scrapegraphai 2.1.2__tar.gz → 2.1.3__tar.gz

{scrapegraphai-2.1.2 → scrapegraphai-2.1.3}/CHANGELOG.md

@@ -1,3 +1,34 @@
+## [2.1.3](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.1.2...v2.1.3) (2026-06-02)
+
+
+### Bug Fixes
+
+* **search:** restore SearchGraph by migrating DuckDuckGo backend to ddgs ([#1083](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1083)) ([2139e37](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/2139e37c0addfb9039e3b985bb33801f20e4e05b)), closes [#1082](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1082) [#1082](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1082)
+
+## [2.2.0-beta.3](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.2.0-beta.2...v2.2.0-beta.3) (2026-06-01)
+
+
+### Bug Fixes
+
+* **nodes:** update outdated ChatOllama import path to langchain_ollama ([#1076](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1076)) ([e6054cb](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/e6054cbf19a7fe940899ea70b30706f676f86fa7))
+
+
+### Docs
+
+* 📚 Standardize and fix links across translated READMEs ([#1074](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1074)) ([458d36a](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/458d36a6b83f4a412206cdbe9935a059e9d47f57))
+
+
+### CI
+
+* **release:** 2.1.2 [skip ci] ([210c992](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/210c99280048863774fa27053412185a5c18150d)), closes [#1076](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1076) [#1074](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1074)
+
+## [2.2.0-beta.2](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.2.0-beta.1...v2.2.0-beta.2) (2026-06-01)
+
+
+### Features
+
+* upgrade MiniMax default model to M3 ([#1080](https://github.com/ScrapeGraphAI/Scrapegraph-ai/issues/1080)) ([1b16c26](https://github.com/ScrapeGraphAI/Scrapegraph-ai/commit/1b16c268f4e9044c1386ccfaf67b38692b487e5a))
+
 ## [2.1.2](https://github.com/ScrapeGraphAI/Scrapegraph-ai/compare/v2.1.1...v2.1.2) (2026-06-01)
 
 

{scrapegraphai-2.1.2 → scrapegraphai-2.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: scrapegraphai
-Version: 2.1.2
+Version: 2.1.3
 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
@@ -11,7 +11,7 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: <4.0,>=3.12
 Requires-Dist: async-timeout>=4.0.0
 Requires-Dist: beautifulsoup4>=4.14.3
-Requires-Dist: duckduckgo-search>=8.1.1
+Requires-Dist: ddgs>=9.0.0
 Requires-Dist: free-proxy>=1.1.3
 Requires-Dist: html2text>=2025.4.15
 Requires-Dist: jsonschema>=4.25.1

{scrapegraphai-2.1.2 → scrapegraphai-2.1.3}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "scrapegraphai"
 
-version = "2.1.2"
+version = "2.1.3"
 
 description = "A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines."
 authors = [
@@ -30,7 +30,7 @@ dependencies = [
     "async-timeout>=4.0.0",
     "simpleeval>=1.0.3",
     "jsonschema>=4.25.1",
-    "duckduckgo-search>=8.1.1",
+    "ddgs>=9.0.0",
     "pydantic>=2.12.5",
     "scrapegraph-py>=2.0.0",
 ]

{scrapegraphai-2.1.2 → scrapegraphai-2.1.3}/scrapegraphai/helpers/models_tokens.py

@@ -408,12 +408,8 @@ models_tokens = {
         "grok-beta": 128000,
     },
     "minimax": {
+        "MiniMax-M3": 524288,
         "MiniMax-M2.7": 204000,
         "MiniMax-M2.7-highspeed": 204000,
-        "MiniMax-M1": 1000000,
-        "MiniMax-M1-40k": 40000,
-        "MiniMax-M2": 204000,
-        "MiniMax-M2.5": 204000,
-        "MiniMax-M2.5-highspeed": 204000,
     },
 }

{scrapegraphai-2.1.2 → scrapegraphai-2.1.3}/scrapegraphai/utils/research_web.py

@@ -11,7 +11,6 @@ from typing import Dict, List, Optional, Union
 
 import requests
 from bs4 import BeautifulSoup
-from langchain_community.tools import DuckDuckGoSearchResults
 from pydantic import BaseModel, Field, validator
 
