigeonhole.py
 create mode 100644 setup.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..c4d72aa
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,9 @@
+#python specific
+*.pyc
+
+## generic files to ignore
+*~
+*.lock
+*.DS_Store
+*.swp
+*.out
\ No newline at end of file
diff --git a/CHANGES.txt b/CHANGES.txt
new file mode 100644
index 0000000..e69de29
diff --git a/LICENCE.txt b/LICENCE.txt
new file mode 100644
index 0000000..e69de29
diff --git a/MANIFEST.in b/MANIFEST.in
new file mode 100644
index 0000000..9203697
--- /dev/null
+++ b/MANIFEST.in
@@ -0,0 +1,2 @@
+include *.txt
+recursive-include docs *.txt
\ No newline at end of file
diff --git a/pigeonhole/__init__.py b/pigeonhole/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/pigeonhole/config.py b/pigeonhole/config.py
new file mode 100644
index 0000000..855e1a3
--- /dev/null
+++ b/pigeonhole/config.py
@@ -0,0 +1,14 @@
+# -*- coding: UTF8 -*- 
+# Configuration file
+
+### If a folder only contains these types of files, we can delete it.
+useless_files_extensions = ('srr', 'nfo', 'sfv')
+
+### Consider only files with these extensions
+shows_extensions = ('avi', 'mkv')
+
+### Dictionary for special filenames
+shows_dict = {
+	'white collar' : ['wc'],
+	'the big bang theory' : ['tbbt']
+}
\ No newline at end of file
diff --git a/pigeonhole/pigeonhole.py b/pigeonhole/pigeonhole.py
new file mode 100644
index 0000000..dc4fc7a
--- /dev/null
+++ b/pigeonhole/pigeonhole.py
@@ -0,0 +1,132 @@
+#encoding: utf-8
+
+import os
+import re
+import shutil
+import filecmp
+import config
+
+class Folder(object):
+	""" Directory show instanciation, relative to a path on the disk
+		ie. Show name
+			- Season 1
+			- Season 2
+			- ...
+	"""
+	
+	directory = None
+	name = None
+
+	def __init__(self, path):
+		self.directory = path;
+		self.name = os.path.basename(self.directory)
+
+	def __str__(self):
+		return self.name + ' [' + self.directory + ']'
+
+class Show(object):
+	""" Represents a show file; ie. a file associated to its fullname """
+	
+	path = None
+	name = None
+
+	def __init__(self, fullname, filename):
+		self.path = fullname
+		self.name = filename
+
+	def __str__(self):
+		return self.name
+		
+
+class PigeonHole(object):
+	""" Takes all the media files in a (download) folder and sort 
+		them into the corresponding folder, based on the found file name
+	"""
+	
+	directories = None
+	series = None
+	matches = None
+
+	downloadDir = ""
+	rootShows = ""
+
+	def __init__(self, root, downloaddir):
+		self.downloadDir = downloaddir
+		self.rootShows = root
+		self.directories = os.listdir(self.rootShows)
+		self.series = list()
+
+	def walk(self):		
+		""" Walks through the downloaded folders and yields .avi and .mkv files """
+		for root, dirs, files in os.walk(self.downloadDir):
+			for filename in files:			
+				if filename.endswith(config.shows_extensions):
+					yield Show(os.path.join(root, filename), filename)
+
+	def walk(self, foldername, extensions):
+		for root, dirs, files in os.walk(foldername):
+			for filename in files:
+				if not filename.endswith(extensions):
+					yield os.path.join(root, filename)
+	
+	def process(self):
+		""" Parses the directories within the 'rootShows' folder and stores them as shows in a list. """
+		self.series = [ Folder(os.path.join(self.rootShows, x)) for x in self.directories]
+
+		for path in self.walk(config.shows_extensions):
+			self.moveToFolder(path)
+	
+	def moveToFolder(self, show):
+		""" Moves a specific show to its right folder. """
+		
+		destinationfile = self.findFolder(show)
+
+		if destinationfile is not None:
+			self.move(show.path, destinationfile)
+
+			if self.isDeletable(show.path):
+				shutil.rmtree(show.path)
+
+	def findFolder(self, show):
+		"""Finds and returns the complete destinationpath for a specific show."""
+		
+		rx = re.compile('\W+')
+		result = rx.sub(' ', show.name.lower()).strip()
+
+		for s in self.series:
+			if s.name.lower() in result:
+				return os.path.join(s.directory, show.name)
+
+
+	def move(self, originalfile, destinationfile):
+		""" Moves the downloaded file to the found folder. """
+		print "Moving " + show.name + " to " + destinationfile
+		shutil.move(originalfile, destinationfile)
+
+	def isDeletable(self, foldername):
+		""" Walks through the current directory and deletes it if nothing's really important in it
+			ie. .nfo, .srr or .sfv files. 
+		"""
+		if foldername is None:
+			return False
+
+		if foldername == self.downloadDir or foldername == self.rootShows:
+			return False
+
+		if self.downloadDir in foldername or self.rootShows in foldername:
+			return False
+		
+		if sum(1 for x in self.walk(foldername, config.useless_files_extensions)) is 0:
+			return True
+
+		return False
+		
+	def __str__(self):
+		return 'PigeonHole module'
+	
+	def __name__(self):
+		return 'PigeonHole'
+
+if __name__ == "__main__":
+	pHole = PigeonHole(r'C:\test', r'C:\temp')
+	pHole.process()
diff --git a/pigeonhole/test/__init__.py b/pigeonhole/test/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/pigeonhole/test/test_pigeonhole.py b/pigeonhole/test/test_pigeonhole.py
new file mode 100644
index 0000000..dcdf324
--- /dev/null
+++ b/pigeonhole/test/test_pigeonhole.py
@@ -0,0 +1,76 @@
+import random
+import unittest
+import tempfile
+import shutil
+import os
+from pigeonhole import PigeonHole
+import config
+
+class TestPigeonHoleFunctions(unittest.TestCase):
+	"""Test the methods defined inside the PigeonHole class"""
+	
+	def setUp(self):
+		"""Set up the test environment"""
+		self.rootdir = tempfile.mkdtemp(prefix='pigeonHole_root_')
+		self.downloaddir = tempfile.mkdtemp(prefix='pigeonHole_dl_dir_')
+
+		# Create an environment with three folders
+		os.mkdir(os.path.join(self.rootdir, 'White Collar'))
+		os.mkdir(os.path.join(self.rootdir, 'The Big Bang Theory'))
+		os.mkdir(os.path.join(self.rootdir, 'Being Erica'))
+
+		self.pigeonHole = PigeonHole(self.rootdir, self.downloaddir)
+		
+		self.notDeletableTmpDir = tempfile.mkdtemp(prefix='pigeonHole_')
+		self.deletableTmpDir = tempfile.mkdtemp(prefix='pigeonHole_')
+
+	def tearDown(self):
+		"""Tear down the test environment"""
+		self.pigeonHole = None
+		
+		shutil.rmtree(self.notDeletableTmpDir)
+		shutil.rmtree(self.deletableTmpDir)
+
+		shutil.rmtree(self.rootdir)
+		shutil.rmtree(self.downloaddir)
+
+		
+	def test_init(self):
+		""" Testing the constructor """
+		self.assertEqual(self.pigeonHole.rootShows, self.rootdir)
+		self.assertEqual(self.pigeonHole.downloadDir, self.downloaddir)
+		self.assertTrue(str(self.pigeonHole) == 'PigeonHole module', 'The module string is not correct.')
+		self.assertTrue(str(self.pigeonHole.__name__ == 'PigeonHole'), 'The module name is not correct.')
+
+	def test_clean(self):
+		"""Testing the cleaning method"""
+
+		self.generatedfiles_bad = list()
+		self.generatedfiles_good = list()
+
+		for x in config.useless_files_extensions + config.shows_extensions:
+			fd, temppath = tempfile.mkstemp(x, 'tmp', self.notDeletableTmpDir)
+			self.generatedfiles_bad.append(temppath)
+			os.close(fd)
+			
+		for y in config.useless_files_extensions:
+			fd, temppath = tempfile.mkstemp(y, 'tmp', self.deletableTmpDir)
+			self.generatedfiles_good.append(temppath)
+			os.close(fd)
+
+		self.assertFalse(self.pigeonHole.isDeletable(self.notDeletableTmpDir))
+		self.assertTrue(self.pigeonHole.isDeletable(self.deletableTmpDir))
+
+		self.assertFalse(self.pigeonHole.isDeletable(self.rootdir))
+		self.assertFalse(self.pigeonHole.isDeletable(self.downloaddir))
+
+	def test_findFolder(self):
+		"""Try to move a file to a specific location"""
+
+		
+		
+
+		
+
+if __name__ == '__main__':
+    unittest.main()
\ No newline at end of file
diff --git a/setup.py b/setup.py
new file mode 100644
index 0000000..7c94f6b
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,15 @@
+from distutils.core import setup
+
+setup {
+	name='PigeonHole',
+	version='0.1.0',
+	author='Fred Pauchet'
+	author_email='fpauchet@gmail.com',
+	packages=['pigeonhole','pigeonhole.test'],
+	scripts=[],
+	url='',
+	licence='LICENCE.txt',
+	description='',
+	long_description=long_description=open('README.txt').read(),
+	install_require=[],
+}
\ No newline at end of file

