diff --git a/crawl4ai/async_configs.py b/crawl4ai/async_configs.py
index aa0b849e..3d866529 100644
--- a/crawl4ai/async_configs.py
+++ b/crawl4ai/async_configs.py
@@ -1,14 +1,18 @@
 from .config import (
-    MIN_WORD_THRESHOLD, 
+    MIN_WORD_THRESHOLD,
     IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD,
     SCREENSHOT_HEIGHT_TRESHOLD,
-    PAGE_TIMEOUT
+    PAGE_TIMEOUT,
+    IMAGE_SCORE_THRESHOLD,
+    SOCIAL_MEDIA_DOMAINS,
+
 )
 from .user_agent_generator import UserAgentGenerator
 from .extraction_strategy import ExtractionStrategy
 from .chunking_strategy import ChunkingStrategy
 from .markdown_generation_strategy import MarkdownGenerationStrategy
 
+
 class BrowserConfig:
     """
     Configuration class for setting up a browser instance and its context in AsyncPlaywrightCrawlerStrategy.
@@ -127,7 +131,7 @@ class BrowserConfig:
         self.extra_args = extra_args if extra_args is not None else []
         self.sleep_on_close = sleep_on_close
         self.verbose = verbose
-        
+
         user_agenr_generator = UserAgentGenerator()
         if self.user_agent_mode != "random":
             self.user_agent = user_agenr_generator.generate(
@@ -160,15 +164,16 @@ class BrowserConfig:
             java_script_enabled=kwargs.get("java_script_enabled", True),
             cookies=kwargs.get("cookies", []),
             headers=kwargs.get("headers", {}),
-            user_agent=kwargs.get("user_agent",
+            user_agent=kwargs.get(
+                "user_agent",
                 "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
-                "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36"
+                "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36",
             ),
             user_agent_mode=kwargs.get("user_agent_mode"),
             user_agent_generator_config=kwargs.get("user_agent_generator_config"),
             text_only=kwargs.get("text_only", False),
             light_mode=kwargs.get("light_mode", False),
-            extra_args=kwargs.get("extra_args", [])
+            extra_args=kwargs.get("extra_args", []),
         )
 
 
@@ -182,22 +187,37 @@ class CrawlerRunConfig:
     By using this class, you have a single place to understand and adjust the crawling options.
 
     Attributes:
+        # Content Processing Parameters
         word_count_threshold (int): Minimum word count threshold before processing content.
                                     Default: MIN_WORD_THRESHOLD (typically 200).
         extraction_strategy (ExtractionStrategy or None): Strategy to extract structured data from crawled pages.
                                                           Default: None (NoExtractionStrategy is used if None).
         chunking_strategy (ChunkingStrategy): Strategy to chunk content before extraction.
                                               Default: RegexChunking().
+        markdown_generator (MarkdownGenerationStrategy): Strategy for generating markdown.
+                                                         Default: None.
         content_filter (RelevantContentFilter or None): Optional filter to prune irrelevant content.
                                                         Default: None.
+        only_text (bool): If True, attempt to extract text-only content where applicable.
+                          Default: False.
+        css_selector (str or None): CSS selector to extract a specific portion of the page.
+                                    Default: None.
+        excluded_tags (list of str or None): List of HTML tags to exclude from processing.
+                                             Default: None.
+        keep_data_attributes (bool): If True, retain `data-*` attributes while removing unwanted attributes.
+                                     Default: False.
+        remove_forms (bool): If True, remove all `<form>` elements from the HTML.
+                             Default: False.
+        prettiify (bool): If True, apply `fast_format_html` to produce prettified HTML output.
+                          Default: False.
+
+        # Caching Parameters
         cache_mode (CacheMode or None): Defines how caching is handled.
                                         If None, defaults to CacheMode.ENABLED internally.
                                         Default: None.
-        session_id (str or None):   Optional session ID to persist the browser context and the created 
-                                    page instance. If the ID already exists, the crawler does not 
-                                    create a new page and uses the current page to preserve the state;
-                                    if not, it creates a new page and context then stores it in 
-                                    memory with the given session ID.
+        session_id (str or None): Optional session ID to persist the browser context and the created
+                                  page instance. If the ID already exists, the crawler does not
+                                  create a new page and uses the current page to preserve the state.
         bypass_cache (bool): Legacy parameter, if True acts like CacheMode.BYPASS.
                              Default: False.
         disable_cache (bool): Legacy parameter, if True acts like CacheMode.DISABLED.
@@ -206,36 +226,32 @@ class CrawlerRunConfig:
                               Default: False.
         no_cache_write (bool): Legacy parameter, if True acts like CacheMode.READ_ONLY.
                                Default: False.
-        css_selector (str or None): CSS selector to extract a specific portion of the page.
-                                    Default: None.
-        screenshot (bool): Whether to take a screenshot after crawling.
-                           Default: False.