 
@@ -215,12 +214,9 @@ def search_on_web(
 
         results = []
         if config.search_engine == "duckduckgo":
-            # Create a DuckDuckGo search object with max_results
-            research = DuckDuckGoSearchResults(max_results=config.max_results)
-            # Run the search
-            res = research.run(config.query)
-            # Extract URLs using regex
-            results = re.findall(r"https?://[^\s,\]]+", res)
+            results = _search_duckduckgo(
+                config.query, config.max_results, formatted_proxy
+            )
 
         elif config.search_engine == "bing":
             results = _search_bing(
@@ -247,6 +243,45 @@ def search_on_web(
         raise SearchConfigError(f"Invalid search configuration: {str(e)}")
 
 
+def _search_duckduckgo(
+    query: str, max_results: int, proxy: Optional[str] = None
+) -> List[str]:
+    """
+    Helper function for DuckDuckGo search using the ``ddgs`` package.
+
+    The ``duckduckgo-search`` package was renamed to ``ddgs``; recent
+    ``langchain-community`` releases import ``from ddgs import DDGS``, which
+    silently broke the previous langchain-based implementation. This calls
+    ``ddgs`` directly so results no longer depend on parsing a formatted string.
+
+    Args:
+        query (str): Search query
+        max_results (int): Maximum number of results to return
+        proxy (str, optional): Proxy configuration
+
+    Returns:
+        List[str]: List of URLs from search results
+    """
+    try:
+        from ddgs import DDGS
+    except ImportError as e:
+        raise ImportError(
+            "Could not import the 'ddgs' package required for DuckDuckGo "
+            "search. Please install it with `pip install -U ddgs`."
+        ) from e
+
+    try:
+        with DDGS(proxy=proxy) as ddgs:
+            results = [
+                result["href"]
+                for result in ddgs.text(query, max_results=max_results)
+                if result.get("href")
+            ]
+        return results
+    except Exception as e:
+        raise SearchRequestError(f"DuckDuckGo search failed: {str(e)}")
+
+
 def _search_bing(
     query: str, max_results: int, timeout: int, proxy: Optional[str] = None
 ) -> List[str]:

scrapegraphai-2.1.3/tests/test_minimax_models.py

@@ -0,0 +1,62 @@
+"""Tests for MiniMax model configuration."""
+
+import importlib.util
+import os
+import sys
+
+import pytest
+
+
+@pytest.fixture(scope="module")
+def models_tokens():
+    """Import models_tokens directly to avoid triggering the full package init."""
+    spec = importlib.util.spec_from_file_location(
+        "models_tokens",
+        os.path.join(
+            os.path.dirname(__file__),
+            "..",
+            "scrapegraphai",
+            "helpers",
+            "models_tokens.py",
+        ),
+    )
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module.models_tokens
+
+
+def test_minimax_m3_in_model_list(models_tokens):
+    """MiniMax-M3 should be in the model list."""
+    minimax_models = models_tokens["minimax"]
+    assert "MiniMax-M3" in minimax_models
+
+
+def test_minimax_m3_listed_first(models_tokens):
+    """MiniMax-M3 should be the first (default) model in the minimax dict."""
+    minimax_models = list(models_tokens["minimax"].keys())
+    assert minimax_models[0] == "MiniMax-M3"
+
+
+def test_minimax_m27_still_available(models_tokens):
+    """MiniMax-M2.7 and its highspeed variant should remain as legacy options."""
+    minimax_models = models_tokens["minimax"]
+    assert "MiniMax-M2.7" in minimax_models
+    assert "MiniMax-M2.7-highspeed" in minimax_models
+
+
+def test_minimax_deprecated_models_removed(models_tokens):
+    """Older deprecated MiniMax models should be removed from the list."""
+    minimax_models = models_tokens["minimax"]
+    assert "MiniMax-M2.5" not in minimax_models
+    assert "MiniMax-M2.5-highspeed" not in minimax_models
+    assert "MiniMax-M2" not in minimax_models
+    assert "MiniMax-M1" not in minimax_models
+    assert "MiniMax-M1-40k" not in minimax_models
+
+
+def test_minimax_token_limits(models_tokens):
+    """MiniMax model token limits should match upstream documentation."""
+    minimax_models = models_tokens["minimax"]
+    assert minimax_models["MiniMax-M3"] == 524288
+    assert minimax_models["MiniMax-M2.7"] == 204000
+    assert minimax_models["MiniMax-M2.7-highspeed"] == 204000