Merge pull request #31 from ScrapeGraphAI/pre/beta

SearchScraper

Author: PeriniM

README.md

@@ -9,15 +9,15 @@
   <img src="https://raw.githubusercontent.com/VinciGit00/Scrapegraph-ai/main/docs/assets/api-banner.png" alt="ScrapeGraph API Banner" style="width: 70%;">
 </p>
 
-Official SDKs for the ScrapeGraph AI API - Intelligent web scraping powered by AI. Extract structured data from any webpage with natural language prompts.
+Official SDKs for the ScrapeGraph AI API - Intelligent web scraping and search powered by AI. Extract structured data from any webpage or perform AI-powered web searches with natural language prompts.
 
 Get your [API key](https://scrapegraphai.com)!
 
 ## 🚀 Quick Links
 
 - [Python SDK Documentation](scrapegraph-py/README.md)
 - [JavaScript SDK Documentation](scrapegraph-js/README.md)
-- [API Documentation](https://docs.scrapegraphai.com) 
+- [API Documentation](https://docs.scrapegraphai.com)
 - [Website](https://scrapegraphai.com)
 
 ## 📦 Installation
@@ -34,31 +34,31 @@ npm install scrapegraph-js
 
 ## 🎯 Core Features
 
-- 🤖 **AI-Powered Extraction**: Use natural language to describe what data you want
+- 🤖 **AI-Powered Extraction & Search**: Use natural language to extract data or search the web
 - 📊 **Structured Output**: Get clean, structured data with optional schema validation
 - 🔄 **Multiple Formats**: Extract data as JSON, Markdown, or custom schemas
 - ⚡ **High Performance**: Concurrent processing and automatic retries
 - 🔒 **Enterprise Ready**: Production-grade security and rate limiting
 
 ## 🛠️ Available Endpoints
 
-### 🔍 SmartScraper
-Extract structured data from any webpage using natural language prompts.
+### 🤖 SmartScraper
+Using AI to extract structured data from any webpage or HTML content with natural language prompts.
+
+### 🔍 SearchScraper
+Perform AI-powered web searches with structured results and reference URLs.
 
 ### 📝 Markdownify
 Convert any webpage into clean, formatted markdown.
 
-### 💻 LocalScraper
-Extract information from a local HTML file using AI.
-
-
 ## 🌟 Key Benefits
 
 - 📝 **Natural Language Queries**: No complex selectors or XPath needed
 - 🎯 **Precise Extraction**: AI understands context and structure
-- 🔄 **Adaptive Scraping**: Works with dynamic and static content
+- 🔄 **Adaptive Processing**: Works with both web content and direct HTML
 - 📊 **Schema Validation**: Ensure data consistency with Pydantic/TypeScript
 - ⚡ **Async Support**: Handle multiple requests efficiently
+- 🔍 **Source Attribution**: Get reference URLs for search results
 
 ## 💡 Use Cases
 
@@ -67,13 +67,14 @@ Extract information from a local HTML file using AI.
 - 📰 **Content Aggregation**: Convert articles to structured formats
 - 🔍 **Data Mining**: Extract specific information from multiple sources
 - 📱 **App Integration**: Feed clean data into your applications
+- 🌐 **Web Research**: Perform AI-powered searches with structured results
 
 ## 📖 Documentation
 
 For detailed documentation and examples, visit:
 - [Python SDK Guide](scrapegraph-py/README.md)
 - [JavaScript SDK Guide](scrapegraph-js/README.md)
-- [API Documentation](https://docs.scrapegraphai.com) 
+- [API Documentation](https://docs.scrapegraphai.com)
 
 ## 💬 Support & Feedback
 

scrapegraph-py/CHANGELOG.md

@@ -1,3 +1,4 @@
+## [1.9.0-beta.7](https://github.com/ScrapeGraphAI/scrapegraph-sdk/compare/v1.9.0-beta.6...v1.9.0-beta.7) (2025-02-03)
 ## [1.10.2](https://github.com/ScrapeGraphAI/scrapegraph-sdk/compare/v1.10.1...v1.10.2) (2025-01-22)
 