-        pdf (bool): Whether to generate a PDF of the page.
-                    Default: False.
-        verbose (bool): Enable verbose logging.
-                        Default: True.
-        only_text (bool): If True, attempt to extract text-only content where applicable.
-                          Default: False.
-        image_description_min_word_threshold (int): Minimum words for image description extraction.
-                                                    Default: IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD (e.g., 50).
-        prettiify (bool): If True, apply `fast_format_html` to produce prettified HTML output.
-                          Default: False.
-        js_code (str or list of str or None): JavaScript code/snippets to run on the page.
-                                              Default: None.
-        wait_for (str or None): A CSS selector or JS condition to wait for before extracting content.
-                                Default: None.
-        js_only (bool): If True, indicates subsequent calls are JS-driven updates, not full page loads.
-                        Default: False.
+
+        # Page Navigation and Timing Parameters
         wait_until (str): The condition to wait for when navigating, e.g. "domcontentloaded".
                           Default: "domcontentloaded".
         page_timeout (int): Timeout in ms for page operations like navigation.
                             Default: 60000 (60 seconds).
+        wait_for (str or None): A CSS selector or JS condition to wait for before extracting content.
+                                Default: None.
+        wait_for_images (bool): If True, wait for images to load before extracting content.
+                                Default: True.
+        delay_before_return_html (float): Delay in seconds before retrieving final HTML.
+                                          Default: 0.1.
+        mean_delay (float): Mean base delay between requests when calling arun_many.
+                            Default: 0.1.
+        max_range (float): Max random additional delay range for requests in arun_many.
+                           Default: 0.3.
+        semaphore_count (int): Number of concurrent operations allowed.
+                               Default: 5.
+
+        # Page Interaction Parameters
+        js_code (str or list of str or None): JavaScript code/snippets to run on the page.
+                                              Default: None.
+        js_only (bool): If True, indicates subsequent calls are JS-driven updates, not full page loads.
+                        Default: False.
         ignore_body_visibility (bool): If True, ignore whether the body is visible before proceeding.
                                        Default: True.
-        wait_for_images (bool): If True, wait for images to load before extracting content. 
-                                Default: True.
-        adjust_viewport_to_content (bool): If True, adjust viewport according to the page content dimensions.
-                                           Default: False.
         scan_full_page (bool): If True, scroll through the entire page to load all content.
                                Default: False.
         scroll_delay (float): Delay in seconds between scroll steps if scan_full_page is True.
@@ -244,163 +260,322 @@ class CrawlerRunConfig:
                                 Default: False.
         remove_overlay_elements (bool): If True, remove overlays/popups before extracting HTML.
                                         Default: False.
-        delay_before_return_html (float): Delay in seconds before retrieving final HTML.
-                                          Default: 0.1.
-        log_console (bool): If True, log console messages from the page.
-                            Default: False.
         simulate_user (bool): If True, simulate user interactions (mouse moves, clicks) for anti-bot measures.
                               Default: False.
         override_navigator (bool): If True, overrides navigator properties for more human-like behavior.
                                    Default: False.
         magic (bool): If True, attempts automatic handling of overlays/popups.
                       Default: False.
+        adjust_viewport_to_content (bool): If True, adjust viewport according to the page content dimensions.
+                                           Default: False.
+
+        # Media Handling Parameters
+        screenshot (bool): Whether to take a screenshot after crawling.
+                           Default: False.
         screenshot_wait_for (float or None): Additional wait time before taking a screenshot.
                                              Default: None.
         screenshot_height_threshold (int): Threshold for page height to decide screenshot strategy.
                                            Default: SCREENSHOT_HEIGHT_TRESHOLD (from config, e.g. 20000).
-        mean_delay (float): Mean base delay between requests when calling arun_many.
-                            Default: 0.1.
-        max_range (float): Max random additional delay range for requests in arun_many.
-                           Default: 0.3.
-        # session_id and semaphore_count might be set at runtime, not needed as defaults here.
+        pdf (bool): Whether to generate a PDF of the page.
+                    Default: False.
+        image_description_min_word_threshold (int): Minimum words for image description extraction.
+                                                    Default: IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD (e.g., 50).
+        image_score_threshold (int): Minimum score threshold for processing an image.
+                                     Default: IMAGE_SCORE_THRESHOLD (e.g., 3).
+        exclude_external_images (bool): If True, exclude all external images from processing.
+                                         Default: False.
+
+        # Link and Domain Handling Parameters
+        exclude_social_media_domains (list of str): List of domains to exclude for social media links.
+                                                    Default: SOCIAL_MEDIA_DOMAINS (from config).
+        exclude_external_links (bool): If True, exclude all external links from the results.
+                                       Default: False.
+        exclude_social_media_links (bool): If True, exclude links pointing to social media domains.
+                                           Default: False.
+        exclude_domains (list of str): List of specific domains to exclude from results.
+                                       Default: [].
