#1559 :Add tests for sitemap parsing and URL normalization in AsyncUrlSeeder

feat(ManagedBrowser): add viewport size configuration for browser launch

crawl4ai/async_crawler_strategy.py

@@ -1383,9 +1383,10 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
         try:
             await self.adapter.evaluate(page,
                 f"""
-                (() => {{
+                (async () => {{
                     try {{
-                        {remove_overlays_js}
+                        const removeOverlays = {remove_overlays_js};
+                        await removeOverlays();
                         return {{ success: true }};
                     }} catch (error) {{
                         return {{

crawl4ai/async_url_seeder.py

@@ -845,6 +845,15 @@ class AsyncUrlSeeder:
             return
 
         data = gzip.decompress(r.content) if url.endswith(".gz") else r.content
+        base_url = str(r.url)
+
+        def _normalize_loc(raw: Optional[str]) -> Optional[str]:
+            if not raw:
+                return None
+            normalized = urljoin(base_url, raw.strip())
+            if not normalized:
+                return None
+            return normalized
 
         # Detect if this is a sitemap index by checking for <sitemapindex> or presence of <sitemap> elements
         is_sitemap_index = False
@@ -857,25 +866,42 @@ class AsyncUrlSeeder:
                 # Use XML parser for sitemaps, not HTML parser
                 parser = etree.XMLParser(recover=True)
                 root = etree.fromstring(data, parser=parser)
+                # Namespace-agnostic lookups using local-name() so we honor custom or missing namespaces
+                sitemap_loc_nodes = root.xpath("//*[local-name()='sitemap']/*[local-name()='loc']")
+                url_loc_nodes = root.xpath("//*[local-name()='url']/*[local-name()='loc']")
 
-                # Define namespace for sitemap
-                ns = {'s': 'http://www.sitemaps.org/schemas/sitemap/0.9'}
+                self._log(
+                    "debug",
+                    "Parsed sitemap {url}: {sitemap_count} sitemap entries, {url_count} url entries discovered",
+                    params={
+                        "url": url,
+                        "sitemap_count": len(sitemap_loc_nodes),
+                        "url_count": len(url_loc_nodes),
+                    },
+                    tag="URL_SEED",
+                )
 
                 # Check for sitemap index entries
-                sitemap_locs = root.xpath('//s:sitemap/s:loc', namespaces=ns)
-                if sitemap_locs:
+                if sitemap_loc_nodes:
                     is_sitemap_index = True
-                    for sitemap_elem in sitemap_locs:
-                        loc = sitemap_elem.text.strip() if sitemap_elem.text else ""
+                    for sitemap_elem in sitemap_loc_nodes:
+                        loc = _normalize_loc(sitemap_elem.text)
                         if loc:
                             sub_sitemaps.append(loc)
 
                 # If not a sitemap index, get regular URLs
                 if not is_sitemap_index:
-                    for loc_elem in root.xpath('//s:url/s:loc', namespaces=ns):
-                        loc = loc_elem.text.strip() if loc_elem.text else ""
+                    for loc_elem in url_loc_nodes:
+                        loc = _normalize_loc(loc_elem.text)
                         if loc:
                             regular_urls.append(loc)
+                    if not regular_urls:
+                        self._log(
+                            "warning",
+                            "No <loc> entries found inside <url> tags for sitemap {url}. The sitemap might be empty or use an unexpected structure.",
+                            params={"url": url},
+                            tag="URL_SEED",
+                        )
             except Exception as e:
                 self._log("error", "LXML parsing error for sitemap {url}: {error}",
                           params={"url": url, "error": str(e)}, tag="URL_SEED")
@@ -892,19 +918,39 @@ class AsyncUrlSeeder:
 
                 # Check for sitemap index entries
                 sitemaps = root.findall('.//sitemap')
+                url_entries = root.findall('.//url')
+                self._log(
+                    "debug",
+                    "ElementTree parsed sitemap {url}: {sitemap_count} sitemap entries, {url_count} url entries discovered",
+                    params={
+                        "url": url,
+                        "sitemap_count": len(sitemaps),
+                        "url_count": len(url_entries),
+                    },
+                    tag="URL_SEED",
+                )
                 if sitemaps:
                     is_sitemap_index = True
                     for sitemap in sitemaps:
                         loc_elem = sitemap.find('loc')
-                        if loc_elem is not None and loc_elem.text:
-                            sub_sitemaps.append(loc_elem.text.strip())
+                        loc = _normalize_loc(loc_elem.text if loc_elem is not None else None)
+                        if loc:
+                            sub_sitemaps.append(loc)
 
                 # If not a sitemap index, get regular URLs
                 if not is_sitemap_index:
-                    for url_elem in root.findall('.//url'):
+                    for url_elem in url_entries:
                         loc_elem = url_elem.find('loc')
-                        if loc_elem is not None and loc_elem.text:
-                            regular_urls.append(loc_elem.text.strip())
+                        loc = _normalize_loc(loc_elem.text if loc_elem is not None else None)
+                        if loc:
+                            regular_urls.append(loc)
+                    if not regular_urls:
+                        self._log(
+                            "warning",
+                            "No <loc> entries found inside <url> tags for sitemap {url}. The sitemap might be empty or use an unexpected structure.",
+                            params={"url": url},
+                            tag="URL_SEED",
+                        )
             except Exception as e:
                 self._log("error", "ElementTree parsing error for sitemap {url}: {error}",
                           params={"url": url, "error": str(e)}, tag="URL_SEED")

crawl4ai/async_webcrawler.py

@@ -617,7 +617,17 @@ class AsyncWebCrawler:
                 else config.chunking_strategy
             )
             sections = chunking.chunk(content)
-            extracted_content = config.extraction_strategy.run(url, sections)
+            # extracted_content = config.extraction_strategy.run(url, sections)
+
+            # Use async version if available for better parallelism
+            if hasattr(config.extraction_strategy, 'arun'):
+                extracted_content = await config.extraction_strategy.arun(url, sections)
+            else:
+                # Fallback to sync version run in thread pool to avoid blocking
+                extracted_content = await asyncio.to_thread(
+                    config.extraction_strategy.run, url, sections
+                )
+
             extracted_content = json.dumps(
                 extracted_content, indent=4, default=str, ensure_ascii=False
             )

crawl4ai/browser_manager.py

@@ -1,23 +1,22 @@
 import asyncio
-import hashlib
+import time
+from typing import List, Optional
 import os
-import shlex
+import sys
 import shutil
+import tempfile
+import psutil  
 import signal
 import subprocess
-import sys
-import tempfile
-import time
-import warnings
-from typing import List, Optional
-
-import psutil
+import shlex
 from playwright.async_api import BrowserContext
-
-from .async_configs import BrowserConfig, CrawlerRunConfig
-from .config import DOWNLOAD_PAGE_TIMEOUT
+import hashlib
 from .js_snippet import load_js_script
+from .config import DOWNLOAD_PAGE_TIMEOUT
+from .async_configs import BrowserConfig, CrawlerRunConfig
 from .utils import get_chromium_path
+import warnings
+
 
