added gitigore

.gitignore

@@ -0,0 +1,29 @@
+^JAVA_CMD$
+^PYTHON_CMD$
+
+.DS_Store
+
+# ignore any data
+^data/*$
+
+# ignore working bytecode
+\.class$
+\.pyc$
+
+^datadump/*
+
+# ignore test and tutorial directories
+test/*$
+tests/*$
+testsuite/*$
+tutorial/*$
+
+# Solr/Jetty
+^java/solr/server/solr-webapp/*
+^java/solr/server/logs/*
+
+# ignore the downloaded logos
+^python/media/images/logos/*
+
+# PyCharm project files
+^.idea/

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/stackdump.iml" filepath="$PROJECT_DIR$/.idea/stackdump.iml" />
+    </modules>
+  </component>
+</project>

.idea/stackdump.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

manage.sh

@@ -35,5 +35,5 @@ else
     # shift off the command name so we don't pass it on
     shift
 
-    $SCRIPT_DIR/start_python.sh $command "$@"
+    $SCRIPT_DIR/start_python3.sh $command "$@"
 fi

python/src/stackdump/commands/download_site_info.py

@@ -6,29 +6,37 @@ import urllib
 from xml.etree import ElementTree
 import os
 import sys
+We
+
+se_dir = os.path.join(os.environ.get('HOME'), 'stackexchange')
+sites_path = os.path.join(se_dir, 'Sites.xml')
 
 script_dir = os.path.dirname(sys.argv[0])
 sites_file_path = os.path.join(script_dir, '../../../../data/sites')
 
-# ensure the data directory exists
+# ensure the data directory exists\\\\
 if not os.path.exists(os.path.dirname(sites_file_path)):
     os.mkdir(os.path.dirname(sites_file_path))
 
 # download the sites RSS file
-print 'Downloading StackExchange sites RSS file...',
-urllib.urlretrieve('http://stackexchange.com/feeds/sites', sites_file_path)
-print 'done.'
+print('Downloading StackExchange sites XML file...',)
+urllib.urlretrieve('https://archive.org/download/stackexchange/Sites.xml', sites_file_path)
+print('done.')
 
-print ''
+print('')
 
-# parse sites RSS file and download logos
-logos_dir_path = os.path.join(script_dir, '../../../media/images/logos')
+# parse sites RSS file and download logosc
+images_dir_path = os.path.join(script_dir, '../../../media/images/logos')
+logos_dir_path = os.path.join(images_dir_path, 'logos')
+icons_dir_path = os.path.join(images_dir_path, 'icons')
+badgos_dir_path = os.path.join(images_dir_path, 'badgos')
 if not os.path.exists(logos_dir_path):
     os.mkdir(logos_dir_path)
 
-with open(sites_file_path) as f:
+with open(sites_path) as f:
     sites_file = ElementTree.parse(f)
-    entries = sites_file.findall('{http://www.w3.org/2005/Atom}entry')
+    entries = sites_file.findall('sites/row')
+    print(entries)
     
     for entry in entries:
         entry_title = entry.find('{http://www.w3.org/2005/Atom}title').text.encode('ascii', 'ignore')
@@ -42,6 +50,7 @@ with open(sites_file_path) as f:
         if site_key.endswith('.stackexchange'):
             site_key = site_key[:-len('.stackexchange')]
         
-        print 'Downloading logo for %s...' % entry_title,
-        urllib.urlretrieve('http://cdn.sstatic.net/Sites/%s/img/icon-48.png' % site_key, os.path.join(logos_dir_path, '%s.png' % site_key))
-        print 'done.'
+        print('Downloading logo for %s...' % entry_title,
+              urllib.urlretrieve('http://cdn.sstatic.net/Sites/%s/img/icon-48.png' % site_key,
+                                 os.path.join(logos_dir_path, '%s.png' % site_key)))
+        print('done.')

start_python3.sh

@@ -0,0 +1,54 @@
+#!/bin/bash
+
+##
+# This script attempts to find a version of Python on the system PATH, and
+# checks that it is 2.5+.
+#
+# A alternate Python command can be specified in a file named PYTHON_CMD in this
+# script's directory. This path will override any lookup on the system PATH.
+##
+
+# FUNCTIONS
+function checkPythonVersion {
+    if [ ! -z "$1" ]
+    then
+        PYTHON_VER_MAJOR=`echo $1 | cut -d "." -f 1`
+        PYTHON_VER_MINOR=`echo $1 | cut -d "." -f 2`
+        
+        if [ $PYTHON_VER_MAJOR -eq "3" -a $PYTHON_VER_MINOR -ge "5" ]
+        then
+            return 1
+        fi
+    fi
+    
+    return 0
+}
+
+# MAIN
+SCRIPT_DIR=`dirname $0`
+PYTHON_CMD=python3
+
+# if there is a PYTHON_CMD file in the script directory, use that instead
+if [ -e "$SCRIPT_DIR/PYTHON_CMD" ]
+then
+    PYTHON_CMD=`cat "$SCRIPT_DIR/PYTHON_CMD"`
+fi
+
+if [ ! -z "`which "$PYTHON_CMD" 2>/dev/null`" ]
+then
+    # check if Python is the right version
+    PYTHON_VER=`"$PYTHON_CMD" -V 2>&1 | cut -d " " -f 2`
+    checkPythonVersion "$PYTHON_VER"
+    if [ $? == 1 ]
+    then
+        echo "Using Python `which "$PYTHON_CMD"`"
+        
+        # execution ends here if Python is found
+        PYTHONPATH=$SCRIPT_DIR/python3/packages:$SCRIPT_DIR/python3/src:$PYTHONPATH
+        env "PYTHONPATH=$PYTHONPATH" "$PYTHON_CMD" "$@"
+        exit $?
+    fi
+fi
+
+# if we get here, it means the right version of Python was not found
+echo 'No suitable version of Python was found. Python 2.5 or later is required.'