+
+        # Debugging and Logging Parameters
+        verbose (bool): Enable verbose logging.
+                        Default: True.
+        log_console (bool): If True, log console messages from the page.
+                            Default: False.
     """
 
     def __init__(
         self,
-        word_count_threshold: int =  MIN_WORD_THRESHOLD ,
-        extraction_strategy : ExtractionStrategy=None,  # Will default to NoExtractionStrategy if None
-        chunking_strategy : ChunkingStrategy= None,    # Will default to RegexChunking if None
-        markdown_generator : MarkdownGenerationStrategy = None,
+        # Content Processing Parameters
+        word_count_threshold: int = MIN_WORD_THRESHOLD,
+        extraction_strategy: ExtractionStrategy = None,
+        chunking_strategy: ChunkingStrategy = None,
+        markdown_generator: MarkdownGenerationStrategy = None,
         content_filter=None,
+        only_text: bool = False,
+        css_selector: str = None,
+        excluded_tags: list = None,
+        keep_data_attributes: bool = False,
+        remove_forms: bool = False,
+        prettiify: bool = False,
+
+        # Caching Parameters
         cache_mode=None,
         session_id: str = None,
         bypass_cache: bool = False,
         disable_cache: bool = False,
         no_cache_read: bool = False,
         no_cache_write: bool = False,
-        css_selector: str = None,
-        screenshot: bool = False,
-        pdf: bool = False,
-        verbose: bool = True,
-        only_text: bool = False,
-        image_description_min_word_threshold: int = IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD,
-        prettiify: bool = False,
-        js_code=None,
-        wait_for: str = None,
-        js_only: bool = False,
+
+        # Page Navigation and Timing Parameters
         wait_until: str = "domcontentloaded",
         page_timeout: int = PAGE_TIMEOUT,
-        ignore_body_visibility: bool = True,
+        wait_for: str = None,
         wait_for_images: bool = True,
-        adjust_viewport_to_content: bool = False,
+        delay_before_return_html: float = 0.1,
+        mean_delay: float = 0.1,
+        max_range: float = 0.3,
+        semaphore_count: int = 5,
+
+        # Page Interaction Parameters
+        js_code=None,
+        js_only: bool = False,
+        ignore_body_visibility: bool = True,
         scan_full_page: bool = False,
         scroll_delay: float = 0.2,
         process_iframes: bool = False,
         remove_overlay_elements: bool = False,
-        delay_before_return_html: float = 0.1,
-        log_console: bool = False,
         simulate_user: bool = False,
         override_navigator: bool = False,
         magic: bool = False,
+        adjust_viewport_to_content: bool = False,
+
+        # Media Handling Parameters
+        screenshot: bool = False,
         screenshot_wait_for: float = None,
         screenshot_height_threshold: int = SCREENSHOT_HEIGHT_TRESHOLD,
-        mean_delay: float = 0.1,
-        max_range: float = 0.3,
-        semaphore_count: int = 5,
+        pdf: bool = False,
+        image_description_min_word_threshold: int = IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD,
+        image_score_threshold: int = IMAGE_SCORE_THRESHOLD,
+        exclude_external_images: bool = False,
+
+        # Link and Domain Handling Parameters
+        exclude_social_media_domains: list = None,
+        exclude_external_links: bool = False,
+        exclude_social_media_links: bool = False,
+        exclude_domains: list = None,
+
+        # Debugging and Logging Parameters
+        verbose: bool = True,
+        log_console: bool = False,
     ):
+        # Content Processing Parameters
         self.word_count_threshold = word_count_threshold
         self.extraction_strategy = extraction_strategy
         self.chunking_strategy = chunking_strategy
         self.markdown_generator = markdown_generator
         self.content_filter = content_filter
+        self.only_text = only_text
+        self.css_selector = css_selector
+        self.excluded_tags = excluded_tags or []
+        self.keep_data_attributes = keep_data_attributes
+        self.remove_forms = remove_forms
+        self.prettiify = prettiify
+
+        # Caching Parameters
         self.cache_mode = cache_mode
         self.session_id = session_id
         self.bypass_cache = bypass_cache
         self.disable_cache = disable_cache
         self.no_cache_read = no_cache_read
         self.no_cache_write = no_cache_write
-        self.css_selector = css_selector
-        self.screenshot = screenshot
-        self.pdf = pdf
-        self.verbose = verbose
-        self.only_text = only_text
-        self.image_description_min_word_threshold = image_description_min_word_threshold
-        self.prettiify = prettiify
-        self.js_code = js_code
-        self.wait_for = wait_for
-        self.js_only = js_only
+
+        # Page Navigation and Timing Parameters
         self.wait_until = wait_until
         self.page_timeout = page_timeout
