v1.1.3: Enhanced extract function and fixed parse_content auto-detection

- Added url and output_scheme parameters to extract function
- Implemented OpenAI Structured Outputs support with schema validation
- Fixed parse_content to auto-detect multiple results
- Added user-agent headers to all dataset API requests
- Updated examples with proper schema formatting

Author: Idan Vilenski

README.md

@@ -152,19 +152,28 @@ print(f"Found {len(parsed['links'])} links")
 
 #### `extract()`
 ```python
-# Simple AI-powered extraction using natural language
-result = client.extract("extract the latest news headlines from bbc.com")
-print(result)  # Prints extracted headlines directly
-
-# Extract specific information with custom query
-result = client.extract("get product name and price from amazon.com/dp/B079QHML21")
-print(f"Product info: {result}")
-print(f"Source: {result.url}")
-print(f"Tokens used: {result.token_usage['total_tokens']}")
-
-# Extract structured data
-result = client.extract("find contact information and business hours from company-website.com")
-print(result)  # AI-formatted contact details
+# Basic extraction (URL in query)
+result = client.extract("Extract news headlines from CNN.com")
+print(result)
+
+# Using URL parameter with structured output
+schema = {
+    "type": "object",
+    "properties": {
+        "headlines": {
+            "type": "array",
+            "items": {"type": "string"}
+        }
+    },
+    "required": ["headlines"]
+}
+
+result = client.extract(
+    query="Extract main headlines",
+    url="https://cnn.com",
+    output_scheme=schema
+)
+print(result)  # Returns structured JSON matching the schema
 ```
 
 #### `connect_browser()`
@@ -265,13 +274,15 @@ Extract and parse useful information from API responses.
 <details>
     <summary>🤖 <strong>extract(...)</strong></summary>
 
-Extract specific information from websites using AI-powered natural language processing.
+Extract specific information from websites using AI-powered natural language processing with OpenAI.
 
 ```python
-- `query`: Natural language query containing what to extract and from which URL (required)
+- `query`: Natural language query describing what to extract (required)
+- `url`: Single URL or list of URLs to extract from (optional - if not provided, extracts URL from query)
+- `output_scheme`: JSON Schema for OpenAI Structured Outputs (optional - enables reliable JSON responses)
 - `llm_key`: OpenAI API key (optional - uses OPENAI_API_KEY env variable if not provided)
 
-# Returns: Extracted content as string with metadata attributes
+# Returns: ExtractResult object (string-like with metadata attributes)
 # Available attributes: .url, .query, .source_title, .token_usage, .content_length
 ```
 

brightdata/__init__.py

@@ -64,7 +64,7 @@
 )
 from .utils import parse_content, parse_multiple, extract_structured_data
 
-__version__ = "1.1.2"
+__version__ = "1.1.3"
 __author__ = "Bright Data"
 __email__ = "[email protected]"
 

brightdata/api/chatgpt.py

@@ -42,9 +42,16 @@ def scrape_chatgpt(
         - Dict containing response with snapshot_id or direct data (if sync=True)
         """
         url = "https://api.brightdata.com/datasets/v3/scrape" if sync else "https://api.brightdata.com/datasets/v3/trigger"
+        try:
+            from .. import __version__
+            user_agent = f"brightdata-sdk/{__version__}"
+        except ImportError:
+            user_agent = "brightdata-sdk/unknown"
+        
         headers = {
             "Authorization": f"Bearer {self.api_token}",
-            "Content-Type": "application/json"
+            "Content-Type": "application/json",
+            "User-Agent": user_agent
         }
         params = {
             "dataset_id": "gd_m7aof0k82r803d5bjm",

brightdata/api/download.py

@@ -125,9 +125,16 @@ def download_snapshot(
                 raise ValidationError("Part parameter requires batch_size to be specified")
 
         url = f"https://api.brightdata.com/datasets/v3/snapshot/{snapshot_id}"
+        try:
+            from .. import __version__
+            user_agent = f"brightdata-sdk/{__version__}"
+        except ImportError:
+            user_agent = "brightdata-sdk/unknown"
+        
         headers = {
             "Authorization": f"Bearer {self.api_token}",
-            "Accept": "application/json"
+            "Accept": "application/json",
+            "User-Agent": user_agent
         }
         params = {
             "format": format