 BROWSER_DISABLE_OPTIONS = [
     "--disable-background-networking",
@@ -66,7 +65,7 @@ class ManagedBrowser:
             _cleanup(): Terminates the browser process and removes the temporary directory.
             create_profile(): Static method to create a user profile by launching a browser for user interaction.
     """
-
+    
     @staticmethod
     def build_browser_flags(config: BrowserConfig) -> List[str]:
         """Common CLI flags for launching Chromium"""
@@ -93,25 +92,21 @@ class ManagedBrowser:
         if config.light_mode:
             flags.extend(BROWSER_DISABLE_OPTIONS)
         if config.text_mode:
-            flags.extend(
-                [
-                    "--blink-settings=imagesEnabled=false",
-                    "--disable-remote-fonts",
-                    "--disable-images",
-                    "--disable-javascript",
-                    "--disable-software-rasterizer",
-                    "--disable-dev-shm-usage",
-                ]
-            )
+            flags.extend([
+                "--blink-settings=imagesEnabled=false",
+                "--disable-remote-fonts",
+                "--disable-images",
+                "--disable-javascript",
+                "--disable-software-rasterizer",
+                "--disable-dev-shm-usage",
+            ])
         # proxy support
         if config.proxy:
             flags.append(f"--proxy-server={config.proxy}")
         elif config.proxy_config:
             creds = ""
             if config.proxy_config.username and config.proxy_config.password:
-                creds = (
-                    f"{config.proxy_config.username}:{config.proxy_config.password}@"
-                )
+                creds = f"{config.proxy_config.username}:{config.proxy_config.password}@"
             flags.append(f"--proxy-server={creds}{config.proxy_config.server}")
         # dedupe
         return list(dict.fromkeys(flags))
@@ -132,7 +127,7 @@ class ManagedBrowser:
         logger=None,
         host: str = "localhost",
         debugging_port: int = 9222,
-        cdp_url: Optional[str] = None,
+        cdp_url: Optional[str] = None, 
         browser_config: Optional[BrowserConfig] = None,
     ):
         """
@@ -168,7 +163,7 @@ class ManagedBrowser:
         Starts the browser process or returns CDP endpoint URL.
         If cdp_url is provided, returns it directly.
         If user_data_dir is not provided for local browser, creates a temporary directory.
-
+        
         Returns:
             str: CDP endpoint URL
         """
@@ -184,9 +179,10 @@ class ManagedBrowser:
         # Get browser path and args based on OS and browser type
         # browser_path = self._get_browser_path()
         args = await self._get_browser_args()
-
+        
         if self.browser_config.extra_args:
             args.extend(self.browser_config.extra_args)
+            
 
         # ── make sure no old Chromium instance is owning the same port/profile ──
         try:
@@ -204,9 +200,7 @@ class ManagedBrowser:
             else:  # macOS / Linux
                 # kill any process listening on the same debugging port
                 pids = (
-                    subprocess.check_output(
-                        shlex.split(f"lsof -t -i:{self.debugging_port}")
-                    )
+                    subprocess.check_output(shlex.split(f"lsof -t -i:{self.debugging_port}"))
                     .decode()
                     .strip()
                     .splitlines()
@@ -225,7 +219,8 @@ class ManagedBrowser:
                         os.remove(fp)
         except Exception as _e:
             # non-fatal — we'll try to start anyway, but log what happened
-            self.logger.warning(f"pre-launch cleanup failed: {_e}", tag="BROWSER")
+            self.logger.warning(f"pre-launch cleanup failed: {_e}", tag="BROWSER")            
+            
 