-        self.ignore_body_visibility = ignore_body_visibility
+        self.wait_for = wait_for
         self.wait_for_images = wait_for_images
-        self.adjust_viewport_to_content = adjust_viewport_to_content
-        self.scan_full_page = scan_full_page
-        self.scroll_delay = scroll_delay
-        self.process_iframes = process_iframes
-        self.remove_overlay_elements = remove_overlay_elements
         self.delay_before_return_html = delay_before_return_html
-        self.log_console = log_console
-        self.simulate_user = simulate_user
-        self.override_navigator = override_navigator
-        self.magic = magic
-        self.screenshot_wait_for = screenshot_wait_for
-        self.screenshot_height_threshold = screenshot_height_threshold
         self.mean_delay = mean_delay
         self.max_range = max_range
         self.semaphore_count = semaphore_count
 
+        # Page Interaction Parameters
+        self.js_code = js_code
+        self.js_only = js_only
+        self.ignore_body_visibility = ignore_body_visibility
+        self.scan_full_page = scan_full_page
+        self.scroll_delay = scroll_delay
+        self.process_iframes = process_iframes
+        self.remove_overlay_elements = remove_overlay_elements
+        self.simulate_user = simulate_user
+        self.override_navigator = override_navigator
+        self.magic = magic
+        self.adjust_viewport_to_content = adjust_viewport_to_content
+
+        # Media Handling Parameters
+        self.screenshot = screenshot
+        self.screenshot_wait_for = screenshot_wait_for
+        self.screenshot_height_threshold = screenshot_height_threshold
+        self.pdf = pdf
+        self.image_description_min_word_threshold = image_description_min_word_threshold
+        self.image_score_threshold = image_score_threshold
+        self.exclude_external_images = exclude_external_images
+
+        # Link and Domain Handling Parameters
+        self.exclude_social_media_domains = exclude_social_media_domains or SOCIAL_MEDIA_DOMAINS
+        self.exclude_external_links = exclude_external_links
+        self.exclude_social_media_links = exclude_social_media_links
+        self.exclude_domains = exclude_domains or []
+
+        # Debugging and Logging Parameters
+        self.verbose = verbose
+        self.log_console = log_console
+
         # Validate type of extraction strategy and chunking strategy if they are provided
-        if self.extraction_strategy is not None and not isinstance(self.extraction_strategy, ExtractionStrategy):
+        if self.extraction_strategy is not None and not isinstance(
+            self.extraction_strategy, ExtractionStrategy
+        ):
             raise ValueError("extraction_strategy must be an instance of ExtractionStrategy")
-        if self.chunking_strategy is not None and not isinstance(self.chunking_strategy, ChunkingStrategy):
+        if self.chunking_strategy is not None and not isinstance(
+            self.chunking_strategy, ChunkingStrategy
+        ):
             raise ValueError("chunking_strategy must be an instance of ChunkingStrategy")
 
         # Set default chunking strategy if None
         if self.chunking_strategy is None:
             from .chunking_strategy import RegexChunking
             self.chunking_strategy = RegexChunking()
-        
 
     @staticmethod
     def from_kwargs(kwargs: dict) -> "CrawlerRunConfig":
         return CrawlerRunConfig(
+            # Content Processing Parameters
             word_count_threshold=kwargs.get("word_count_threshold", 200),
             extraction_strategy=kwargs.get("extraction_strategy"),
             chunking_strategy=kwargs.get("chunking_strategy"),
             markdown_generator=kwargs.get("markdown_generator"),
             content_filter=kwargs.get("content_filter"),
+            only_text=kwargs.get("only_text", False),
+            css_selector=kwargs.get("css_selector"),
+            excluded_tags=kwargs.get("excluded_tags", []),
+            keep_data_attributes=kwargs.get("keep_data_attributes", False),
+            remove_forms=kwargs.get("remove_forms", False),
+            prettiify=kwargs.get("prettiify", False),
+
+            # Caching Parameters
             cache_mode=kwargs.get("cache_mode"),
             session_id=kwargs.get("session_id"),
             bypass_cache=kwargs.get("bypass_cache", False),
             disable_cache=kwargs.get("disable_cache", False),
             no_cache_read=kwargs.get("no_cache_read", False),
             no_cache_write=kwargs.get("no_cache_write", False),
-            css_selector=kwargs.get("css_selector"),
-            screenshot=kwargs.get("screenshot", False),
-            pdf=kwargs.get("pdf", False),
-            verbose=kwargs.get("verbose", True),
-            only_text=kwargs.get("only_text", False),
-            image_description_min_word_threshold=kwargs.get("image_description_min_word_threshold",  IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD),
-            prettiify=kwargs.get("prettiify", False),
-            js_code=kwargs.get("js_code"), # If not provided here, will default inside constructor