From 63d737a02e174ca586aac45832c36b3aeb42aff9 Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Tue, 27 Sep 2011 17:01:27 +0200
Subject: [PATCH 03/17] Change the filename of CHANGES and LICENCE

---
 CHANGES | 0
 LICENCE | 0
 2 files changed, 0 insertions(+), 0 deletions(-)
 create mode 100644 CHANGES
 create mode 100644 LICENCE

diff --git a/CHANGES b/CHANGES
new file mode 100644
index 0000000..e69de29
diff --git a/LICENCE b/LICENCE
new file mode 100644
index 0000000..e69de29

From 9d0afafa80f44d8b90f02aea44926cdaecc4847b Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Tue, 27 Sep 2011 19:08:15 +0200
Subject: [PATCH 04/17] Delete two useless files

---
 CHANGES.txt | 0
 LICENCE.txt | 0
 2 files changed, 0 insertions(+), 0 deletions(-)
 delete mode 100644 CHANGES.txt
 delete mode 100644 LICENCE.txt

diff --git a/CHANGES.txt b/CHANGES.txt
deleted file mode 100644
index e69de29..0000000
diff --git a/LICENCE.txt b/LICENCE.txt
deleted file mode 100644
index e69de29..0000000

From 96efba1d54c4042d970f234ef5cba536db114407 Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Tue, 27 Sep 2011 22:36:14 +0200
Subject: [PATCH 05/17] Correcting a line in the setup.py file so it takes
 CHANGE and LICENCE file again, and adds a 'pass' statement in unit testing so
 it succeeded :p

---
 pigeonhole/test/test_pigeonhole.py | 4 ++--
 setup.py                           | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/pigeonhole/test/test_pigeonhole.py b/pigeonhole/test/test_pigeonhole.py
index dcdf324..c215253 100644
--- a/pigeonhole/test/test_pigeonhole.py
+++ b/pigeonhole/test/test_pigeonhole.py
@@ -67,10 +67,10 @@ class TestPigeonHoleFunctions(unittest.TestCase):
 	def test_findFolder(self):
 		"""Try to move a file to a specific location"""
 
-		
+		pass
 		
 
 		
 
 if __name__ == '__main__':
-    unittest.main()
\ No newline at end of file
+    unittest.main()
diff --git a/setup.py b/setup.py
index 7c94f6b..63de899 100644
--- a/setup.py
+++ b/setup.py
@@ -8,8 +8,8 @@ setup {
 	packages=['pigeonhole','pigeonhole.test'],
 	scripts=[],
 	url='',
-	licence='LICENCE.txt',
+	licence='LICENCE',
 	description='',
-	long_description=long_description=open('README.txt').read(),
+	long_description=long_description=open('README').read(),
 	install_require=[],
-}
\ No newline at end of file
+}

From f9449896460a02b9984c62a11a5fb0bd020cb57f Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Thu, 29 Sep 2011 17:50:32 +0200
Subject: [PATCH 06/17] Adding a dictionary inside the config file for special
 names

---
 pigeonhole/config.py     |  5 +++--
 pigeonhole/pigeonhole.py | 15 +++++++++++----
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/pigeonhole/config.py b/pigeonhole/config.py
index 855e1a3..fe3d08b 100644
--- a/pigeonhole/config.py
+++ b/pigeonhole/config.py
@@ -9,6 +9,7 @@ shows_extensions = ('avi', 'mkv')
 
 ### Dictionary for special filenames
 shows_dict = {
-	'white collar' : ['wc'],
-	'the big bang theory' : ['tbbt']
+	'wc' : 'white collar',
+	'tbbt' : 'the big bang theory',
+	'beingerica' : 'being erica',
 }
\ No newline at end of file
diff --git a/pigeonhole/pigeonhole.py b/pigeonhole/pigeonhole.py
index dc4fc7a..f2d10c1 100644
--- a/pigeonhole/pigeonhole.py
+++ b/pigeonhole/pigeonhole.py
@@ -63,7 +63,7 @@ class PigeonHole(object):
 				if filename.endswith(config.shows_extensions):
 					yield Show(os.path.join(root, filename), filename)
 
-	def walk(self, foldername, extensions):
+	def walk2(self, foldername, extensions):
 		for root, dirs, files in os.walk(foldername):
 			for filename in files:
 				if not filename.endswith(extensions):
@@ -73,7 +73,7 @@ class PigeonHole(object):
 		""" Parses the directories within the 'rootShows' folder and stores them as shows in a list. """
 		self.series = [ Folder(os.path.join(self.rootShows, x)) for x in self.directories]
 