         # Start browser process
         try:
@@ -233,26 +228,26 @@ class ManagedBrowser:
             # On Unix, we'll use preexec_fn=os.setpgrp to start the process in a new process group
             if sys.platform == "win32":
                 self.browser_process = subprocess.Popen(
-                    args,
-                    stdout=subprocess.PIPE,
+                    args, 
+                    stdout=subprocess.PIPE, 
                     stderr=subprocess.PIPE,
-                    creationflags=subprocess.DETACHED_PROCESS
-                    | subprocess.CREATE_NEW_PROCESS_GROUP,
+                    creationflags=subprocess.DETACHED_PROCESS | subprocess.CREATE_NEW_PROCESS_GROUP
                 )
             else:
                 self.browser_process = subprocess.Popen(
-                    args,
-                    stdout=subprocess.PIPE,
+                    args, 
+                    stdout=subprocess.PIPE, 
                     stderr=subprocess.PIPE,
-                    preexec_fn=os.setpgrp,  # Start in a new process group
+                    preexec_fn=os.setpgrp  # Start in a new process group
                 )
-
+                
             # If verbose is True print args used to run the process
             if self.logger and self.browser_config.verbose:
                 self.logger.debug(
-                    f"Starting browser with args: {' '.join(args)}", tag="BROWSER"
-                )
-
+                    f"Starting browser with args: {' '.join(args)}",
+                    tag="BROWSER"
+                )    
+                
             # We'll monitor for a short time to make sure it starts properly, but won't keep monitoring
             await asyncio.sleep(0.5)  # Give browser time to start
             await self._initial_startup_check()
@@ -269,7 +264,7 @@ class ManagedBrowser:
         """
         if not self.browser_process:
             return
-
+            
         # Check that process started without immediate termination
         await asyncio.sleep(0.5)
         if self.browser_process.poll() is not None:
@@ -279,7 +274,7 @@ class ManagedBrowser:
                 stdout, stderr = self.browser_process.communicate(timeout=0.5)
             except subprocess.TimeoutExpired:
                 pass
-
+                
             self.logger.error(
                 message="Browser process terminated during startup | Code: {code} | STDOUT: {stdout} | STDERR: {stderr}",
                 tag="ERROR",
@@ -289,7 +284,7 @@ class ManagedBrowser:
                     "stderr": stderr.decode() if stderr else "",
                 },
             )
-
+    
     async def _monitor_browser_process(self):
         """
         Monitor the browser process for unexpected termination.
@@ -374,6 +369,9 @@ class ManagedBrowser:
             ]
             if self.headless:
                 flags.append("--headless=new")
+            # Add viewport flag if specified in config
+            if self.browser_config.viewport_height and self.browser_config.viewport_width:
+                flags.append(f"--window-size={self.browser_config.viewport_width},{self.browser_config.viewport_height}")
             # merge common launch flags
             flags.extend(self.build_browser_flags(self.browser_config))
         elif self.browser_type == "firefox":
@@ -412,14 +410,7 @@ class ManagedBrowser:
                         if sys.platform == "win32":
                             # On Windows we might need taskkill for detached processes
                             try:
-                                subprocess.run(
-                                    [
-                                        "taskkill",
-                                        "/F",
-                                        "/PID",
-                                        str(self.browser_process.pid),
-                                    ]
-                                )
+                                subprocess.run(["taskkill", "/F", "/PID", str(self.browser_process.pid)])
                             except Exception:
                                 self.browser_process.kill()
                         else:
@@ -429,7 +420,7 @@ class ManagedBrowser:
             except Exception as e:
                 self.logger.error(
                     message="Error terminating browser: {error}",
-                    tag="ERROR",
+                    tag="ERROR", 
                     params={"error": str(e)},
                 )
 
@@ -442,77 +433,75 @@ class ManagedBrowser:
                     tag="ERROR",
                     params={"error": str(e)},
                 )
-
+                
     # These methods have been moved to BrowserProfiler class
     @staticmethod
     async def create_profile(browser_config=None, profile_name=None, logger=None):
         """
         This method has been moved to the BrowserProfiler class.
-
+        
         Creates a browser profile by launching a browser for interactive user setup
         and waits until the user closes it. The profile is stored in a directory that
         can be used later with BrowserConfig.user_data_dir.
-
+        
         Please use BrowserProfiler.create_profile() instead.
-
+        
         Example:
             ```python
             from crawl4ai.browser_profiler import BrowserProfiler
-
+            
             profiler = BrowserProfiler()
             profile_path = await profiler.create_profile(profile_name="my-login-profile")
             ```
         """
         from .browser_profiler import BrowserProfiler
-
+        
         # Create a BrowserProfiler instance and delegate to it
         profiler = BrowserProfiler(logger=logger)
-        return await profiler.create_profile(
-            profile_name=profile_name, browser_config=browser_config
-        )
-
+        return await profiler.create_profile(profile_name=profile_name, browser_config=browser_config)
+    
     @staticmethod
     def list_profiles():
         """
         This method has been moved to the BrowserProfiler class.
-
+        
         Lists all available browser profiles in the Crawl4AI profiles directory.
-
+        
         Please use BrowserProfiler.list_profiles() instead.
-
+        
         Example:
             ```python
             from crawl4ai.browser_profiler import BrowserProfiler
-
+            
             profiler = BrowserProfiler()
             profiles = profiler.list_profiles()
             ```
         """
         from .browser_profiler import BrowserProfiler
-
+        
         # Create a BrowserProfiler instance and delegate to it
         profiler = BrowserProfiler()
         return profiler.list_profiles()
-
+        
     @staticmethod
     def delete_profile(profile_name_or_path):
         """
         This method has been moved to the BrowserProfiler class.
-
+        
         Delete a browser profile by name or path.
-
+        
         Please use BrowserProfiler.delete_profile() instead.
-
+        
         Example:
             ```python
             from crawl4ai.browser_profiler import BrowserProfiler
-
+            
             profiler = BrowserProfiler()
             success = profiler.delete_profile("my-profile")
             ```
         """
         from .browser_profiler import BrowserProfiler
-
+        
         # Create a BrowserProfiler instance and delegate to it
         profiler = BrowserProfiler()
         return profiler.delete_profile(profile_name_or_path)
@@ -565,10 +554,11 @@ async def clone_runtime_state(
                 "accuracy": crawlerRunConfig.geolocation.accuracy,
             }
         )
-
+        
     return dst
 
 
+
 class BrowserManager:
     """
     Manages the browser instance and context.
@@ -585,7 +575,7 @@ class BrowserManager:
     """
 
     _playwright_instance = None
-
+    
     @classmethod
     async def get_playwright(cls, use_undetected: bool = False):
         if use_undetected:
@@ -593,11 +583,9 @@ class BrowserManager:
         else:
             from playwright.async_api import async_playwright
         cls._playwright_instance = await async_playwright().start()
-        return cls._playwright_instance
+        return cls._playwright_instance    
 
-    def __init__(
-        self, browser_config: BrowserConfig, logger=None, use_undetected: bool = False
-    ):
+    def __init__(self, browser_config: BrowserConfig, logger=None, use_undetected: bool = False):
         """
         Initialize the BrowserManager with a browser configuration.
 
