chg: [pystemon importer] create new PystemonImporter module, refactor pystemon feeder

bin/LAUNCH.sh

@@ -483,7 +483,7 @@ function launch_feeder {
         screen -dmS "Feeder_Pystemon"
         sleep 0.1
         echo -e $GREEN"\t* Launching Pystemon feeder"$DEFAULT
-        screen -S "Feeder_Pystemon" -X screen -t "Pystemon_feeder" bash -c "cd ${AIL_BIN}; ${ENV_PY} ./feeder/pystemon-feeder.py; read x"
+        screen -S "Feeder_Pystemon" -X screen -t "Pystemon_feeder" bash -c "cd ${AIL_BIN}; ${ENV_PY} ./importer/PystemonImporter.py; read x"
         sleep 0.1
         screen -S "Feeder_Pystemon" -X screen -t "Pystemon" bash -c "cd ${AIL_HOME}/../pystemon; ${ENV_PY} ./pystemon.py; read x"
     else

bin/feeder/pystemon-feeder.py

@@ -1,83 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-#
-# This file is part of AIL framework - Analysis Information Leak framework
-#
-# This a simple feeder script feeding data from pystemon to AIL.
-#
-# Don't forget to set your pystemonpath and ensure that the
-# configuration matches this script. Default is Redis DB 10.
-#
-# https://github.com/cvandeplas/pystemon/blob/master/pystemon.yaml#L16
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# Copyright (c) 2014 Alexandre Dulaunoy - a@foo.be
-
-import os
-import sys
-
-import zmq
-import random
-import time
-import redis
-import base64
-
-sys.path.append(os.path.join(os.environ['AIL_BIN'], 'lib/'))
-import ConfigLoader
-
-config_loader = ConfigLoader.ConfigLoader()
-
-if config_loader.has_option("ZMQ_Global", "bind"):
-    zmq_url = config_loader.get_config_str("ZMQ_Global", "bind")
-else:
-    zmq_url = "tcp://127.0.0.1:5556"
-
-pystemonpath = config_loader.get_config_str("Directories", "pystemonpath")
-pastes_directory = config_loader.get_config_str("Directories", "pastes")
-pastes_directory = os.path.join(os.environ['AIL_HOME'], pastes_directory)
-base_sleeptime = 0.01
-sleep_inc = 0
-
-config_loader = None
-
-context = zmq.Context()
-socket = context.socket(zmq.PUB)
-socket.bind(zmq_url)
-
-# check https://github.com/cvandeplas/pystemon/blob/master/pystemon.yaml#L16
-r = redis.StrictRedis(host='localhost', db=10, decode_responses=True)
-
-# 101 pastes processed feed
-# 102 raw pastes feed
-topic = '102'
-
-while True:
-    time.sleep(base_sleeptime + sleep_inc)
-    item_id = r.lpop("pastes")
-    if item_id is None:
-        continue
-    try:
-        print(item_id)
-        full_item_path = os.path.join(pystemonpath, item_id)
-        if not os.path.isfile(full_item_path):
-            print('Error: {}, file not found'.format(full_item_path))
-            sleep_inc = 1
-            continue
-
-        with open(full_item_path, 'rb') as f: #.read()
-            messagedata = f.read()
-        path_to_send = os.path.join(pastes_directory, item_id)
-        path_to_send = 'pystemon>>' + path_to_send
-
-        s = b' '.join( [ topic.encode(), path_to_send.encode(), base64.b64encode(messagedata) ] )
-        socket.send(s)
-        sleep_inc = sleep_inc-0.01 if sleep_inc-0.01 > 0 else 0
-    except IOError as e:
-        # file not found, could be a buffering issue -> increase sleeping time
-        print('IOError: Increasing sleep time')
-        sleep_inc += 0.5
-        continue