-            wait_for=kwargs.get("wait_for"),
-            js_only=kwargs.get("js_only", False),
+
+            # Page Navigation and Timing Parameters
             wait_until=kwargs.get("wait_until", "domcontentloaded"),
             page_timeout=kwargs.get("page_timeout", 60000),
+            wait_for=kwargs.get("wait_for"),
+            wait_for_images=kwargs.get("wait_for_images", True),
+            delay_before_return_html=kwargs.get("delay_before_return_html", 0.1),
+            mean_delay=kwargs.get("mean_delay", 0.1),
+            max_range=kwargs.get("max_range", 0.3),
+            semaphore_count=kwargs.get("semaphore_count", 5),
+
+            # Page Interaction Parameters
+            js_code=kwargs.get("js_code"),
+            js_only=kwargs.get("js_only", False),
             ignore_body_visibility=kwargs.get("ignore_body_visibility", True),
-            adjust_viewport_to_content=kwargs.get("adjust_viewport_to_content", False),
             scan_full_page=kwargs.get("scan_full_page", False),
             scroll_delay=kwargs.get("scroll_delay", 0.2),
             process_iframes=kwargs.get("process_iframes", False),
             remove_overlay_elements=kwargs.get("remove_overlay_elements", False),
-            delay_before_return_html=kwargs.get("delay_before_return_html", 0.1),
-            log_console=kwargs.get("log_console", False),
             simulate_user=kwargs.get("simulate_user", False),
             override_navigator=kwargs.get("override_navigator", False),
             magic=kwargs.get("magic", False),
+            adjust_viewport_to_content=kwargs.get("adjust_viewport_to_content", False),
+
+            # Media Handling Parameters
+            screenshot=kwargs.get("screenshot", False),
             screenshot_wait_for=kwargs.get("screenshot_wait_for"),
-            screenshot_height_threshold=kwargs.get("screenshot_height_threshold", 20000),
-            mean_delay=kwargs.get("mean_delay", 0.1),
-            max_range=kwargs.get("max_range", 0.3),
-            semaphore_count=kwargs.get("semaphore_count", 5)
+            screenshot_height_threshold=kwargs.get("screenshot_height_threshold", SCREENSHOT_HEIGHT_TRESHOLD),
+            pdf=kwargs.get("pdf", False),
+            image_description_min_word_threshold=kwargs.get("image_description_min_word_threshold", IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD),
+            image_score_threshold=kwargs.get("image_score_threshold", IMAGE_SCORE_THRESHOLD),
+            exclude_external_images=kwargs.get("exclude_external_images", False),
+
+            # Link and Domain Handling Parameters
+            exclude_social_media_domains=kwargs.get("exclude_social_media_domains", SOCIAL_MEDIA_DOMAINS),
+            exclude_external_links=kwargs.get("exclude_external_links", False),
+            exclude_social_media_links=kwargs.get("exclude_social_media_links", False),
+            exclude_domains=kwargs.get("exclude_domains", []),
+
+            # Debugging and Logging Parameters
+            verbose=kwargs.get("verbose", True),
+            log_console=kwargs.get("log_console", False),
         )
+        
+        
+        
+        
+    # @staticmethod
+    # def from_kwargs(kwargs: dict) -> "CrawlerRunConfig":
+    #     return CrawlerRunConfig(
+    #         word_count_threshold=kwargs.get("word_count_threshold", 200),
+    #         extraction_strategy=kwargs.get("extraction_strategy"),
+    #         chunking_strategy=kwargs.get("chunking_strategy"),
+    #         markdown_generator=kwargs.get("markdown_generator"),
+    #         content_filter=kwargs.get("content_filter"),
+    #         cache_mode=kwargs.get("cache_mode"),
+    #         session_id=kwargs.get("session_id"),
+    #         bypass_cache=kwargs.get("bypass_cache", False),
+    #         disable_cache=kwargs.get("disable_cache", False),
+    #         no_cache_read=kwargs.get("no_cache_read", False),
+    #         no_cache_write=kwargs.get("no_cache_write", False),
+    #         css_selector=kwargs.get("css_selector"),
+    #         screenshot=kwargs.get("screenshot", False),
+    #         pdf=kwargs.get("pdf", False),
+    #         verbose=kwargs.get("verbose", True),
+    #         only_text=kwargs.get("only_text", False),
+    #         image_description_min_word_threshold=kwargs.get(
+    #             "image_description_min_word_threshold",
+    #             IMAGE_DESCRIPTION_MIN_WORD_THRESHOLD,
+    #         ),
+    #         prettiify=kwargs.get("prettiify", False),
+    #         js_code=kwargs.get(
+    #             "js_code"
+    #         ),  # If not provided here, will default inside constructor
+    #         wait_for=kwargs.get("wait_for"),
+    #         js_only=kwargs.get("js_only", False),
+    #         wait_until=kwargs.get("wait_until", "domcontentloaded"),
+    #         page_timeout=kwargs.get("page_timeout", 60000),
+    #         ignore_body_visibility=kwargs.get("ignore_body_visibility", True),
+    #         adjust_viewport_to_content=kwargs.get("adjust_viewport_to_content", False),