-		for path in self.walk(config.shows_extensions):
+		for path in self.walk():
 			self.moveToFolder(path)
 	
 	def moveToFolder(self, show):
@@ -86,6 +86,13 @@ class PigeonHole(object):
 
 			if self.isDeletable(show.path):
 				shutil.rmtree(show.path)
+		else:
+			for key in config.shows_dict:
+				if key.lower() in show.name.lower():
+					if os.path.exists(os.path.join(self.rootShows, config.shows_dict[key])):
+						destinationfile = os.path.join(self.rootShows, config.shows_dict[key], show.name)
+						print destinationfile
+						self.move(show.path, destinationfile)
 
 	def findFolder(self, show):
 		"""Finds and returns the complete destinationpath for a specific show."""
@@ -100,7 +107,7 @@ class PigeonHole(object):
 
 	def move(self, originalfile, destinationfile):
 		""" Moves the downloaded file to the found folder. """
-		print "Moving " + show.name + " to " + destinationfile
+		print "Moving " + originalfile + " to " + destinationfile
 		shutil.move(originalfile, destinationfile)
 
 	def isDeletable(self, foldername):
@@ -116,7 +123,7 @@ class PigeonHole(object):
 		if self.downloadDir in foldername or self.rootShows in foldername:
 			return False
 		
-		if sum(1 for x in self.walk(foldername, config.useless_files_extensions)) is 0:
+		if sum(1 for x in self.walk2(foldername, config.useless_files_extensions)) is 0:
 			return True
 
 		return False

From dd6aac029ee13b9bd325e44f1f65a32ffd87cd3e Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Thu, 29 Sep 2011 21:38:42 +0200
Subject: [PATCH 07/17] Corrects a bug when deleting the dl folder. Being a
 little more verbose. Correcting a little bug with the config file.

---
 pigeonhole/config.py     |  2 +-
 pigeonhole/pigeonhole.py | 14 ++++++++++----
 2 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/pigeonhole/config.py b/pigeonhole/config.py
index fe3d08b..5e32b3f 100644
--- a/pigeonhole/config.py
+++ b/pigeonhole/config.py
@@ -7,7 +7,7 @@ useless_files_extensions = ('srr', 'nfo', 'sfv')
 ### Consider only files with these extensions
 shows_extensions = ('avi', 'mkv')
 
-### Dictionary for special filenames
+### Dictionary for special filename contents
 shows_dict = {
 	'wc' : 'white collar',
 	'tbbt' : 'the big bang theory',
diff --git a/pigeonhole/pigeonhole.py b/pigeonhole/pigeonhole.py
index f2d10c1..20b6efa 100644
--- a/pigeonhole/pigeonhole.py
+++ b/pigeonhole/pigeonhole.py
@@ -29,10 +29,12 @@ class Show(object):
 	
 	path = None
 	name = None
+	directory = None
 
 	def __init__(self, fullname, filename):
 		self.path = fullname
 		self.name = filename
+		self.directory = os.path.dirname(self.path)
 
 	def __str__(self):
 		return self.name
@@ -84,8 +86,10 @@ class PigeonHole(object):
 		if destinationfile is not None:
 			self.move(show.path, destinationfile)
 
-			if self.isDeletable(show.path):
-				shutil.rmtree(show.path)
+			if self.isDeletable(show.directory):
+				print '\tDeleting ' + show.directory
+				shutil.rmtree(show.directory)
+				
 		else:
 			for key in config.shows_dict:
 				if key.lower() in show.name.lower():
@@ -107,7 +111,7 @@ class PigeonHole(object):
 
 	def move(self, originalfile, destinationfile):
 		""" Moves the downloaded file to the found folder. """
-		print "Moving " + originalfile + " to " + destinationfile
+		print 'Moving ' + originalfile + ' to ' + destinationfile
 		shutil.move(originalfile, destinationfile)
 
 	def isDeletable(self, foldername):
@@ -120,9 +124,11 @@ class PigeonHole(object):
 		if foldername == self.downloadDir or foldername == self.rootShows:
 			return False
 
-		if self.downloadDir in foldername or self.rootShows in foldername:
+		if foldername in self.downloadDir or foldername in self.rootShows:
 			return False
 		
+		print 'I got ' + str(sum(1 for x in self.walk2(foldername, config.useless_files_extensions))) + ' int. files'
+
 		if sum(1 for x in self.walk2(foldername, config.useless_files_extensions)) is 0:
 			return True
 

From 18733e69d9a15045bd867cf0d00c8382a26801c7 Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Thu, 29 Sep 2011 22:00:46 +0200
Subject: [PATCH 08/17] Readme

---
 README | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/README b/README
index e69de29..87c3af1 100644
--- a/README
+++ b/README
@@ -0,0 +1,29 @@
+PigeonHole
+==========
+
+The main purpose of this application is to sort some specific types of files into a well-arranged directory. 
+
+I used it for classifying tv shows from a garbage folder into the right one, based on the filename which will be cleaned to help sorting.
+
+How it works
+------------
+
+The project is splitted into several files : 
+* pigeonhole/pigeonhole.py : the one that should be run :)
+* setup.py : not used yet (sorry)
+* pigeonhole/config.py : where you should put your configuration.
+
+### config.py ###
+The configuration file contains the declaration of three variables : 
+1. useless_files_extensions : used to clean a folder when the content of this directory (and its subdirectories) is only composed by this kind of files. Do not try to put `*` inside this filter, I don't know the behavior yet...
+2. shows_extensions : the files that need to be organized. The `process` method of the `PigeonHole` class won't look for anything else than these filetype (sorry to based the recognition on extensions and not on [http://en.wikipedia.org/wiki/List_of_file_signatures](magic numbers))
+3. shows_dict : used for file that have a 'special name'
+(ie. using 'tbbt' while the real name is much much longer)
+Unit testing
+------------
+
+All tests are located inside the `pigeonhole/tests` directory. To launch them, use the following command, based on the python handbook:
+
+	python -m unittest discover 
+
+Temporary files and folders are created (and cleaned) to verify that the behavior is going okay.
\ No newline at end of file

From e125bbc02bfd605fcd3c75242ea59d7d3b156292 Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Fri, 30 Sep 2011 08:18:24 +0200
Subject: [PATCH 09/17] readme

---
 README => README.md | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)
 rename README => README.md (82%)

diff --git a/README b/README.md
similarity index 82%
rename from README
rename to README.md
index 87c3af1..b1ef63e 100644
--- a/README
+++ b/README.md
@@ -10,15 +10,18 @@ How it works
 
 The project is splitted into several files : 
 * pigeonhole/pigeonhole.py : the one that should be run :)
-* setup.py : not used yet (sorry)
+* setup.py : not used yet, sorry.
 * pigeonhole/config.py : where you should put your configuration.
 