bin/importer/PystemonImporter.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# This file is part of AIL framework - Analysis Information Leak framework
+#
+# This a simple feeder script feeding data from pystemon to AIL.
+#
+# Don't forget to set your pystemonpath and ensure that the
+# configuration matches this script. Default is Redis DB 10.
+# https://github.com/cvandeplas/pystemon/blob/master/pystemon.yaml#L52
+#
+
+import base64
+import os
+import gzip
+import sys
+import redis
+
+sys.path.append(os.environ['AIL_BIN'])
+##################################
+# Import Project packages
+##################################
+from importer.abstract_importer import AbstractImporter
+from modules.abstract_module import AbstractModule
+from lib.ConfigLoader import ConfigLoader
+
+class PystemonImporter(AbstractImporter):
+    def __init__(self, pystemon_dir, host='localhost', port=6379, db=10):
+        super().__init__()
+        # Check Pystemon Redis Config:
+        #       https://github.com/cvandeplas/pystemon/blob/master/pystemon.yaml#L54
+        self.r_pystemon = redis.StrictRedis(host=host, port=port, db=db, decode_responses=True)
+        self.dir_pystemon = pystemon_dir
+
+    # # TODO: add exception
+    def encode_and_compress_data(self, content):
+        return base64.b64encode(gzip.compress(content)).decode()
+
+    def importer(self):
+        item_id = self.r_pystemon.lpop("pastes")
+        print(item_id)
+        if item_id:
+            print(item_id)
+            full_item_path = os.path.join(self.dir_pystemon, item_id) # TODO SANITIZE PATH
+            # Check if pystemon file exists
+            if not os.path.isfile(full_item_path):
+                print(f'Error: {full_item_path}, file not found')
+                return None
+            # Get Item Content
+            try:
+                with open(full_item_path, 'rb') as f:
+                    content = f.read()
+                if not content:
+                    return None
+
+                b64_gzipped_content = self.encode_and_compress_data(content)
+                print(item_id, b64_gzipped_content)
+                return f'{item_id} {b64_gzipped_content}'
+            except IOError as e:
+                print(f'Error: {full_item_path}, IOError')
+        return None
+
+
+class PystemonModuleImporter(AbstractModule):
+
+    def __init__(self):
+        super().__init__()
+        self.pending_seconds = 10
+        config_loader = ConfigLoader()
+        # TODO MIGRATE OLD CONFIG
+        # dir_pystemon = config_loader.get_config_str("Directories", "pystemonpath")
+        # Check Pystemon Redis Config:
+        #       https://github.com/cvandeplas/pystemon/blob/master/pystemon.yaml#L54
+        dir_pystemon = config_loader.get_config_str("Pystemon", "dir")
+        host = config_loader.get_config_str("Pystemon", "redis_host")
+        port = config_loader.get_config_str("Pystemon", "redis_port")
+        db = config_loader.get_config_str("Pystemon", "redis_db")
+        self.importer = PystemonImporter(dir_pystemon, host=host, port=port, db=db)
+
+    def get_message(self):
+        return self.importer.importer()
+
+    def compute(self, message):
+        relay_message = f'pystemon {message}'
+        self.add_message_to_queue(relay_message)
+
+
+if __name__ == '__main__':
+    module = PystemonModuleImporter()
+    module.run()

configs/core.cfg.sample

@@ -18,10 +18,14 @@ tldsfile = faup/src/data/mozilla.tlds
 
 domainstrending_csv = var/www/static/csv/domainstrendingdata
 
-pystemonpath = /home/pystemon/pystemon/
-
 sentiment_lexicon_file = sentiment/vader_lexicon.zip/vader_lexicon/vader_lexicon.txt
 
+[Pystemon]
+dir = /home/pystemon/pystemon/
+redis_host = localhost
+redis_port = 6379
+redis_db = 10
+
 ##### Logs ######
 [Logs]
 # activate syslog

configs/modules.cfg

@@ -7,6 +7,9 @@ publish = Importers
 [Importer_Json]
 publish = Importers,Tags
 
+[PystemonModuleImporter]
+publish = Importers
+
 ####################################################
 
 [Mixer]