+    #         scan_full_page=kwargs.get("scan_full_page", False),
+    #         scroll_delay=kwargs.get("scroll_delay", 0.2),
+    #         process_iframes=kwargs.get("process_iframes", False),
+    #         remove_overlay_elements=kwargs.get("remove_overlay_elements", False),
+    #         delay_before_return_html=kwargs.get("delay_before_return_html", 0.1),
+    #         log_console=kwargs.get("log_console", False),
+    #         simulate_user=kwargs.get("simulate_user", False),
+    #         override_navigator=kwargs.get("override_navigator", False),
+    #         magic=kwargs.get("magic", False),
+    #         screenshot_wait_for=kwargs.get("screenshot_wait_for"),
+    #         screenshot_height_threshold=kwargs.get(
+    #             "screenshot_height_threshold", 20000
+    #         ),
+    #         mean_delay=kwargs.get("mean_delay", 0.1),
+    #         max_range=kwargs.get("max_range", 0.3),
+    #         semaphore_count=kwargs.get("semaphore_count", 5),
+    #         image_score_threshold=kwargs.get(
+    #             "image_score_threshold", IMAGE_SCORE_THRESHOLD
+    #         ),
+    #         exclude_social_media_domains=kwargs.get(
+    #             "exclude_social_media_domains", SOCIAL_MEDIA_DOMAINS
+    #         ),
+    #         exclude_external_links=kwargs.get("exclude_external_links", False),
+    #         exclude_social_media_links=kwargs.get("exclude_social_media_links", False),
+    #         exclude_domains=kwargs.get("exclude_domains", []),
+    #         exclude_external_images=kwargs.get("exclude_external_images", False),
+    #         remove_forms=kwargs.get("remove_forms", False),
+    #         keep_data_attributes=kwargs.get("keep_data_attributes", False),
+    #         excluded_tags=kwargs.get("excluded_tags", []),
+    #     )
+        
diff --git a/crawl4ai/async_crawler_strategy.py b/crawl4ai/async_crawler_strategy.py
index 3f040e13..4f9a1f56 100644
--- a/crawl4ai/async_crawler_strategy.py
+++ b/crawl4ai/async_crawler_strategy.py
@@ -21,6 +21,7 @@ from .utils import get_error_context
 from .user_agent_generator import UserAgentGenerator
 from .config import SCREENSHOT_HEIGHT_TRESHOLD, DOWNLOAD_PAGE_TIMEOUT
 from .async_configs import BrowserConfig, CrawlerRunConfig
+from .async_logger import AsyncLogger
 from playwright_stealth import StealthConfig, stealth_async
 
 
@@ -462,7 +463,7 @@ class AsyncCrawlerStrategy(ABC):
         pass
 
 class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
-    def __init__(self, browser_config: BrowserConfig = None, logger = None, **kwargs):
+    def __init__(self, browser_config: BrowserConfig = None, logger : AsyncLogger = None, **kwargs):
         """
         Initialize the AsyncPlaywrightCrawlerStrategy with a browser configuration.
         
@@ -758,16 +759,22 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
         
         # Set up console logging if requested
         if config.log_console:
-            page.on("console", lambda msg: self.logger.debug(
-                message="Console: {msg}",
-                tag="CONSOLE",
-                params={"msg": msg.text}
-            ))
-            page.on("pageerror", lambda exc: self.logger.error(
-                message="Page error: {exc}",
-                tag="ERROR",
-                params={"exc": exc}
-            ))
+            def log_consol(msg, console_log_type="debug"):  # Corrected the parameter syntax
+                if console_log_type == "error":
+                    self.logger.error(
+                        message=f"Console error: {msg}",  # Use f-string for variable interpolation
+                        tag="CONSOLE",
+                        params={"msg": msg.text}
+                    )
+                elif console_log_type == "debug":
+                    self.logger.debug(
+                        message=f"Console: {msg}",  # Use f-string for variable interpolation
+                        tag="CONSOLE",
+                        params={"msg": msg.text}
+                    )
+
+            page.on("console", log_consol)
+            page.on("pageerror", lambda e: log_consol(e, "error"))
         
         try:
             # Set up download handling
@@ -956,12 +963,11 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
 
             # Define delayed content getter
             async def get_delayed_content(delay: float = 5.0) -> str:
-                if self.config.verbose:
-                    self.logger.info(
-                        message="Waiting for {delay} seconds before retrieving content for {url}",
-                        tag="INFO",
-                        params={"delay": delay, "url": url}
-                    )                    
+                self.logger.info(
+                    message="Waiting for {delay} seconds before retrieving content for {url}",
+                    tag="INFO",
+                    params={"delay": delay, "url": url}
+                )                    
                 await asyncio.sleep(delay)
                 return await page.content()
 
