Implement extraction command

Requires !9 (merged)

Closes #9 (closed)

dan/datasets/extract/utils.py

-#!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 
 """
@@ -25,6 +24,13 @@ def get_cli_args():
         help="Name of the corpus from which the data will be retrieved.",
         required=True,
     )
+    parser.add_argument(
+        "--element-type",
+        nargs="+",
+        type=str,
+        help="Type of elements to retrieve",
+        required=True,
+    )
     parser.add_argument(
         "--parents-types",
         nargs="+",
@@ -47,4 +53,22 @@ def get_cli_args():
         help="Names of parents of the elements.",
         default=None,
     )
+    parser.add_argument(
+        "--no-entities", action="store_true", help="Extract text without entities"
+    )
+
+    parser.add_argument(
+        "--use-existing-split",
+        action="store_true",
+        help="Do not partition pages into train/val/test",
+    )
+
+    parser.add_argument(
+        "--train-prob", type=float, default=0.7, help="Training set probability"
+    )
+
+    parser.add_argument(
+        "--val-prob", type=float, default=0.15, help="Validation set probability"
+    )
+
     return parser.parse_args()