 ### config.py ###
+
 The configuration file contains the declaration of three variables : 
+
 1. useless_files_extensions : used to clean a folder when the content of this directory (and its subdirectories) is only composed by this kind of files. Do not try to put `*` inside this filter, I don't know the behavior yet...
-2. shows_extensions : the files that need to be organized. The `process` method of the `PigeonHole` class won't look for anything else than these filetype (sorry to based the recognition on extensions and not on [http://en.wikipedia.org/wiki/List_of_file_signatures](magic numbers))
+2. shows_extensions : the files that need to be organized. The `process` method of the `PigeonHole` class won't look for anything else than these filetype (sorry to based the recognition on extensions and not on [magic numbers](http://en.wikipedia.org/wiki/List_of_file_signatures))
 3. shows_dict : used for file that have a 'special name'
-(ie. using 'tbbt' while the real name is much much longer)
+(ie. using 'tbbt' while the real name that can be found in the destination folder is much much longer)
+
 Unit testing
 ------------
 
@@ -26,4 +29,4 @@ All tests are located inside the `pigeonhole/tests` directory. To launch them, u
 
 	python -m unittest discover 
 
-Temporary files and folders are created (and cleaned) to verify that the behavior is going okay.
\ No newline at end of file
+Temporary files and folders are created (and cleaned) to verify that the file behavior is going okay.
\ No newline at end of file

From dbbcb311543d674f7dd19a51d01f91f9aea395e2 Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Tue, 4 Oct 2011 09:04:37 +0200
Subject: [PATCH 10/17] tvsubtitles query

---
 README                 | 32 ++++++++++++++++++++++++++++++++
 pigeonhole/subQuery.py | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 64 insertions(+)
 create mode 100644 README
 create mode 100644 pigeonhole/subQuery.py

diff --git a/README b/README
new file mode 100644
index 0000000..79ea1b9
--- /dev/null
+++ b/README
@@ -0,0 +1,32 @@
+PigeonHole
+==========
+
+The main purpose of this application is to sort some specific types of files into a well-arranged directory. 
+
+I used it for classifying tv shows from a garbage folder into the right one, based on the filename which will be cleaned to help sorting.
+
+How it works
+------------
+
+The project is splitted into several files : 
+* pigeonhole/pigeonhole.py : the one that should be run :)
+* setup.py : not used yet, sorry.
+* pigeonhole/config.py : where you should put your configuration.
+
+### config.py ###
+
+The configuration file contains the declaration of three variables : 
+
+1. useless_files_extensions : used to clean a folder when the content of this directory (and its subdirectories) is only composed by this kind of files. Do not try to put `*` inside this filter, I don't know the behavior yet...
+2. shows_extensions : the files that need to be organized. The `process` method of the `PigeonHole` class won't look for anything else than these filetype, based the recognition of extensions and not on [magic numbers](http://en.wikipedia.org/wiki/List_of_file_signatures).
+3. shows_dict : used for file that have a 'special name'
+(ie. using 'tbbt' while the real name that can be found in the destination folder is much much longer)
+
+Unit testing
+------------
+
+All tests are located inside the `pigeonhole/tests` directory. To launch them, use the following command, based on the python handbook:
+
+	python -m unittest discover 
+
+Temporary files and folders are created (and cleaned) to verify that the file behavior is going okay.
\ No newline at end of file
diff --git a/pigeonhole/subQuery.py b/pigeonhole/subQuery.py
new file mode 100644
index 0000000..0500b58
--- /dev/null
+++ b/pigeonhole/subQuery.py
@@ -0,0 +1,32 @@
+import urllib2
+import re
+from BeautifulSoup import BeautifulSoup
+
+"""
+	Querying non web services through http interrogation and regex results retrieval.
+"""
+
+def query(showname):
+	print "Trying " + showname
+	socket = urllib2.urlopen('http://www.tvsubtitles.net/search.php?q=' + showname.replace(' ', '%20'))
+	soup = BeautifulSoup(socket.read())
+	socket.close()
+
+	results = soup.findAll(href=re.compile("/tvshow-([A-Za-z0-9]*)\.html$"))
+
+	if len(results) == 1:
+		"ouh yeah baby " + showname + " " + str(results[0])
+		
+	elif len(results) == 0:
+		print "No results found for " + showname
+	else:
+		print "Here are the possible results for " + showname
+		for res in results: 
+			print "\t" + str(res)
+
+if __name__ == "__main__":
+	query('the big bang theory')
+	query('being erica')
+	query('white collar')
+	query('scrubs')
+	query('castle')
\ No newline at end of file

From 2cc271f0978580ed0e999a4a4d119e67b0e39929 Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Tue, 4 Oct 2011 17:26:36 +0200
Subject: [PATCH 11/17] querying non ws interfaces through http and regex
 results retrieval

---
 pigeonhole/subQuery.py | 44 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 42 insertions(+), 2 deletions(-)

diff --git a/pigeonhole/subQuery.py b/pigeonhole/subQuery.py
index 0500b58..aaaae39 100644
--- a/pigeonhole/subQuery.py
+++ b/pigeonhole/subQuery.py
@@ -3,9 +3,15 @@ import re
 from BeautifulSoup import BeautifulSoup
 
 """
-	Querying non web services through http interrogation and regex results retrieval.
+	Querying non web services interfaces 
+	through http interrogation and regex results retrieval.
 """
 
+languages = ('en', 'es', 'fr', 'de')
+
+def queryUrl(baseurl, baseregex):
+	print 'Querying %s w/ %s' % baseurl, baseregex
+
 def query(showname):
 	print "Trying " + showname
 	socket = urllib2.urlopen('http://www.tvsubtitles.net/search.php?q=' + showname.replace(' ', '%20'))
@@ -14,15 +20,49 @@ def query(showname):
 
 	results = soup.findAll(href=re.compile("/tvshow-([A-Za-z0-9]*)\.html$"))
 
+
+	# a yield here would be cool ! :)
 	if len(results) == 1:
-		"ouh yeah baby " + showname + " " + str(results[0])
+		print str(results[0])
+		return results[0]
 		
 	elif len(results) == 0:
 		print "No results found for " + showname
+		return None
 	else:
 		print "Here are the possible results for " + showname
 		for res in results: 
 			print "\t" + str(res)
+		return None
+	
+
+def getSeason(showname, seasonNumber):
+	season = query(showname)
+
+	#idem
+
+	if season is not None:
+		print str(season).replace('.html', '-' + seasonNumber + '.html')
+
+	else:
+		print "no season found"
+
+def getEpisode(showname, seasonNumber, episodeNumber):
+	season = query(showname, seasonNumber)
+
+	urllib2.urlopen(season)
+
+
+	#idem
+
+	if episode is not None:
+		print str(episode).replace('.html', '-')
+	else:
+		print "no episode found"
+
+def getUrl(showname, seasonNumber, episodeNumber, language):
+	"""Supposed to send to the right page, according to the right episode number"""
+	pass
 
 if __name__ == "__main__":
 	query('the big bang theory')

From 638654066f7b93ba5c9cc5f4695cd637e67d38bd Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Wed, 5 Oct 2011 09:08:22 +0200
Subject: [PATCH 12/17] delete experimental files