diff --git a/crawl4ai/async_logger.py b/crawl4ai/async_logger.py
index 220edd11..5d2d54b5 100644
--- a/crawl4ai/async_logger.py
+++ b/crawl4ai/async_logger.py
@@ -42,7 +42,7 @@ class AsyncLogger:
     def __init__(
         self,
         log_file: Optional[str] = None,
-        log_level: LogLevel = LogLevel.INFO,
+        log_level: LogLevel = LogLevel.DEBUG,
         tag_width: int = 10,
         icons: Optional[Dict[str, str]] = None,
         colors: Optional[Dict[LogLevel, str]] = None,
diff --git a/crawl4ai/config.py b/crawl4ai/config.py
index 7c8a9314..c2be7638 100644
--- a/crawl4ai/config.py
+++ b/crawl4ai/config.py
@@ -13,6 +13,8 @@ PROVIDER_MODELS = {
     "groq/llama3-8b-8192": os.getenv("GROQ_API_KEY"),
     "openai/gpt-4o-mini": os.getenv("OPENAI_API_KEY"),
     "openai/gpt-4o": os.getenv("OPENAI_API_KEY"),
+    "openai/o1-mini": os.getenv("OPENAI_API_KEY"),
+    "openai/o1-preview": os.getenv("OPENAI_API_KEY"),
     "anthropic/claude-3-haiku-20240307": os.getenv("ANTHROPIC_API_KEY"),
     "anthropic/claude-3-opus-20240229": os.getenv("ANTHROPIC_API_KEY"),
     "anthropic/claude-3-sonnet-20240229": os.getenv("ANTHROPIC_API_KEY"),
diff --git a/docs/md_v2/api/crawl-config.md b/docs/md_v2/api/crawl-config.md
new file mode 100644
index 00000000..928ae1e2
--- /dev/null
+++ b/docs/md_v2/api/crawl-config.md
@@ -0,0 +1,85 @@
+# CrawlerRunConfig Parameters Documentation
+
+## Content Processing Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `word_count_threshold` | int | 200 | Minimum word count threshold before processing content |
+| `extraction_strategy` | ExtractionStrategy | None | Strategy to extract structured data from crawled pages. When None, uses NoExtractionStrategy |
+| `chunking_strategy` | ChunkingStrategy | RegexChunking() | Strategy to chunk content before extraction |
+| `markdown_generator` | MarkdownGenerationStrategy | None | Strategy for generating markdown from extracted content |
+| `content_filter` | RelevantContentFilter | None | Optional filter to prune irrelevant content |
+| `only_text` | bool | False | If True, attempt to extract text-only content where applicable |
+| `css_selector` | str | None | CSS selector to extract a specific portion of the page |
+| `excluded_tags` | list[str] | [] | List of HTML tags to exclude from processing |
+| `keep_data_attributes` | bool | False | If True, retain `data-*` attributes while removing unwanted attributes |
+| `remove_forms` | bool | False | If True, remove all `<form>` elements from the HTML |
+| `prettiify` | bool | False | If True, apply `fast_format_html` to produce prettified HTML output |
+
+## Caching Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `cache_mode` | CacheMode | None | Defines how caching is handled. Defaults to CacheMode.ENABLED internally |
+| `session_id` | str | None | Optional session ID to persist browser context and page instance |
+| `bypass_cache` | bool | False | Legacy parameter, if True acts like CacheMode.BYPASS |
+| `disable_cache` | bool | False | Legacy parameter, if True acts like CacheMode.DISABLED |
+| `no_cache_read` | bool | False | Legacy parameter, if True acts like CacheMode.WRITE_ONLY |
+| `no_cache_write` | bool | False | Legacy parameter, if True acts like CacheMode.READ_ONLY |
+
+## Page Navigation and Timing Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `wait_until` | str | "domcontentloaded" | The condition to wait for when navigating |
+| `page_timeout` | int | 60000 | Timeout in milliseconds for page operations like navigation |
+| `wait_for` | str | None | CSS selector or JS condition to wait for before extracting content |
+| `wait_for_images` | bool | True | If True, wait for images to load before extracting content |
+| `delay_before_return_html` | float | 0.1 | Delay in seconds before retrieving final HTML |
+| `mean_delay` | float | 0.1 | Mean base delay between requests when calling arun_many |
+| `max_range` | float | 0.3 | Max random additional delay range for requests in arun_many |
+| `semaphore_count` | int | 5 | Number of concurrent operations allowed |
+
+## Page Interaction Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `js_code` | str or list[str] | None | JavaScript code/snippets to run on the page |
+| `js_only` | bool | False | If True, indicates subsequent calls are JS-driven updates |
+| `ignore_body_visibility` | bool | True | If True, ignore whether the body is visible before proceeding |
+| `scan_full_page` | bool | False | If True, scroll through the entire page to load all content |
+| `scroll_delay` | float | 0.2 | Delay in seconds between scroll steps if scan_full_page is True |
+| `process_iframes` | bool | False | If True, attempts to process and inline iframe content |
+| `remove_overlay_elements` | bool | False | If True, remove overlays/popups before extracting HTML |
+| `simulate_user` | bool | False | If True, simulate user interactions for anti-bot measures |
+| `override_navigator` | bool | False | If True, overrides navigator properties for more human-like behavior |
+| `magic` | bool | False | If True, attempts automatic handling of overlays/popups |