@@ -623,17 +611,16 @@ class BrowserManager:
         # Keep track of contexts by a "config signature," so each unique config reuses a single context
         self.contexts_by_config = {}
         self._contexts_lock = asyncio.Lock()
-
+        
         # Serialize context.new_page() across concurrent tasks to avoid races
         # when using a shared persistent context (context.pages may be empty
         # for all racers). Prevents 'Target page/context closed' errors.
         self._page_lock = asyncio.Lock()
-
+        
         # Stealth adapter for stealth mode
         self._stealth_adapter = None
         if self.config.enable_stealth and not self.use_undetected:
             from .browser_adapter import StealthAdapter
-
             self._stealth_adapter = StealthAdapter()
 
         # Initialize ManagedBrowser if needed
@@ -662,7 +649,7 @@ class BrowserManager:
         """
         if self.playwright is not None:
             await self.close()
-
+            
         if self.use_undetected:
             from patchright.async_api import async_playwright
         else:
@@ -673,11 +660,7 @@ class BrowserManager:
 
         if self.config.cdp_url or self.config.use_managed_browser:
             self.config.use_managed_browser = True
-            cdp_url = (
-                await self.managed_browser.start()
-                if not self.config.cdp_url
-                else self.config.cdp_url
-            )
+            cdp_url = await self.managed_browser.start() if not self.config.cdp_url else self.config.cdp_url
             self.browser = await self.playwright.chromium.connect_over_cdp(cdp_url)
             contexts = self.browser.contexts
             if contexts:
@@ -698,6 +681,7 @@ class BrowserManager:
 
             self.default_context = self.browser
 
+
     def _build_browser_args(self) -> dict:
         """Build browser launch arguments from config."""
         args = [
@@ -743,7 +727,7 @@ class BrowserManager:
 
         # Deduplicate args
         args = list(dict.fromkeys(args))
-
+        
         browser_args = {"headless": self.config.headless, "args": args}
 
         if self.config.chrome_channel:
@@ -820,9 +804,9 @@ class BrowserManager:
             context.set_default_navigation_timeout(DOWNLOAD_PAGE_TIMEOUT)
             if self.config.downloads_path:
                 context._impl_obj._options["accept_downloads"] = True
-                context._impl_obj._options["downloads_path"] = (
-                    self.config.downloads_path
-                )
+                context._impl_obj._options[
+                    "downloads_path"
+                ] = self.config.downloads_path
 
         # Handle user agent and browser hints
         if self.config.user_agent:
@@ -853,7 +837,7 @@ class BrowserManager:
                 or crawlerRunConfig.simulate_user
                 or crawlerRunConfig.magic
             ):
-                await context.add_init_script(load_js_script("navigator_overrider"))
+                await context.add_init_script(load_js_script("navigator_overrider"))        
 
     async def create_browser_context(self, crawlerRunConfig: CrawlerRunConfig = None):
         """
@@ -864,7 +848,7 @@ class BrowserManager:
             Context: Browser context object with the specified configurations
         """
         # Base settings
-        user_agent = self.config.headers.get("User-Agent", self.config.user_agent)
+        user_agent = self.config.headers.get("User-Agent", self.config.user_agent) 
         viewport_settings = {
             "width": self.config.viewport_width,
             "height": self.config.viewport_height,
@@ -937,7 +921,7 @@ class BrowserManager:
             "device_scale_factor": 1.0,
             "java_script_enabled": self.config.java_script_enabled,
         }
-
+        
         if crawlerRunConfig:
             # Check if there is value for crawlerRunConfig.proxy_config set add that to context
             if crawlerRunConfig.proxy_config:
@@ -945,12 +929,10 @@ class BrowserManager:
                     "server": crawlerRunConfig.proxy_config.server,
                 }
                 if crawlerRunConfig.proxy_config.username:
-                    proxy_settings.update(
-                        {
-                            "username": crawlerRunConfig.proxy_config.username,
-                            "password": crawlerRunConfig.proxy_config.password,
-                        }
-                    )
+                    proxy_settings.update({
+                        "username": crawlerRunConfig.proxy_config.username,
+                        "password": crawlerRunConfig.proxy_config.password,
+                    })
                 context_settings["proxy"] = proxy_settings
 
         if self.config.text_mode:
@@ -1008,12 +990,12 @@ class BrowserManager:
             "cache_mode",
             "content_filter",
             "semaphore_count",
-            "url",
+            "url"
         ]
-
+        
         # Do NOT exclude locale, timezone_id, or geolocation as these DO affect browser context
         # and should cause a new context to be created if they change
-
+        
         for key in ephemeral_keys:
             if key in config_dict:
                 del config_dict[key]
@@ -1034,7 +1016,7 @@ class BrowserManager:
                     self.logger.warning(
                         message="Failed to apply stealth to page: {error}",
                         tag="STEALTH",
-                        params={"error": str(e)},
+                        params={"error": str(e)}
                     )
 
     async def get_page(self, crawlerRunConfig: CrawlerRunConfig):
@@ -1060,10 +1042,8 @@ class BrowserManager:
         if self.config.use_managed_browser:
             if self.config.storage_state:
                 context = await self.create_browser_context(crawlerRunConfig)
-                ctx = self.default_context  # default context, one window only
-                ctx = await clone_runtime_state(
-                    context, ctx, crawlerRunConfig, self.config
-                )
+                ctx = self.default_context        # default context, one window only
+                ctx = await clone_runtime_state(context, ctx, crawlerRunConfig, self.config)
                 # Avoid concurrent new_page on shared persistent context
                 # See GH-1198: context.pages can be empty under races
                 async with self._page_lock:
@@ -1075,21 +1055,14 @@ class BrowserManager:
                 page = next((p for p in pages if p.url == crawlerRunConfig.url), None)
                 if not page:
                     if pages:
-                        # FIX: Always create a new page for managed browsers to support concurrent crawling
-                        # Previously: page = pages[0]
-                        async with self._page_lock:
-                            page = await context.new_page()
-                        await self._apply_stealth_to_page(page)
+                        page = pages[0]
                     else:
                         # Double-check under lock to avoid TOCTOU and ensure only
                         # one task calls new_page when pages=[] concurrently
                         async with self._page_lock:
                             pages = context.pages
                             if pages:
-                                # FIX: Always create a new page for managed browsers to support concurrent crawling
-                                # Previously: page = pages[0]
-                                page = await context.new_page()
-                                await self._apply_stealth_to_page(page)
+                                page = pages[0]
                             else:
                                 page = await context.new_page()
                                 await self._apply_stealth_to_page(page)
@@ -1145,7 +1118,7 @@ class BrowserManager:
         """Close all browser resources and clean up."""
         if self.config.cdp_url:
             return
-
+        
         if self.config.sleep_on_close:
             await asyncio.sleep(0.5)
 