---
 pigeonhole/subQuery.py | 72 ------------------------------------------
 1 file changed, 72 deletions(-)
 delete mode 100644 pigeonhole/subQuery.py

diff --git a/pigeonhole/subQuery.py b/pigeonhole/subQuery.py
deleted file mode 100644
index aaaae39..0000000
--- a/pigeonhole/subQuery.py
+++ /dev/null
@@ -1,72 +0,0 @@
-import urllib2
-import re
-from BeautifulSoup import BeautifulSoup
-
-"""
-	Querying non web services interfaces 
-	through http interrogation and regex results retrieval.
-"""
-
-languages = ('en', 'es', 'fr', 'de')
-
-def queryUrl(baseurl, baseregex):
-	print 'Querying %s w/ %s' % baseurl, baseregex
-
-def query(showname):
-	print "Trying " + showname
-	socket = urllib2.urlopen('http://www.tvsubtitles.net/search.php?q=' + showname.replace(' ', '%20'))
-	soup = BeautifulSoup(socket.read())
-	socket.close()
-
-	results = soup.findAll(href=re.compile("/tvshow-([A-Za-z0-9]*)\.html$"))
-
-
-	# a yield here would be cool ! :)
-	if len(results) == 1:
-		print str(results[0])
-		return results[0]
-		
-	elif len(results) == 0:
-		print "No results found for " + showname
-		return None
-	else:
-		print "Here are the possible results for " + showname
-		for res in results: 
-			print "\t" + str(res)
-		return None
-	
-
-def getSeason(showname, seasonNumber):
-	season = query(showname)
-
-	#idem
-
-	if season is not None:
-		print str(season).replace('.html', '-' + seasonNumber + '.html')
-
-	else:
-		print "no season found"
-
-def getEpisode(showname, seasonNumber, episodeNumber):
-	season = query(showname, seasonNumber)
-
-	urllib2.urlopen(season)
-
-
-	#idem
-
-	if episode is not None:
-		print str(episode).replace('.html', '-')
-	else:
-		print "no episode found"
-
-def getUrl(showname, seasonNumber, episodeNumber, language):
-	"""Supposed to send to the right page, according to the right episode number"""
-	pass
-
-if __name__ == "__main__":
-	query('the big bang theory')
-	query('being erica')
-	query('white collar')
-	query('scrubs')
-	query('castle')
\ No newline at end of file

From 26cd5e67c304f96572dd776f62d76190cbdf7767 Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Mon, 21 Nov 2011 21:21:31 +0100
Subject: [PATCH 13/17] adding subQuery.py methods to query html pages and
 retrieve specific urls.

---
 pigeonhole/subQuery.py | 109 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 109 insertions(+)
 create mode 100644 pigeonhole/subQuery.py

diff --git a/pigeonhole/subQuery.py b/pigeonhole/subQuery.py
new file mode 100644
index 0000000..d8c1623
--- /dev/null
+++ b/pigeonhole/subQuery.py
@@ -0,0 +1,109 @@
+import urllib2
+import re
+import os
+from BeautifulSoup import BeautifulSoup
+
+"""
+	Querying non web services interfaces 
+	through http interrogation and regex results retrieval.
+"""
+
+languages = ('en', 'es', 'fr', 'de')
+
+def queryUrl(baseurl, baseregex):
+	print 'Querying %s w/ %s' % (baseurl, baseregex)
+
+def query(showname):
+	print "Trying " + showname
+	socket = urllib2.urlopen('http://www.tvsubtitles.net/search.php?q=' + showname.replace(' ', '%20'))
+	soup = BeautifulSoup(socket.read())
+	socket.close()
+
+	results = soup.findAll(href=re.compile("/tvshow-([A-Za-z0-9]*)\.html$"))
+
+
+	# a yield here would be cool ! :)
+	if len(results) == 1:
+		print str(results[0])
+		return results[0]
+		
+	elif len(results) == 0:
+		print "No results found for " + showname
+		return None
+	else:
+		print "Here are the possible results for " + showname
+		for res in results: 
+			print "\t" + str(res)
+		return None
+	
+""" Get a specific season, based on the show name and the season number
+	
+	eg. getSeason('suits', 1)
+		getSeason('dexter', 3)
+"""
+def getSeason(showname, seasonNumber):
+	season = query(showname)
+
+	#idem
+
+	if season is not None:
+		print str(season).replace('.html', '-' + str(seasonNumber) + '.html')
+
+	else:
+		print "no season found"
+
+""" Get a specific episode, based on the show name, the season number and the episode number
+	
+	eg. getEpisode('being erica', 2, 12)
+		getEpisode('the big bang theory', 3, 15)
+"""
+def getEpisode(showname, seasonNumber, episodeNumber):
+
+	raise Exception('not implemented yet')
+
+	season = query(showname, seasonNumber)
+
+	urllib2.urlopen(season)
+
+
+	#idem
+
+	if episode is not None:
+		print str(episode).replace('.html', '-')
+	else:
+		print "no episode found"
+
+def getUrl(showname, seasonNumber, episodeNumber, language):
+	"""Supposed to send to the right page, according to the right episode number"""
+	pass
+
+""" Write a shortcut to a specific web page and fix the shortcutname within the writtent file.
+	
+	eg. writeUrlShortcut('/opt/tmp', 'google.url', 'http://www.google.com', 'Google')	
+	>>> [Google]
+	>>> URL=http://www.google.com
+	>>> inside a file named /opt/tmp/google.url
+"""
+def writeUrlShortcut(folderpath, filename, url, shortcutname):
+	if not os.path.exists(folderpath):
+		raise Exception('Writing Url : Path does not exists')
+
+	filecontent = """[%s]\nURL=%s""" % (shortcutname, url)
+
+	with open(os.path.join(folderpath, filename), 'w+') as f:
+		f.write(filecontent)
+
+
+if __name__ == "__main__":
+	#queryUrl('http://www.tvsubtitles.net/search?q=', 'tvshow')
+
+	# query('the big bang theory')
+	# query('being erica')
+	# query('white collar')
+	# query('scrubs')
+	# query('castle')
+
+	getSeason('the big bang theory', 2)
+	getSeason('white collar', 1)
+	getSeason('suits', 1)
+	getSeason('being erica', 2)
\ No newline at end of file

From f3b14d2516ca858700ef8a760eda77cc38886210 Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Tue, 22 Nov 2011 21:37:47 +0100
Subject: [PATCH 14/17] Refactoring generic url querying Shortcut creation
 nearly running

---
 pigeonhole/subQuery.py | 56 ++++++++++++++++++++++++++++++++----------
 1 file changed, 43 insertions(+), 13 deletions(-)

diff --git a/pigeonhole/subQuery.py b/pigeonhole/subQuery.py
index d8c1623..974ec16 100644
--- a/pigeonhole/subQuery.py
+++ b/pigeonhole/subQuery.py
@@ -10,21 +10,43 @@ from BeautifulSoup import BeautifulSoup
 
 languages = ('en', 'es', 'fr', 'de')
 
-def queryUrl(baseurl, baseregex):
-	print 'Querying %s w/ %s' % (baseurl, baseregex)
 
-def query(showname):
-	print "Trying " + showname
-	socket = urllib2.urlopen('http://www.tvsubtitles.net/search.php?q=' + showname.replace(' ', '%20'))
+"""
+	Querying a base url with a specific regex and a query.
+
+	eg. baseurl = http://duckduckgo.com/?q=
+		query = my_query
+		baseregex = ... :)
+
+	It will query the url, adds the query string and will fetch every href link that match the regular expression.
+"""
+def queryUrl(baseurl, paramindicator, regex, querystring):
+	socket = urllib2.urlopen(baseurl + paramindicator + querystring)
 	soup = BeautifulSoup(socket.read())
 	socket.close()
 
