fix: [crawler] crawler capture with empty task

bin/lib/crawlers.py

@@ -430,7 +430,6 @@ def _reprocess_all_hars_hhhashs():
         extract_hhhash_by_id(har_id, domain, date)
 
 
-
 def _gzip_har(har_id):
     har_path = os.path.join(HAR_DIR, har_id)
     new_id = f'{har_path}.gz'
@@ -1436,8 +1435,8 @@ class CrawlerCapture:
         launch_time = int(time.time())
         r_crawler.hset(f'crawler:task:{task_uuid}', 'capture', self.uuid)
         r_crawler.hset('crawler:captures:tasks', self.uuid, task_uuid)
-        r_crawler.zadd('crawler:captures', {self.uuid: launch_time})
         r_cache.hset(f'crawler:capture:{self.uuid}', 'launch_time', launch_time)
+        r_crawler.zadd('crawler:captures', {self.uuid: launch_time})
         r_cache.zadd('crawler:captures', {self.uuid: launch_time})
 
     def update(self, status):
@@ -1481,6 +1480,15 @@ def get_captures_status():
     for capture_uuid in get_crawler_captures():
         capture = CrawlerCapture(capture_uuid)
         task = capture.get_task()
+        if not task:
+            meta = {
+                'uuid': 'UNKNOWN',
+                'domain': 'UNKNOWN',
+                'type': 'UNKNOWN',
+                'start_time': capture.get_start_time(),
+                'status': capture.get_status(),
+            }
+        else:
             domain = task.get_domain()
             dom = Domain(domain)
             meta = {
@@ -1919,10 +1927,10 @@ def create_item_id(item_dir, domain):
     # remove /
     domain = domain.replace('/', '_')
     if len(domain) > 215:
-        UUID = domain[-215:]+str(uuid.uuid4())
+        n_uuid = domain[-215:]+str(uuid.uuid4())
     else:
-        UUID = domain+str(uuid.uuid4())
-    return os.path.join(item_dir, UUID)
+        n_uuid = domain+str(uuid.uuid4())
+    return os.path.join(item_dir, n_uuid)
 
 # # # # # # # # # # # #
 #                     #
@@ -2161,7 +2169,7 @@ load_blacklist()
 
 # if __name__ == '__main__':
 #     delete_captures()
-
+#
 #     item_id = 'crawled/2023/02/20/data.gz'
 #     item = Item(item_id)
 #     content = item.get_content()