Adding new class type TextHandlers

scrapling/core/custom_types.py

@@ -3,7 +3,7 @@ from types import MappingProxyType
 from collections.abc import Mapping
 
 from scrapling.core.utils import _is_iterable, flatten
-from scrapling.core._types import Dict, List, Union, Pattern
+from scrapling.core._types import Dict, List, Union, Pattern, SupportsIndex
 
 from orjson import loads, dumps
 from w3lib.html import replace_entities as _replace_entities
@@ -69,7 +69,7 @@ class TextHandler(str):
         return [TextHandler(_replace_entities(s)) for s in results]
 
     def re_first(self, regex: Union[str, Pattern[str]], default=None, replace_entities: bool = True,
-                 clean_match: bool = False, case_sensitive: bool = False,):
+                 clean_match: bool = False, case_sensitive: bool = False) -> Union[str, None]:
         """Apply the given regex to text and return the first match if found, otherwise return the default value.
 
         :param regex: Can be either a compiled regular expression or a string.
@@ -83,6 +83,51 @@ class TextHandler(str):
         return result[0] if result else default
 
 
+class TextHandlers(List[TextHandler]):
+    """
+    The :class:`TextHandlers` class is a subclass of the builtin ``List`` class, which provides a few additional methods.
+    """
+    __slots__ = ()
+
+    def __getitem__(self, pos: Union[SupportsIndex, slice]) -> Union[TextHandler, "TextHandlers[TextHandler]"]:
+        lst = super().__getitem__(pos)
+        if isinstance(pos, slice):
+            return self.__class__(lst)
+        else:
+            return lst
+
+    def re(self, regex: Union[str, Pattern[str]], replace_entities: bool = True, clean_match: bool = False,
+            case_sensitive: bool = False) -> 'List[str]':
+        """Call the ``.re()`` method for each element in this list and return
+        their results flattened as TextHandlers.
+
+        :param regex: Can be either a compiled regular expression or a string.
+        :param replace_entities: if enabled character entity references are replaced by their corresponding character
+        :param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching
+        :param case_sensitive: if enabled, function will set the regex to ignore letters case while compiling it
+        """
+        results = [
+            n.re(regex, replace_entities, clean_match, case_sensitive) for n in self
+        ]
+        return flatten(results)
+
+    def re_first(self, regex: Union[str, Pattern[str]], default=None, replace_entities: bool = True,
+                 clean_match: bool = False, case_sensitive: bool = False) -> Union[str, None]:
+        """Call the ``.re_first()`` method for each element in this list and return
+        the first result or the default value otherwise.
+
+        :param regex: Can be either a compiled regular expression or a string.
+        :param default: The default value to be returned if there is no match
+        :param replace_entities: if enabled character entity references are replaced by their corresponding character
+        :param clean_match: if enabled, this will ignore all whitespaces and consecutive spaces while matching
+        :param case_sensitive: if enabled, function will set the regex to ignore letters case while compiling it
+        """
+        for n in self:
+            for result in n.re(regex, replace_entities, clean_match, case_sensitive):
+                return result
+        return default
+
+
 class AttributesHandler(Mapping):
     """A read-only mapping to use instead of the standard dictionary for the speed boost but
      at the same time I use it to add more functionalities.

scrapling/parser.py

@@ -3,7 +3,7 @@ from difflib import SequenceMatcher
 
 from scrapling.core.translator import HTMLTranslator
 from scrapling.core.mixins import SelectorsGeneration
-from scrapling.core.custom_types import TextHandler, AttributesHandler
+from scrapling.core.custom_types import TextHandler, TextHandlers, AttributesHandler
 from scrapling.core.storage_adaptors import SQLiteStorageSystem, StorageSystemMixin, _StorageTools
 from scrapling.core.utils import setup_basic_logging, logging, clean_spaces, flatten, html_forbidden
 from scrapling.core._types import Any, Dict, List, Tuple, Optional, Pattern, Union, Callable, Generator, SupportsIndex
@@ -158,6 +158,8 @@ class Adaptor(SelectorsGeneration):
             results = [self.__get_correct_result(n) for n in result]
             if all(isinstance(res, self.__class__) for res in results):
                 return Adaptors(results)
+            elif all(isinstance(res, TextHandler) for res in results):
+                return TextHandlers(results)
             return results
 
         return self.__get_correct_result(result)