-	results = soup.findAll(href=re.compile("/tvshow-([A-Za-z0-9]*)\.html$"))
+	tags = soup.findAll(href=re.compile(regex))
 
+	mylist = list()
+
+	for tag in tags:
+		bsoup = BeautifulSoup(str(tag))
+		mylist.append(baseurl + bsoup.a['href'])
+
+	return mylist
+
+def queryShow(showname):
+	return queryUrl('http://www.tvsubtitles.net', '/search.php?q=', '/tvshow-([A-Za-z0-9]*)\.html$', showname.replace(' ', '%20'))
+
+def querySeason(showname, seasonnumber):
+	pass
+
+def query(showname):
+	results = queryShow(showname)
 
 	# a yield here would be cool ! :)
 	if len(results) == 1:
-		print str(results[0])
+		print results[0]
 		return results[0]
 		
 	elif len(results) == 0:
@@ -59,7 +81,7 @@ def getSeason(showname, seasonNumber):
 """
 def getEpisode(showname, seasonNumber, episodeNumber):
 
-	raise Exception('not implemented yet')
+	raise Exception('not yet implemented')
 
 	season = query(showname, seasonNumber)
 
@@ -73,8 +95,8 @@ def getEpisode(showname, seasonNumber, episodeNumber):
 	else:
 		print "no episode found"
 
+"""Supposed to send to the right page, according to the right episode number"""
 def getUrl(showname, seasonNumber, episodeNumber, language):
-	"""Supposed to send to the right page, according to the right episode number"""
 	pass
 
 """ Write a shortcut to a specific web page and fix the shortcutname within the writtent file.
@@ -93,6 +115,11 @@ def writeUrlShortcut(folderpath, filename, url, shortcutname):
 	with open(os.path.join(folderpath, filename), 'w+') as f:
 		f.write(filecontent)
 
+def walk(foldername):
+	for root, dirs, files in os.walk(foldername):
+		for directory in dirs:
+			if query(directory) is not None:
+				yield directory
 
 if __name__ == "__main__":
 	#queryUrl('http://www.tvsubtitles.net/search?q=', 'tvshow')
@@ -103,7 +130,10 @@ if __name__ == "__main__":
 	# query('scrubs')
 	# query('castle')
 
-	getSeason('the big bang theory', 2)
-	getSeason('white collar', 1)
-	getSeason('suits', 1)
-	getSeason('being erica', 2)
\ No newline at end of file
+	for match in walk(r'C:\Tmp'):
+		print match
+
+	# getSeason('the big bang theory', 2)
+	# getSeason('white collar', 1)
+	# getSeason('suits', 1)
+	# getSeason('being erica', 2)
\ No newline at end of file

From b6ef8c14da47711a25185c71bd0c24ee4ace79e1 Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Wed, 28 Dec 2011 16:10:02 +0100
Subject: [PATCH 15/17] changing model, adding subtitles query, building
 structure

---
 pigeonhole/model.py      |  47 +++++++++++++++++
 pigeonhole/pigeonhole.py |  17 +-----
 pigeonhole/subQuery.py   | 110 +++++++++++++--------------------------
 3 files changed, 84 insertions(+), 90 deletions(-)
 create mode 100644 pigeonhole/model.py

diff --git a/pigeonhole/model.py b/pigeonhole/model.py
new file mode 100644
index 0000000..0722dd4
--- /dev/null
+++ b/pigeonhole/model.py
@@ -0,0 +1,47 @@
+from subQuery import *
+
+class Structure(object):
+
+	def __init__(self):
+		print 'building myself'
+
+class Show(object):
+	""" Represents a show file; ie. a file associated to its fullname """
+	
+	path = None
+	name = None
+	directory = None
+
+	url = None
+
+	Seasons = list()
+
+	def append(self, season):
+		self.Seasons.append(season)
+		season.parent = self
+
+	def __init__(self, fullname, filename):
+		self.path = fullname
+		self.name = filename
+		self.directory = os.path.dirname(self.path)
+		url = queryShow(self.name)
+
+	def __str__(self):
+		return self.name
+
+class Season(object):
+	""" Represents a season within a show """
+
+	seasonnumber = None
+	parent = None
+
+	def __init__(self, seasonnumber):
+		self.seasonnumber = seasonnumber
+
+class Episode(object):
+	""" Represents an episode within a season """
+
+	title = None
+
+	def __init__(self, title):
+		self.title = title
\ No newline at end of file
diff --git a/pigeonhole/pigeonhole.py b/pigeonhole/pigeonhole.py
index 20b6efa..4a27f3e 100644
--- a/pigeonhole/pigeonhole.py
+++ b/pigeonhole/pigeonhole.py
@@ -5,6 +5,7 @@ import re
 import shutil
 import filecmp
 import config
+from model import Show
 
 class Folder(object):
 	""" Directory show instanciation, relative to a path on the disk
@@ -24,22 +25,6 @@ class Folder(object):
 	def __str__(self):
 		return self.name + ' [' + self.directory + ']'
 
-class Show(object):
-	""" Represents a show file; ie. a file associated to its fullname """
-	
-	path = None
-	name = None
-	directory = None
-
-	def __init__(self, fullname, filename):
-		self.path = fullname
-		self.name = filename
-		self.directory = os.path.dirname(self.path)
-
-	def __str__(self):
-		return self.name
-		
-
 class PigeonHole(object):
 	""" Takes all the media files in a (download) folder and sort 
 		them into the corresponding folder, based on the found file name
diff --git a/pigeonhole/subQuery.py b/pigeonhole/subQuery.py
index 974ec16..e3e035c 100644
--- a/pigeonhole/subQuery.py
+++ b/pigeonhole/subQuery.py
@@ -10,6 +10,26 @@ from BeautifulSoup import BeautifulSoup
 
 languages = ('en', 'es', 'fr', 'de')
 
+""" not documented yet
+"""
+class CustomUrl(object):
+	fullUrl = None
+	suffix = None
+	base = None
+
+	def __init__(self, base, suffix):
+		self.base = base
+		self.suffix = suffix
+		self.fullUrl = base + suffix
+
+	def __str__(self):
+		return str(self.fullUrl)
+
+	def __unicode__(self):
+		return str(self.fullUrl)
+
+	def replace(self, oldstr, newstr):
+		return CustomUrl(self.base, self.suffix.replace(oldstr, newstr))
 