+| `adjust_viewport_to_content` | bool | False | If True, adjust viewport according to page content dimensions |
+
+## Media Handling Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `screenshot` | bool | False | Whether to take a screenshot after crawling |
+| `screenshot_wait_for` | float | None | Additional wait time before taking a screenshot |
+| `screenshot_height_threshold` | int | 20000 | Threshold for page height to decide screenshot strategy |
+| `pdf` | bool | False | Whether to generate a PDF of the page |
+| `image_description_min_word_threshold` | int | 50 | Minimum words for image description extraction |
+| `image_score_threshold` | int | 3 | Minimum score threshold for processing an image |
+| `exclude_external_images` | bool | False | If True, exclude all external images from processing |
+
+## Link and Domain Handling Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `exclude_social_media_domains` | list[str] | SOCIAL_MEDIA_DOMAINS | List of domains to exclude for social media links |
+| `exclude_external_links` | bool | False | If True, exclude all external links from the results |
+| `exclude_social_media_links` | bool | False | If True, exclude links pointing to social media domains |
+| `exclude_domains` | list[str] | [] | List of specific domains to exclude from results |
+
+## Debugging and Logging Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `verbose` | bool | True | Enable verbose logging |
+| `log_console` | bool | False | If True, log console messages from the page |
\ No newline at end of file
diff --git a/docs/md_v2/blog/articles/dockerize_hooks.md b/docs/md_v2/blog/articles/dockerize_hooks.md
new file mode 100644
index 00000000..965388ee
--- /dev/null
+++ b/docs/md_v2/blog/articles/dockerize_hooks.md
@@ -0,0 +1,46 @@
+## Introducing Event Streams and Interactive Hooks in Crawl4AI
+
+![event-driven-crawl](https://res.cloudinary.com/kidocode/image/upload/t_400x400/v1734344008/15bb8bbb-83ac-43ac-962d-3feb3e0c3bbf_2_tjmr4n.webp)
+
+In the near future, I’m planning to enhance Crawl4AI’s capabilities by introducing an event stream mechanism that will give clients deeper, real-time insights into the crawling process. Today, hooks are a powerful feature at the code level—they let developers define custom logic at key points in the crawl. However, when using Crawl4AI as a service (e.g., through a Dockerized API), there isn’t an easy way to interact with these hooks at runtime.
+
+**What’s Changing?**
+
+I’m working on a solution that will allow the crawler to emit a continuous stream of events, updating clients on the current crawling stage, encountered pages, and any decision points. This event stream could be exposed over a standardized protocol like Server-Sent Events (SSE) or WebSockets, enabling clients to “subscribe” and listen as the crawler works.
+
+**Interactivity Through Process IDs**
+
+A key part of this new design is the concept of a unique process ID for each crawl session. Imagine you’re listening to an event stream that informs you:
+- The crawler just hit a certain page  
+- It triggered a hook and is now pausing for instructions  
+
+With the event stream in place, you can send a follow-up request back to the server—referencing the unique process ID—to provide extra data, instructions, or parameters. This might include selecting which links to follow next, adjusting extraction strategies, or providing authentication tokens for a protected API. Once the crawler receives these instructions, it resumes execution with the updated context.
+
+```mermaid
+sequenceDiagram
+    participant Client
+    participant Server
+    participant Crawler
+
+    Client->>Server: Start crawl request
+    Server->>Crawler: Initiate crawl with Process ID
+    Crawler-->>Server: Event: Page hit
+    Server-->>Client: Stream: Page hit event
+    Client->>Server: Instruction for Process ID
+    Server->>Crawler: Update crawl with new instructions
+    Crawler-->>Server: Event: Crawl completed
+    Server-->>Client: Stream: Crawl completed
+```
+
+**Benefits for Developers and Users**
+
+1. **Fine-Grained Control**: Instead of predefining all logic upfront, you can dynamically guide the crawler in response to actual data and conditions encountered mid-crawl.
+2. **Real-Time Insights**: Monitor progress, errors, or network bottlenecks as they happen, without waiting for the entire crawl to finish.
+3. **Enhanced Collaboration**: Different team members or automated systems can watch the same crawl events and provide input, making the crawling process more adaptive and intelligent.
+
+**Next Steps**
+
+I’m currently exploring the best APIs, technologies, and patterns to make this vision a reality. My goal is to deliver a seamless developer experience—one that integrates with existing Crawl4AI workflows while offering new flexibility and power.
+
+Stay tuned for more updates as I continue building this feature out. In the meantime, I’d love to hear any feedback or suggestions you might have to help shape this interactive, event-driven future of web crawling with Crawl4AI.
+