@@ -1161,7 +1134,7 @@ class BrowserManager:
                 self.logger.error(
                     message="Error closing context: {error}",
                     tag="ERROR",
-                    params={"error": str(e)},
+                    params={"error": str(e)}
                 )
         self.contexts_by_config.clear()
 

crawl4ai/extraction_strategy.py

@@ -94,6 +94,20 @@ class ExtractionStrategy(ABC):
                 extracted_content.extend(future.result())
         return extracted_content
 
+    async def arun(self, url: str, sections: List[str], *q, **kwargs) -> List[Dict[str, Any]]:
+        """
+        Async version: Process sections of text in parallel using asyncio.
+
+        Default implementation runs the sync version in a thread pool.
+        Subclasses can override this for true async processing.
+
+        :param url: The URL of the webpage.
+        :param sections: List of sections (strings) to process.
+        :return: A list of processed JSON blocks.
+        """
+        import asyncio
+        return await asyncio.to_thread(self.run, url, sections, *q, **kwargs)
+
 
 class NoExtractionStrategy(ExtractionStrategy):
     """
@@ -780,6 +794,177 @@ class LLMExtractionStrategy(ExtractionStrategy):
 
         return extracted_content
 
+    async def aextract(self, url: str, ix: int, html: str) -> List[Dict[str, Any]]:
+        """
+        Async version: Extract meaningful blocks or chunks from the given HTML using an LLM.
+
+        How it works:
+        1. Construct a prompt with variables.
+        2. Make an async request to the LLM using the prompt.
+        3. Parse the response and extract blocks or chunks.
+
+        Args:
+            url: The URL of the webpage.
+            ix: Index of the block.
+            html: The HTML content of the webpage.
+
+        Returns:
+            A list of extracted blocks or chunks.
+        """
+        from .utils import aperform_completion_with_backoff
+
+        if self.verbose:
+            print(f"[LOG] Call LLM for {url} - block index: {ix}")
+
+        variable_values = {
+            "URL": url,
+            "HTML": escape_json_string(sanitize_html(html)),
+        }
+
+        prompt_with_variables = PROMPT_EXTRACT_BLOCKS
+        if self.instruction:
+            variable_values["REQUEST"] = self.instruction
+            prompt_with_variables = PROMPT_EXTRACT_BLOCKS_WITH_INSTRUCTION
+
+        if self.extract_type == "schema" and self.schema:
+            variable_values["SCHEMA"] = json.dumps(self.schema, indent=2)
+            prompt_with_variables = PROMPT_EXTRACT_SCHEMA_WITH_INSTRUCTION
+
+        if self.extract_type == "schema" and not self.schema:
+            prompt_with_variables = PROMPT_EXTRACT_INFERRED_SCHEMA
+
+        for variable in variable_values:
+            prompt_with_variables = prompt_with_variables.replace(
+                "{" + variable + "}", variable_values[variable]
+            )
+
+        try:
+            response = await aperform_completion_with_backoff(
+                self.llm_config.provider,
+                prompt_with_variables,
+                self.llm_config.api_token,
+                base_url=self.llm_config.base_url,
+                json_response=self.force_json_response,
+                extra_args=self.extra_args,
+            )
+            # Track usage
+            usage = TokenUsage(
+                completion_tokens=response.usage.completion_tokens,
+                prompt_tokens=response.usage.prompt_tokens,
+                total_tokens=response.usage.total_tokens,
+                completion_tokens_details=response.usage.completion_tokens_details.__dict__
+                if response.usage.completion_tokens_details
+                else {},
+                prompt_tokens_details=response.usage.prompt_tokens_details.__dict__
+                if response.usage.prompt_tokens_details
+                else {},
+            )
+            self.usages.append(usage)
+
+            # Update totals
+            self.total_usage.completion_tokens += usage.completion_tokens
+            self.total_usage.prompt_tokens += usage.prompt_tokens
+            self.total_usage.total_tokens += usage.total_tokens
+
+            try:
+                content = response.choices[0].message.content
+                blocks = None
+
+                if self.force_json_response:
+                    blocks = json.loads(content)
+                    if isinstance(blocks, dict):
+                        if len(blocks) == 1 and isinstance(list(blocks.values())[0], list):
+                            blocks = list(blocks.values())[0]
+                        else:
+                            blocks = [blocks]
+                    elif isinstance(blocks, list):
+                        blocks = blocks
+                else:
+                    blocks = extract_xml_data(["blocks"], content)["blocks"]
+                    blocks = json.loads(blocks)
+
+                for block in blocks:
+                    block["error"] = False
+            except Exception:
+                parsed, unparsed = split_and_parse_json_objects(
+                    response.choices[0].message.content
+                )
+                blocks = parsed
+                if unparsed:
+                    blocks.append(
+                        {"index": 0, "error": True, "tags": ["error"], "content": unparsed}
+                    )
+
+            if self.verbose:
+                print(
+                    "[LOG] Extracted",
+                    len(blocks),
+                    "blocks from URL:",
+                    url,
+                    "block index:",
+                    ix,
+                )
+            return blocks
+        except Exception as e:
+            if self.verbose:
+                print(f"[LOG] Error in LLM extraction: {e}")
+            return [
+                {
+                    "index": ix,
+                    "error": True,
+                    "tags": ["error"],
+                    "content": str(e),
+                }
+            ]
+
+    async def arun(self, url: str, sections: List[str]) -> List[Dict[str, Any]]:
+        """
+        Async version: Process sections with true parallelism using asyncio.gather.
+
+        Args:
+            url: The URL of the webpage.
+            sections: List of sections (strings) to process.
+
+        Returns:
+            A list of extracted blocks or chunks.
+        """
+        import asyncio
+
+        merged_sections = self._merge(
+            sections,
+            self.chunk_token_threshold,
+            overlap=int(self.chunk_token_threshold * self.overlap_rate),
+        )
+
+        extracted_content = []
+
+        # Create tasks for all sections to run in parallel
+        tasks = [
+            self.aextract(url, ix, sanitize_input_encode(section))
+            for ix, section in enumerate(merged_sections)
+        ]
+
+        # Execute all tasks concurrently
+        results = await asyncio.gather(*tasks, return_exceptions=True)
+
+        # Process results
+        for result in results:
+            if isinstance(result, Exception):
+                if self.verbose:
+                    print(f"Error in async extraction: {result}")
+                extracted_content.append(
+                    {
+                        "index": 0,
+                        "error": True,
+                        "tags": ["error"],
+                        "content": str(result),
+                    }
+                )
+            else:
+                extracted_content.extend(result)
+
+        return extracted_content
+
     def show_usage(self) -> None:
         """Print a detailed token usage report showing total and per-request usage."""
         print("\n=== Token Usage Summary ===")

crawl4ai/utils.py

@@ -1825,6 +1825,82 @@ def perform_completion_with_backoff(
             # ]
 
