🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
Python aiai-scrapingautomationcrawlercrawlingcrawling-pythondatadata-extractionmcpmcp-serverplaywrightpythonscrapingselectorsstealthweb-scraperweb-scrapingweb-scraping-pythonwebscrapingxpath
perf: force ad blocking on the MCP server and when the AI mode is activated on CLI
Karim shoairad6fd5284553
diff --git a/scrapling/cli.py b/scrapling/cli.pyindex 3327dcb..47056d9 100644--- a/scrapling/cli.py+++ b/scrapling/cli.py@@ -53,6 +53,8 @@ def __Request_and_Save(if not output_path.is_absolute():output_path = Path.cwd() / output_file+ if ai_targeted:+ kwargs.setdefault("block_ads", True)response = fetcher_func(url, **kwargs)Convertor.write_content_to_file(response, str(output_path), css_selector, main_content_only=ai_targeted)log.info(f"Content successfully saved to '{output_path}'")diff --git a/scrapling/core/ai.py b/scrapling/core/ai.pyindex 9b33821..060cb20 100644--- a/scrapling/core/ai.py+++ b/scrapling/core/ai.py@@ -183,6 +183,7 @@ class ScraplingMCPServer:cookies=cookies,cdp_url=cdp_url,headless=headless,+ block_ads=True,max_pages=max_pages,useragent=useragent,timezone_id=timezone_id,@@ -569,6 +570,7 @@ class ScraplingMCPServer:cookies=cookies,cdp_url=cdp_url,headless=headless,+ block_ads=True,max_pages=len(urls),useragent=useragent,timezone_id=timezone_id,@@ -777,6 +779,7 @@ class ScraplingMCPServer:timeout=timeout,cookies=cookies,headless=headless,+ block_ads=True,useragent=useragent,timezone_id=timezone_id,real_chrome=real_chrome,