 """
 	Querying a base url with a specific regex and a query.
@@ -21,6 +41,7 @@ languages = ('en', 'es', 'fr', 'de')
 	It will query the url, adds the query string and will fetch every href link that match the regular expression.
 """
 def queryUrl(baseurl, paramindicator, regex, querystring):
+	#print '\tProbing ' + baseurl + ' ' + paramindicator + ' ' + regex + ' ' + querystring
 	socket = urllib2.urlopen(baseurl + paramindicator + querystring)
 	soup = BeautifulSoup(socket.read())
 	socket.close()
@@ -31,7 +52,7 @@ def queryUrl(baseurl, paramindicator, regex, querystring):
 
 	for tag in tags:
 		bsoup = BeautifulSoup(str(tag))
-		mylist.append(baseurl + bsoup.a['href'])
+		mylist.append(CustomUrl(baseurl, bsoup.a['href']))
 
 	return mylist
 
@@ -39,65 +60,14 @@ def queryShow(showname):
 	return queryUrl('http://www.tvsubtitles.net', '/search.php?q=', '/tvshow-([A-Za-z0-9]*)\.html$', showname.replace(' ', '%20'))
 
 def querySeason(showname, seasonnumber):
+	return [x.replace('.html', '-' + str(seasonnumber) + '.html') for x in queryShow(showname)]
+
+
+"""Supposed to return the url, according to the show name and season number"""
+def getUrl(showname, seasonNumber, episodenumber, language):
+	Raise("not implemented yet")
 	pass
 
-def query(showname):
-	results = queryShow(showname)
-
-	# a yield here would be cool ! :)
-	if len(results) == 1:
-		print results[0]
-		return results[0]
-		
-	elif len(results) == 0:
-		print "No results found for " + showname
-		return None
-	else:
-		print "Here are the possible results for " + showname
-		for res in results: 
-			print "\t" + str(res)
-		return None
-	
-""" Get a specific season, based on the show name and the season number
-	
-	eg. getSeason('suits', 1)
-		getSeason('dexter', 3)
-"""
-def getSeason(showname, seasonNumber):
-	season = query(showname)
-
-	#idem
-
-	if season is not None:
-		print str(season).replace('.html', '-' + str(seasonNumber) + '.html')
-
-	else:
-		print "no season found"
-
-""" Get a specific episode, based on the show name, the season number and the episode number
-	
-	eg. getEpisode('being erica', 2, 12)
-		getEpisode('the big bang theory', 3, 15)
-"""
-def getEpisode(showname, seasonNumber, episodeNumber):
-
-	raise Exception('not yet implemented')
-
-	season = query(showname, seasonNumber)
-
-	urllib2.urlopen(season)
-
-
-	#idem
-
-	if episode is not None:
-		print str(episode).replace('.html', '-')
-	else:
-		print "no episode found"
-
-"""Supposed to send to the right page, according to the right episode number"""
-def getUrl(showname, seasonNumber, episodeNumber, language):
-	pass
 
 """ Write a shortcut to a specific web page and fix the shortcutname within the writtent file.
 	
@@ -118,22 +88,14 @@ def writeUrlShortcut(folderpath, filename, url, shortcutname):
 def walk(foldername):
 	for root, dirs, files in os.walk(foldername):
 		for directory in dirs:
-			if query(directory) is not None:
-				yield directory
+			
+
+def echo(var):
+	for x in var:
+		print x
 
 if __name__ == "__main__":
-	#queryUrl('http://www.tvsubtitles.net/search?q=', 'tvshow')
+	for x in walk(r'C:\temp'):
+		print x
 
-	# query('the big bang theory')
-	# query('being erica')
-	# query('white collar')
-	# query('scrubs')
-	# query('castle')
-
-	for match in walk(r'C:\Tmp'):
-		print match
-
-	# getSeason('the big bang theory', 2)
-	# getSeason('white collar', 1)
-	# getSeason('suits', 1)
-	# getSeason('being erica', 2)
\ No newline at end of file
+	echo(queryShow('saison 1'))
\ No newline at end of file

From 55537c04e5a4d77f402b66202722c6045f6e908d Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Thu, 29 Dec 2011 15:58:09 +0100
Subject: [PATCH 16/17] url shortcurt writer seems to work

---
 pigeonhole/model.py                | 87 ++++++++++++++++++++++--------
 pigeonhole/pigeonhole.py           | 29 +++-------
 pigeonhole/subQuery.py             | 32 +++--------
 pigeonhole/test/test_pigeonhole.py |  7 ++-
 setup.py                           | 26 ++++-----
 5 files changed, 92 insertions(+), 89 deletions(-)

diff --git a/pigeonhole/model.py b/pigeonhole/model.py
index 0722dd4..7b90e4e 100644
--- a/pigeonhole/model.py
+++ b/pigeonhole/model.py
@@ -1,30 +1,28 @@
 from subQuery import *
+import os
 
 class Structure(object):
+	"""Represents the complete structure, with its shows, seasons and episodes"""
+	
+	def __init__(self, path):
+		self.shows = [Show(os.path.join(path, x)) for x in os.listdir(path) if os.path.isdir(os.path.join(path, x))]
 
-	def __init__(self):
-		print 'building myself'
+	def writeUrls(self):
+		for s in self.shows:
+			for season in s.seasons:
+				season.writeUrl()
 
 class Show(object):
 	""" Represents a show file; ie. a file associated to its fullname """
-	
-	path = None
-	name = None
-	directory = None
 
-	url = None
+	def __init__(self, path):
 
-	Seasons = list()
+		self.path = path
+		self.name = os.path.basename(path)
 
-	def append(self, season):
-		self.Seasons.append(season)
-		season.parent = self
+		self.url = queryShow(self.name)
 
-	def __init__(self, fullname, filename):
-		self.path = fullname
-		self.name = filename
-		self.directory = os.path.dirname(self.path)
-		url = queryShow(self.name)
+		self.seasons = [Season(self, os.path.join(path, x)) for x in os.listdir(path) if os.path.isdir(os.path.join(path, x))]
 
 	def __str__(self):
 		return self.name
@@ -32,16 +30,59 @@ class Show(object):
 class Season(object):
 	""" Represents a season within a show """
 
-	seasonnumber = None
-	parent = None
+	def __init__(self, parent, path):
 
-	def __init__(self, seasonnumber):
-		self.seasonnumber = seasonnumber
+		self.parent = parent
+		self.path = path
+		self.name = os.path.basename(path)
+		self.seasonnumber = re.findall('[0-9]+', os.path.basename(path))[0]
+		self.episodes = [Episode(self, os.path.join(path, x)) for x in os.listdir(path) if os.path.isfile(os.path.join(path, x))]
+
+		self.url = querySeason(parent.name, self.seasonnumber)
+
+	def writeUrl(self):
+		if len(self.url) == 1:
+			results = querySeason(self.parent.name, self.seasonnumber)
+
+			if len(results) == 1:
+				print 'Writing subtitles shortcut for ' + self.parent.name
+				writeUrlShortcut(self.path, self.parent.name + '.url', str(self.url[0]), 'InternetShortcut')
+			elif len(results) == 0:
+				print 'no results have been found for ' + self.parent.name
+			else:
+				print 'too much results have been found'
+		elif len(self.url) == 0:
+			print 'too few urls for ' + self.parent.name
+		else:
+			print 'too many urls for ' + self.parent.name
 
 class Episode(object):
 	""" Represents an episode within a season """
 
-	title = None
+	def __init__(self, parent, path):
+		print 'Building an episode: ' + path
 