 
+async def aperform_completion_with_backoff(
+    provider,
+    prompt_with_variables,
+    api_token,
+    json_response=False,
+    base_url=None,
+    **kwargs,
+):
+    """
+    Async version: Perform an API completion request with exponential backoff.
+
+    How it works:
+    1. Sends an async completion request to the API.
+    2. Retries on rate-limit errors with exponential delays (async).
+    3. Returns the API response or an error after all retries.
+
+    Args:
+        provider (str): The name of the API provider.
+        prompt_with_variables (str): The input prompt for the completion request.
+        api_token (str): The API token for authentication.
+        json_response (bool): Whether to request a JSON response. Defaults to False.
+        base_url (Optional[str]): The base URL for the API. Defaults to None.
+        **kwargs: Additional arguments for the API request.
+
+    Returns:
+        dict: The API response or an error message after all retries.
+    """
+
+    from litellm import acompletion
+    from litellm.exceptions import RateLimitError
+    import asyncio
+
+    max_attempts = 3
+    base_delay = 2  # Base delay in seconds, you can adjust this based on your needs
+
+    extra_args = {"temperature": 0.01, "api_key": api_token, "base_url": base_url}
+    if json_response:
+        extra_args["response_format"] = {"type": "json_object"}
+
+    if kwargs.get("extra_args"):
+        extra_args.update(kwargs["extra_args"])
+
+    for attempt in range(max_attempts):
+        try:
+            response = await acompletion(
+                model=provider,
+                messages=[{"role": "user", "content": prompt_with_variables}],
+                **extra_args,
+            )
+            return response  # Return the successful response
+        except RateLimitError as e:
+            print("Rate limit error:", str(e))
+
+            if attempt == max_attempts - 1:
+                # Last attempt failed, raise the error.
+                raise
+
+            # Check if we have exhausted our max attempts
+            if attempt < max_attempts - 1:
+                # Calculate the delay and wait
+                delay = base_delay * (2**attempt)  # Exponential backoff formula
+                print(f"Waiting for {delay} seconds before retrying...")
+                await asyncio.sleep(delay)
+            else:
+                # Return an error response after exhausting all retries
+                return [
+                    {
+                        "index": 0,
+                        "tags": ["error"],
+                        "content": ["Rate limit error. Please try again later."],
+                    }
+                ]
+        except Exception as e:
+            raise e  # Raise any other exceptions immediately
+
+
 def extract_blocks(url, html, provider=DEFAULT_PROVIDER, api_token=None, base_url=None):
     """
     Extract content blocks from website HTML using an AI provider.

docker-compose.yml

@@ -6,15 +6,16 @@ x-base-config: &base-config
     - "11235:11235"  # Gunicorn port
   env_file:
     - .llm.env       # API keys (create from .llm.env.example)
-  environment:
-    - OPENAI_API_KEY=${OPENAI_API_KEY:-}
-    - DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY:-}
-    - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
-    - GROQ_API_KEY=${GROQ_API_KEY:-}
-    - TOGETHER_API_KEY=${TOGETHER_API_KEY:-}
-    - MISTRAL_API_KEY=${MISTRAL_API_KEY:-}
-    - GEMINI_API_TOKEN=${GEMINI_API_TOKEN:-}
-    - LLM_PROVIDER=${LLM_PROVIDER:-}  # Optional: Override default provider (e.g., "anthropic/claude-3-opus")
+  # Uncomment to set default environment variables (will overwrite .llm.env)
+  # environment:
+  #   - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+  #   - DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY:-}
+  #   - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
+  #   - GROQ_API_KEY=${GROQ_API_KEY:-}
+  #   - TOGETHER_API_KEY=${TOGETHER_API_KEY:-}
+  #   - MISTRAL_API_KEY=${MISTRAL_API_KEY:-}
+  #   - GEMINI_API_KEY=${GEMINI_API_KEY:-}
+  #   - LLM_PROVIDER=${LLM_PROVIDER:-}  # Optional: Override default provider (e.g., "anthropic/claude-3-opus")
   volumes:
     - /dev/shm:/dev/shm  # Chromium performance
   deploy:

docs/examples/c4a_script/tutorial/README.md

@@ -18,7 +18,7 @@ A comprehensive web-based tutorial for learning and experimenting with C4A-Scrip
 
 2. **Install Dependencies**
    ```bash
-   pip install flask
+   pip install -r requirements.txt
    ```
 
 3. **Launch the Server**
@@ -28,7 +28,7 @@ A comprehensive web-based tutorial for learning and experimenting with C4A-Scrip
 
 4. **Open in Browser**
    ```
-   http://localhost:8080
+   http://localhost:8000
    ```
 
 **🌐 Try Online**: [Live Demo](https://docs.crawl4ai.com/c4a-script/demo)
@@ -325,7 +325,7 @@ Powers the recording functionality:
 ### Configuration
 ```python
 # server.py configuration
-PORT = 8080
+PORT = 8000
 DEBUG = True
 THREADED = True
 ```
@@ -343,9 +343,9 @@ THREADED = True
 **Port Already in Use**
 ```bash
 # Kill existing process
-lsof -ti:8080 | xargs kill -9
+lsof -ti:8000 | xargs kill -9
 # Or use different port
-python server.py --port 8081
+python server.py --port 8001
 ```
 
 **Blockly Not Loading**

docs/examples/c4a_script/tutorial/server.py

@@ -216,7 +216,7 @@ def get_examples():
             'name': 'Handle Cookie Banner',
             'description': 'Accept cookies and close newsletter popup',
             'script': '''# Handle cookie banner and newsletter
-GO http://127.0.0.1:8080/playground/
+GO http://127.0.0.1:8000/playground/
 WAIT `body` 2
 IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
 IF (EXISTS `.newsletter-popup`) THEN CLICK `.close`'''

docs/md_v2/advanced/identity-based-crawling.md

@@ -82,6 +82,42 @@ If you installed Crawl4AI (which installs Playwright under the hood), you alread
 