 
@@ -18,6 +19,19 @@
 
 ### Features
 
+* add optional headers to request ([bb851d7](https://github.com/ScrapeGraphAI/scrapegraph-sdk/commit/bb851d785d121b039d5e968327fb930955a3fd92))
+* merged localscraper into smartscraper ([503dbd1](https://github.com/ScrapeGraphAI/scrapegraph-sdk/commit/503dbd19b8cec4d2ff4575786b0eec25db2e80e6))
+* modified icons ([bcb9b0b](https://github.com/ScrapeGraphAI/scrapegraph-sdk/commit/bcb9b0b731b057d242fdf80b43d96879ff7a2764))
+* searchscraper ([2e04e5a](https://github.com/ScrapeGraphAI/scrapegraph-sdk/commit/2e04e5a1bbd207a7ceeea594878bdea542a7a856))
+* updated readmes ([bfdbea0](https://github.com/ScrapeGraphAI/scrapegraph-sdk/commit/bfdbea038918d79df2e3e9442e25d5f08bbccbbc))
+
+
+### chore
+
+* refactor examples ([8e00846](https://github.com/ScrapeGraphAI/scrapegraph-sdk/commit/8e008465f7280c53e2faab7a92f02871ffc5b867))
+* **tests:** updated tests ([9149ce8](https://github.com/ScrapeGraphAI/scrapegraph-sdk/commit/9149ce85a78b503098f80910c20de69831030378))
+
+## [1.9.0-beta.6](https://github.com/ScrapeGraphAI/scrapegraph-sdk/compare/v1.9.0-beta.5...v1.9.0-beta.6) (2025-01-08)
 * add integration for sql ([2543b5a](https://github.com/ScrapeGraphAI/scrapegraph-sdk/commit/2543b5a9b84826de5c583d38fe89cf21aad077e6))
 
 

scrapegraph-py/README.md

@@ -4,7 +4,7 @@
 [![Python Support](https://img.shields.io/pypi/pyversions/scrapegraph-py.svg)](https://pypi.org/project/scrapegraph-py/)
 [![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
-[![Documentation Status](https://readthedocs.org/projects/scrapegraph-py/badge/?version=latest)](https://docs.scrapegraphai.com) 
+[![Documentation Status](https://readthedocs.org/projects/scrapegraph-py/badge/?version=latest)](https://docs.scrapegraphai.com)
 
 <p align="left">
   <img src="https://raw.githubusercontent.com/VinciGit00/Scrapegraph-ai/main/docs/assets/api-banner.png" alt="ScrapeGraph API Banner" style="width: 70%;">
@@ -20,7 +20,7 @@ pip install scrapegraph-py
 
 ## 🚀 Features
 
-- 🤖 AI-powered web scraping
+- 🤖 AI-powered web scraping and search
 - 🔄 Both sync and async clients
 - 📊 Structured output with Pydantic schemas
 - 🔍 Detailed logging
@@ -40,21 +40,36 @@ client = Client(api_key="your-api-key-here")
 
 ## 📚 Available Endpoints
 
-### 🔍 SmartScraper
+### 🤖 SmartScraper
 
-Scrapes any webpage using AI to extract specific information.
+Extract structured data from any webpage or HTML content using AI.
 
 ```python
 from scrapegraph_py import Client
 
 client = Client(api_key="your-api-key-here")
 
-# Basic usage
+# Using a URL
 response = client.smartscraper(
     website_url="https://example.com",
     user_prompt="Extract the main heading and description"
 )
 
+# Or using HTML content
+html_content = """
+<html>
+    <body>
+        <h1>Company Name</h1>
+        <p>We are a technology company focused on AI solutions.</p>
+    </body>
+</html>
+"""
+
+response = client.smartscraper(
+    website_html=html_content,
+    user_prompt="Extract the company description"
+)
+
 print(response)
 ```
 
