fix: [crawler] filter lookup parent + domain daterange

bin/crawlers/Crawler.py

@@ -78,6 +78,7 @@ def __init__(self):
         self.items_dir = None
         self.original_domain = None
         self.domain = None
+        self.parent = None
 
         # TODO Replace with warning list ???
         self.placeholder_screenshots = {'07244254f73e822bd4a95d916d8b27f2246b02c428adc29082d09550c6ed6e1a'   # blank
@@ -243,6 +244,7 @@ def compute(self, capture):
             return None
 
         self.domain = Domain(domain)
+        self.parent = self.domain.get_parent()
         self.original_domain = Domain(domain)
 
         epoch = int(time.time())
@@ -263,14 +265,17 @@ def compute(self, capture):
         # Save Capture
         self.save_capture_response(parent_id, entries)
 
-        self.domain.update_daterange(self.date.replace('/', ''))
+        if self.parent != 'lookup':
+            # Update domain first/last seen
+            self.domain.update_daterange(self.date.replace('/', ''))
         # Origin + History + tags
         if self.root_item:
             self.domain.set_last_origin(parent_id)
             self.domain.update_vanity_cluster()
             # Tags
             for tag in task.get_tags():
                 self.domain.add_tag(tag)
+        # Crawler stats
         self.domain.add_history(epoch, root_item=self.root_item)
 
         if self.domain != self.original_domain:

bin/lib/ail_core.py

@@ -86,7 +86,7 @@ def get_default_correlation_objects():
     return AIL_OBJECTS_CORRELATIONS_DEFAULT
 
 def get_obj_queued():
-    return ['item', 'image', 'message', 'ocr', 'qrcode']
+    return ['item', 'image', 'message', 'ocr', 'qrcode'] # screenshot ???
 
 def get_objects_tracked():
     return ['decoded', 'item', 'pgp', 'message', 'ocr', 'qrcode', 'title']

bin/lib/ail_queues.py

@@ -195,6 +195,9 @@ def get_processed_end_objs():
 def get_processed_end_obj():
     return r_obj_process.spop(f'objs:processed')
 
+def is_obj_in_process(obj_gid):
+    return r_obj_process.sismember(f'objs:process', obj_gid)
+
 def get_processed_objs_by_type(obj_type):
     return r_obj_process.zrange(f'objs:process:{obj_type}', 0, -1)
 

bin/lib/crawlers.py

@@ -67,7 +67,7 @@
 # is safe ???
 # TODO FILTER URL ???
 
-def api_get_onion_lookup(domain):
+def api_get_onion_lookup(domain):  # TODO check if object process done ???
     domain = domain.lower()
     url_unpack = unpack_url(domain)
     domain = url_unpack['domain']
@@ -78,6 +78,11 @@ def api_get_onion_lookup(domain):
         if is_crawler_activated():
             create_task(domain, parent='lookup', priority=0, har=D_HAR, screenshot=D_SCREENSHOT)
         return {'error': 'domain not found', 'domain': domain}, 404
+    if not dom.was_up():
+        return {'error': 'domain not found', 'domain': domain}, 404
+    # else
+    ## TODO check if object process done -> return result if more than one history
+    #   #-> check item history
     meta = dom.get_meta(options={'languages'})
     meta['first_seen'] = meta['first_seen'].replace('/', '-')
     meta['last_seen'] = meta['last_check'].replace('/', '-')

bin/lib/objects/abstract_object.py

@@ -19,6 +19,7 @@
 # Import Project packages
 ##################################
 from lib import ail_logger
+from lib.ail_queues import is_obj_in_process
 from lib import Tag
 from lib.ConfigLoader import ConfigLoader
 from lib import Duplicate
@@ -92,6 +93,15 @@ def _set_field(self, field, value):
         else:
             return r_object.hset(f'meta:{self.type}:{self.get_subtype(r_str=True)}:{self.id}', field, value)
 
+    ## Queues ##
+
+    # is_in_queue , is_in_module
+
+    def is_being_processed(self):
+        return is_obj_in_process(self.get_global_id())
+
+    # -Queues- #
+
     ## Tags ##
     def get_tags(self, r_list=False):
         tags = Tag.get_object_tags(self.type, self.id, self.get_subtype(r_str=True))