 ---
 
+### Creating a Profile Using the Crawl4AI CLI (Easiest)
+
+If you prefer a guided, interactive setup, use the built-in CLI to create and manage persistent browser profiles.
+
+1.⠀Launch the profile manager:
+   ```bash
+   crwl profiles
+   ```
+
+2.⠀Choose "Create new profile" and enter a profile name. A Chromium window opens so you can log in to sites and configure settings. When finished, return to the terminal and press `q` to save the profile.
+
+3.⠀Profiles are saved under `~/.crawl4ai/profiles/<profile_name>` (for example: `/home/<you>/.crawl4ai/profiles/test_profile_1`) along with a `storage_state.json` for cookies and session data.
+
+4.⠀Optionally, choose "List profiles" in the CLI to view available profiles and their paths.
+
+5.⠀Use the saved path with `BrowserConfig.user_data_dir`:
+   ```python
+   from crawl4ai import AsyncWebCrawler, BrowserConfig
+
+   profile_path = "/home/<you>/.crawl4ai/profiles/test_profile_1"
+
+   browser_config = BrowserConfig(
+       headless=True,
+       use_managed_browser=True,
+       user_data_dir=profile_path,
+       browser_type="chromium",
+   )
+
+   async with AsyncWebCrawler(config=browser_config) as crawler:
+       result = await crawler.arun(url="https://example.com/private")
+   ```
+
+The CLI also supports listing and deleting profiles, and even testing a crawl directly from the menu.
+
+---
+
 ## 3. Using Managed Browsers in Crawl4AI
 
 Once you have a data directory with your session data, pass it to **`BrowserConfig`**:

docs/md_v2/apps/c4a-script/README.md

@@ -18,7 +18,7 @@ A comprehensive web-based tutorial for learning and experimenting with C4A-Scrip
 
 2. **Install Dependencies**
    ```bash
-   pip install flask
+   pip install -r requirements.txt
    ```
 
 3. **Launch the Server**
@@ -28,7 +28,7 @@ A comprehensive web-based tutorial for learning and experimenting with C4A-Scrip
 
 4. **Open in Browser**
    ```
-   http://localhost:8080
+   http://localhost:8000
    ```
 
 **🌐 Try Online**: [Live Demo](https://docs.crawl4ai.com/c4a-script/demo)
@@ -325,7 +325,7 @@ Powers the recording functionality:
 ### Configuration
 ```python
 # server.py configuration
-PORT = 8080
+PORT = 8000
 DEBUG = True
 THREADED = True
 ```
@@ -343,9 +343,9 @@ THREADED = True
 **Port Already in Use**
 ```bash
 # Kill existing process
-lsof -ti:8080 | xargs kill -9
+lsof -ti:8000 | xargs kill -9
 # Or use different port
-python server.py --port 8081
+python server.py --port 8001
 ```
 
 **Blockly Not Loading**

docs/md_v2/apps/c4a-script/server.py

@@ -216,7 +216,7 @@ def get_examples():
             'name': 'Handle Cookie Banner',
             'description': 'Accept cookies and close newsletter popup',
             'script': '''# Handle cookie banner and newsletter
-GO http://127.0.0.1:8080/playground/
+GO http://127.0.0.1:8000/playground/
 WAIT `body` 2
 IF (EXISTS `.cookie-banner`) THEN CLICK `.accept`
 IF (EXISTS `.newsletter-popup`) THEN CLICK `.close`'''
@@ -283,7 +283,7 @@ WAIT `.success-message` 5'''
     return jsonify(examples)
 
 if __name__ == '__main__':
-    port = int(os.environ.get('PORT', 8080))
+    port = int(os.environ.get('PORT', 8000))
     print(f"""
 ╔══════════════════════════════════════════════════════════╗
 ║          C4A-Script Interactive Tutorial Server          ║

docs/md_v2/core/c4a-script.md

@@ -69,12 +69,12 @@ The tutorial includes a Flask-based web interface with:
 cd docs/examples/c4a_script/tutorial/
 