@@ -80,46 +95,56 @@ response = client.smartscraper(
 
 </details>
 
-### 📝 Markdownify
+### 🔍 SearchScraper
 
-Converts any webpage into clean, formatted markdown.
+Perform AI-powered web searches with structured results and reference URLs.
 
 ```python
 from scrapegraph_py import Client
 
 client = Client(api_key="your-api-key-here")
 
-response = client.markdownify(
-    website_url="https://example.com"
+response = client.searchscraper(
+    user_prompt="What is the latest version of Python and its main features?"
 )
 
-print(response)
+print(f"Answer: {response['result']}")
+print(f"Sources: {response['reference_urls']}")
 ```
 
-### 💻 LocalScraper
-
-Extracts information from HTML content using AI.
+<details>
+<summary>Output Schema (Optional)</summary>
 
 ```python
+from pydantic import BaseModel, Field
 from scrapegraph_py import Client
 
 client = Client(api_key="your-api-key-here")
 
-html_content = """
-<html>
-    <body>
-        <h1>Company Name</h1>
-        <p>We are a technology company focused on AI solutions.</p>
-        <div class="contact">
-            <p>Email: contact@example.com</p>
-        </div>
-    </body>
-</html>
-"""
+class PythonVersionInfo(BaseModel):
+    version: str = Field(description="The latest Python version number")
+    release_date: str = Field(description="When this version was released")
+    major_features: list[str] = Field(description="List of main features")
+
+response = client.searchscraper(
+    user_prompt="What is the latest version of Python and its main features?",
+    output_schema=PythonVersionInfo
+)
+```
+
+</details>
 
-response = client.localscraper(
-    user_prompt="Extract the company description",
-    website_html=html_content
+### 📝 Markdownify
+
+Converts any webpage into clean, formatted markdown.
+
+```python
+from scrapegraph_py import Client
+
+client = Client(api_key="your-api-key-here")
+
+response = client.markdownify(
+    website_url="https://example.com"
 )
 
 print(response)
@@ -177,7 +202,7 @@ This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
 ## 🔗 Links
 
 - [Website](https://scrapegraphai.com)
-- [Documentation](https://docs.scrapegraphai.com) 
+- [Documentation](https://docs.scrapegraphai.com)
 - [GitHub](https://github.com/ScrapeGraphAI/scrapegraph-sdk)
 
 ---

scrapegraph-py/examples/async_markdownify_example.py renamed to scrapegraph-py/examples/async/async_markdownify_example.py

@@ -0,0 +1,46 @@
+"""
+Example of using the async searchscraper functionality to search for information concurrently.
+"""
+
+import asyncio
+
+from scrapegraph_py import AsyncClient
+from scrapegraph_py.logger import sgai_logger
+
+sgai_logger.set_logging(level="INFO")
+
+
+async def main():
+    # Initialize async client
+    sgai_client = AsyncClient(api_key="your-api-key-here")
+
+    # List of search queries
+    queries = [
+        "What is the latest version of Python and what are its main features?",
+        "What are the key differences between Python 2 and Python 3?",
+        "What is Python's GIL and how does it work?",
+    ]
+
+    # Create tasks for concurrent execution
+    tasks = [sgai_client.searchscraper(user_prompt=query) for query in queries]
+
+    # Execute requests concurrently
+    responses = await asyncio.gather(*tasks, return_exceptions=True)
+
+    # Process results
+    for i, response in enumerate(responses):
+        if isinstance(response, Exception):
+            print(f"\nError for query {i+1}: {response}")
+        else:
+            print(f"\nSearch {i+1}:")
+            print(f"Query: {queries[i]}")
+            print(f"Result: {response['result']}")
+            print("Reference URLs:")
+            for url in response["reference_urls"]:
+                print(f"- {url}")
+
+    await sgai_client.close()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())