-	def __init__(self, title):
-		self.title = title
\ No newline at end of file
+		self.parent = parent
+		self.path = path
+		self.name = os.path.basename(path)
+
+	def __str__(self):
+		return self.name
+
+class Folder(object):
+	""" Directory show instanciation, relative to a path on the disk
+		ie. Show name
+			- Season 1
+			- Season 2
+			- ...
+	"""
+	
+	directory = None
+	name = None
+
+	def __init__(self, path):
+		self.directory = path;
+		self.name = os.path.basename(self.directory)
+
+	def __str__(self):
+		return self.name + ' [' + self.directory + ']'
\ No newline at end of file
diff --git a/pigeonhole/pigeonhole.py b/pigeonhole/pigeonhole.py
index 4a27f3e..f1a619f 100644
--- a/pigeonhole/pigeonhole.py
+++ b/pigeonhole/pigeonhole.py
@@ -5,39 +5,20 @@ import re
 import shutil
 import filecmp
 import config
-from model import Show
 
-class Folder(object):
-	""" Directory show instanciation, relative to a path on the disk
-		ie. Show name
-			- Season 1
-			- Season 2
-			- ...
-	"""
-	
-	directory = None
-	name = None
-
-	def __init__(self, path):
-		self.directory = path;
-		self.name = os.path.basename(self.directory)
-
-	def __str__(self):
-		return self.name + ' [' + self.directory + ']'
+from model import *
 
 class PigeonHole(object):
 	""" Takes all the media files in a (download) folder and sort 
 		them into the corresponding folder, based on the found file name
 	"""
 	
-	directories = None
-	series = None
 	matches = None
 
-	downloadDir = ""
-	rootShows = ""
-
 	def __init__(self, root, downloaddir):
+
+		self.structure = Structure(root)
+
 		self.downloadDir = downloaddir
 		self.rootShows = root
 		self.directories = os.listdir(self.rootShows)
@@ -128,3 +109,5 @@ class PigeonHole(object):
 if __name__ == "__main__":
 	pHole = PigeonHole(r'C:\test', r'C:\temp')
 	pHole.process()
+	pHole.structure.writeUrls()
+
diff --git a/pigeonhole/subQuery.py b/pigeonhole/subQuery.py
index e3e035c..e0d206e 100644
--- a/pigeonhole/subQuery.py
+++ b/pigeonhole/subQuery.py
@@ -10,7 +10,9 @@ from BeautifulSoup import BeautifulSoup
 
 languages = ('en', 'es', 'fr', 'de')
 
-""" not documented yet
+""" 
+	Represents a custom url object. 
+	It refers to a simple web page and can be embedded anywhere.
 """
 class CustomUrl(object):
 	fullUrl = None
@@ -18,9 +20,9 @@ class CustomUrl(object):
 	base = None
 
 	def __init__(self, base, suffix):
-		self.base = base
-		self.suffix = suffix
-		self.fullUrl = base + suffix
+		self.base = str(base)
+		self.suffix = str(suffix)
+		self.fullUrl = self.base + self.suffix
 
 	def __str__(self):
 		return str(self.fullUrl)
@@ -62,13 +64,6 @@ def queryShow(showname):
 def querySeason(showname, seasonnumber):
 	return [x.replace('.html', '-' + str(seasonnumber) + '.html') for x in queryShow(showname)]
 
-
-"""Supposed to return the url, according to the show name and season number"""
-def getUrl(showname, seasonNumber, episodenumber, language):
-	Raise("not implemented yet")
-	pass
-
-
 """ Write a shortcut to a specific web page and fix the shortcutname within the writtent file.
 	
 	eg. writeUrlShortcut('/opt/tmp', 'google.url', 'http://www.google.com', 'Google')	
@@ -84,18 +79,3 @@ def writeUrlShortcut(folderpath, filename, url, shortcutname):
 
 	with open(os.path.join(folderpath, filename), 'w+') as f:
 		f.write(filecontent)
-
-def walk(foldername):
-	for root, dirs, files in os.walk(foldername):
-		for directory in dirs:
-			
-
-def echo(var):
-	for x in var:
-		print x
-
-if __name__ == "__main__":
-	for x in walk(r'C:\temp'):
-		print x
-
-	echo(queryShow('saison 1'))
\ No newline at end of file
diff --git a/pigeonhole/test/test_pigeonhole.py b/pigeonhole/test/test_pigeonhole.py
index c215253..41abbb4 100644
--- a/pigeonhole/test/test_pigeonhole.py
+++ b/pigeonhole/test/test_pigeonhole.py
@@ -1,10 +1,9 @@
-import random
 import unittest
 import tempfile
 import shutil
 import os
-from pigeonhole import PigeonHole
-import config
+from pigeonhole import *
+#import config
 
 class TestPigeonHoleFunctions(unittest.TestCase):
 	"""Test the methods defined inside the PigeonHole class"""
@@ -19,7 +18,7 @@ class TestPigeonHoleFunctions(unittest.TestCase):
 		os.mkdir(os.path.join(self.rootdir, 'The Big Bang Theory'))
 		os.mkdir(os.path.join(self.rootdir, 'Being Erica'))
 
-		self.pigeonHole = PigeonHole(self.rootdir, self.downloaddir)
+		self.pigeonHole = pigeonhole.PigeonHole(self.rootdir, self.downloaddir)
 		
 		self.notDeletableTmpDir = tempfile.mkdtemp(prefix='pigeonHole_')
 		self.deletableTmpDir = tempfile.mkdtemp(prefix='pigeonHole_')
diff --git a/setup.py b/setup.py
index 63de899..b982237 100644
--- a/setup.py
+++ b/setup.py
@@ -1,15 +1,15 @@
 from distutils.core import setup
 
-setup {
-	name='PigeonHole',
-	version='0.1.0',
-	author='Fred Pauchet'
-	author_email='fpauchet@gmail.com',
-	packages=['pigeonhole','pigeonhole.test'],
-	scripts=[],
-	url='',
-	licence='LICENCE',
-	description='',
-	long_description=long_description=open('README').read(),
-	install_require=[],
-}
+#setup {
+#	name='PigeonHole',
+#	version='0.1.0',
+#	author='Fred Pauchet'
+#	author_email='fpauchet@gmail.com',
+#	packages=['pigeonhole','pigeonhole.test'],
+#	scripts=[],
+#	url='',
+#	licence='LICENCE',
+#	description='',
+#	long_description=long_description=open('README').read(),
+#	install_require=[],
+#}

From 2049acc7815b7a56550c29dccc2a898ab307cb80 Mon Sep 17 00:00:00 2001
From: Fred Pauchet <fpauchet@gmail.com>
Date: Thu, 29 Dec 2011 16:01:04 +0100
Subject: [PATCH 17/17] disable echo for building episode

---
 pigeonhole/model.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/pigeonhole/model.py b/pigeonhole/model.py
index 7b90e4e..a110176 100644
--- a/pigeonhole/model.py
+++ b/pigeonhole/model.py
@@ -60,8 +60,7 @@ class Episode(object):
 	""" Represents an episode within a season """
 
 	def __init__(self, parent, path):
-		print 'Building an episode: ' + path
-
+		
 		self.parent = parent
 		self.path = path
 		self.name = os.path.basename(path)