scrapegraphai 2.3.0__tar.gz → 2.3.1__tar.gz

{scrapegraphai-2.3.0 → scrapegraphai-2.3.1}/CHANGELOG.md

@@ -1,3 +1,10 @@
+## [2.3.1](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.3.0...v2.3.1) (2026-10-06)
+
+
+### Bug Fixes
+
+* **utils:** keep Optional fields in transform_schema ([#1160](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1160)) ([9906c69](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/9906c69d0bed28c5932c5b5df79a0a9b8fe19fd7))
+
 ## [2.3.0](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.2.4...v2.3.0) (2026-09-25)
 
 

{scrapegraphai-2.3.0 → scrapegraphai-2.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: scrapegraphai
-Version: 2.3.0
+Version: 2.3.1
 Summary: A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines.
 Author-email: Marco Vinciguerra <mvincig11@gmail.com>, Lorenzo Padoan <lorenzo.padoan977@gmail.com>
 Keywords: ai,artificial intelligence,gpt,graph,langchain,llm,machine learning,natural language processing,nlp,openai,rag,scrapegraph,scrapegraphai,scraping,web scraping,web scraping library,web scraping tool,webscraping

{scrapegraphai-2.3.0 → scrapegraphai-2.3.1}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "scrapegraphai"
 
-version = "2.3.0"
+version = "2.3.1"
 
 description = "A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines."
 authors = [

{scrapegraphai-2.3.0 → scrapegraphai-2.3.1}/scrapegraphai/utils/schema_trasform.py

@@ -17,6 +17,11 @@ def transform_schema(pydantic_schema):
     def process_properties(properties):
         result = {}
         for key, value in properties.items():
+            if "anyOf" in value:
+                # Optional[X] is emitted as anyOf [X, null]: describe it as X
+                variants = [v for v in value["anyOf"] if v.get("type") != "null"]
+                if len(variants) == 1:
+                    value = {**value, **variants[0]}
             if "type" in value:
                 if value["type"] == "array":
                     if "items" in value and "$ref" in value["items"]:

scrapegraphai-2.3.1/tests/utils/schema_transform_test.py

@@ -0,0 +1,27 @@
+from typing import List, Optional
+
+from pydantic import BaseModel, Field
+
+from scrapegraphai.utils.schema_trasform import transform_schema
+
+
+class Seller(BaseModel):
+    name: str
+
+
+class Product(BaseModel):
+    title: str = Field(description="Product title")
+    price: Optional[float] = Field(default=None, description="Price in USD")
+    tags: Optional[List[str]] = None
+    seller: Optional[Seller] = None
+
+
+def test_transform_schema_keeps_optional_fields():
+    result = transform_schema(Product.model_json_schema())
+
+    assert result == {
+        "title": {"type": "string", "description": "Product title"},
+        "price": {"type": "number", "description": "Price in USD"},
+        "tags": ["string"],
+        "seller": {"name": {"type": "string", "description": ""}},
+    }