Update default data_format to html, bump version to 1.0.6, and update README

Author: עידן וילנסקי

brightdata/__init__.py

@@ -32,7 +32,7 @@
     APIError
 )
 
-__version__ = "1.0.5"
+__version__ = "1.0.6"
 __author__ = "Bright Data"
 __email__ = "[email protected]"
 

brightdata/client.py

@@ -141,7 +141,7 @@ def scrape(
         response_format: str = "raw",
         method: str = "GET", 
         country: str = "",
-        data_format: str = "markdown",
+        data_format: str = "html",
         async_request: bool = False,
         max_workers: int = None,
         timeout: int = None
@@ -154,10 +154,10 @@ def scrape(
         ### Parameters:
         - `url` (str | List[str]): Single URL string or list of URLs to scrape
         - `zone` (str, optional): Zone identifier (default: auto-configured web_unlocker_zone)
-        - `response_format` (str, optional): Response format - `"json"` for structured data, `"raw"` for HTML string (default: `"json"`)
+        - `response_format` (str, optional): Response format - `"json"` for structured data, `"raw"` for HTML string (default: `"raw"`)
         - `method` (str, optional): HTTP method for the request (default: `"GET"`)
         - `country` (str, optional): Two-letter ISO country code for proxy location (defaults to fastest connection)
-        - `data_format` (str, optional): Additional format transformation (default: `"markdown"`)
+        - `data_format` (str, optional): Additional format transformation (default: `"html"`)
         - `async_request` (bool, optional): Enable asynchronous processing (default: `False`)
         - `max_workers` (int, optional): Maximum parallel workers for multiple URLs (default: `10`)
         - `timeout` (int, optional): Request timeout in seconds (default: `30`)
@@ -204,7 +204,7 @@ def search(
         response_format: str = "raw",
         method: str = "GET",
         country: str = "",
-        data_format: str = "markdown",
+        data_format: str = "html",
         async_request: bool = False,
         max_workers: int = None,
         timeout: int = None,
@@ -220,10 +220,10 @@ def search(
         - `query` (str | List[str]): Search query string or list of search queries
         - `search_engine` (str, optional): Search engine to use - `"google"`, `"bing"`, or `"yandex"` (default: `"google"`)
         - `zone` (str, optional): Zone identifier (default: auto-configured serp_zone)
-        - `response_format` (str, optional): Response format - `"json"` for structured data, `"raw"` for HTML string (default: `"json"`)
+        - `response_format` (str, optional): Response format - `"json"` for structured data, `"raw"` for HTML string (default: `"raw"`)
         - `method` (str, optional): HTTP method for the request (default: `"GET"`)
         - `country` (str, optional): Two-letter ISO country code for proxy location (default: `"us"`)
-        - `data_format` (str, optional): Additional format transformation (default: `"markdown"`)
+        - `data_format` (str, optional): Additional format transformation (default: `"html"`)
         - `async_request` (bool, optional): Enable asynchronous processing (default: `False`)
         - `max_workers` (int, optional): Maximum parallel workers for multiple queries (default: `10`)
         - `timeout` (int, optional): Request timeout in seconds (default: `30`)

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "brightdata-sdk"
-version = "1.0.5"
+version = "1.0.6"
 description = "Python SDK for Bright Data Web Scraping and SERP APIs"
 authors = [
     {name = "Bright Data", email = "[email protected]"}