 # Install dependencies
-pip install flask
+pip install -r requirements.txt
 
 # Launch the tutorial server
-python app.py
+python server.py
 
-# Open http://localhost:5000 in your browser
+# Open http://localhost:8000 in your browser
 ```
 
 ## Core Concepts
@@ -111,8 +111,8 @@ CLICK `.submit-btn`
 # By attribute
 CLICK `button[type="submit"]`
 
-# By text content
-CLICK `button:contains("Sign In")`
+# By accessible attributes
+CLICK `button[aria-label="Search"][title="Search"]`
 
 # Complex selectors
 CLICK `.form-container input[name="email"]`

docs/md_v2/index.md

@@ -57,7 +57,7 @@
 
 Crawl4AI is the #1 trending GitHub repository, actively maintained by a vibrant community. It delivers blazing-fast, AI-ready web crawling tailored for large language models, AI agents, and data pipelines. Fully open source, flexible, and built for real-time performance, **Crawl4AI** empowers developers with unmatched speed, precision, and deployment ease.
 
-> **Note**: If you're looking for the old documentation, you can access it [here](https://old.docs.crawl4ai.com).
+> Enjoy using Crawl4AI? Consider **[becoming a sponsor](https://github.com/sponsors/unclecode)** to support ongoing development and community growth!
 
 ## 🆕 AI Assistant Skill Now Available!
 

tests/general/test_async_crawler_strategy.py

@@ -364,5 +364,19 @@ async def test_network_error_handling():
         async with AsyncPlaywrightCrawlerStrategy() as strategy:
             await strategy.crawl("https://invalid.example.com", config)
 
+@pytest.mark.asyncio
+async def test_remove_overlay_elements(crawler_strategy):
+    config = CrawlerRunConfig(
+        remove_overlay_elements=True,
+        delay_before_return_html=5,
+    )
+    
+    response = await crawler_strategy.crawl(
+        "https://www2.hm.com/en_us/index.html",
+        config
+    )
+    assert response.status_code == 200
+    assert "Accept all cookies" not in response.html
+
 if __name__ == "__main__":
     pytest.main([__file__, "-v"])

tests/test_cdp_concurrency_compact.py

@@ -1,283 +0,0 @@
-"""
-Compact test suite for CDP concurrency fix.
-
-This file consolidates all tests related to the CDP concurrency fix for
-AsyncWebCrawler.arun_many() with managed browsers.
-
-The bug was that all concurrent tasks were fighting over one shared tab,
-causing failures. This has been fixed by modifying the get_page() method
-in browser_manager.py to always create new pages instead of reusing pages[0].
-"""
-
-import asyncio
-import shutil
-import sys
-import tempfile
-from pathlib import Path
-
-# Add parent directory to path for imports
-sys.path.insert(0, str(Path(__file__).parent.parent))
-
-from crawl4ai import AsyncWebCrawler, CacheMode, CrawlerRunConfig
-from crawl4ai.async_configs import BrowserConfig
-
-# =============================================================================
-# TEST 1: Basic arun_many functionality
-# =============================================================================
-
-
-async def test_basic_arun_many():
-    """Test that arun_many works correctly with basic configuration."""
-    print("=== TEST 1: Basic arun_many functionality ===")
-
-    # Configuration to bypass cache for testing
-    config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS)
-
-    # Test URLs - using reliable test URLs
-    test_urls = [
-        "https://httpbin.org/html",  # Simple HTML page
-        "https://httpbin.org/json",  # Simple JSON response
-    ]
-
-    async with AsyncWebCrawler() as crawler:
-        print(f"Testing concurrent crawling of {len(test_urls)} URLs...")
-
-        # This should work correctly
-        result = await crawler.arun_many(urls=test_urls, config=config)
-
-        # Simple verification - if we get here without exception, the basic functionality works
-        print(f"✓ arun_many completed successfully")
-        return True
-
-
-# =============================================================================
-# TEST 2: CDP Browser with Managed Configuration
-# =============================================================================
-
-
-async def test_arun_many_with_managed_cdp_browser():
-    """Test that arun_many works correctly with managed CDP browsers."""
-    print("\n=== TEST 2: arun_many with managed CDP browser ===")
-
-    # Create a temporary user data directory for the CDP browser
-    user_data_dir = tempfile.mkdtemp(prefix="crawl4ai-cdp-test-")
-
-    try:
-        # Configure browser to use managed CDP mode
-        browser_config = BrowserConfig(
-            use_managed_browser=True,
-            browser_type="chromium",
-            headless=True,
-            user_data_dir=user_data_dir,
-            verbose=True,
-        )
-
-        # Configuration to bypass cache for testing
-        crawler_config = CrawlerRunConfig(
-            cache_mode=CacheMode.BYPASS,
-            page_timeout=60000,
-            wait_until="domcontentloaded",
-        )
-
-        # Test URLs - using reliable test URLs
-        test_urls = [
-            "https://httpbin.org/html",  # Simple HTML page
-            "https://httpbin.org/json",  # Simple JSON response
-        ]
-
-        # Create crawler with CDP browser configuration
-        async with AsyncWebCrawler(config=browser_config) as crawler:
-            print(f"Testing concurrent crawling of {len(test_urls)} URLs...")
-
-            # This should work correctly with our fix
-            result = await crawler.arun_many(urls=test_urls, config=crawler_config)
-
-            print(f"✓ arun_many completed successfully with managed CDP browser")
-            return True
-
-    except Exception as e:
-        print(f"❌ Test failed with error: {str(e)}")
-        raise
-    finally:
-        # Clean up temporary directory
-        try:
-            shutil.rmtree(user_data_dir, ignore_errors=True)
-        except:
-            pass
-
-
-# =============================================================================
-# TEST 3: Concurrency Verification
-# =============================================================================
-
-
-async def test_concurrent_crawling():
-    """Test concurrent crawling to verify the fix works."""
-    print("\n=== TEST 3: Concurrent crawling verification ===")
-
-    # Configuration to bypass cache for testing
-    config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS)
-
-    # Test URLs - using reliable test URLs
-    test_urls = [
-        "https://httpbin.org/html",  # Simple HTML page
-        "https://httpbin.org/json",  # Simple JSON response
-        "https://httpbin.org/uuid",  # Simple UUID response
-        "https://example.com/",  # Standard example page
-    ]
-
-    async with AsyncWebCrawler() as crawler:
-        print(f"Testing concurrent crawling of {len(test_urls)} URLs...")
-
-        # This should work correctly with our fix
-        results = await crawler.arun_many(urls=test_urls, config=config)
-
-        # Simple verification - if we get here without exception, the fix works
-        print("✓ arun_many completed successfully with concurrent crawling")
-        return True
-
-
-# =============================================================================
-# TEST 4: Concurrency Fix Demonstration
-# =============================================================================
-
-
-async def test_concurrency_fix():
-    """Demonstrate that the concurrency fix works."""
-    print("\n=== TEST 4: Concurrency fix demonstration ===")
-
-    # Configuration to bypass cache for testing
-    config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS)
-
-    # Test URLs - using reliable test URLs
-    test_urls = [
-        "https://httpbin.org/html",  # Simple HTML page
-        "https://httpbin.org/json",  # Simple JSON response
-        "https://httpbin.org/uuid",  # Simple UUID response
-    ]
-
-    async with AsyncWebCrawler() as crawler:
-        print(f"Testing concurrent crawling of {len(test_urls)} URLs...")
-
-        # This should work correctly with our fix
-        results = await crawler.arun_many(urls=test_urls, config=config)
-
-        # Simple verification - if we get here without exception, the fix works
-        print("✓ arun_many completed successfully with concurrent crawling")
-        return True
-
-
-# =============================================================================
-# TEST 5: Before/After Behavior Comparison
-# =============================================================================
-
-
-async def test_before_after_behavior():
-    """Test that demonstrates concurrent crawling works correctly after the fix."""
-    print("\n=== TEST 5: Before/After behavior test ===")
-
-    # Configuration to bypass cache for testing
-    config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS)
-
-    # Test URLs - using reliable test URLs that would stress the concurrency system
-    test_urls = [
-        "https://httpbin.org/delay/1",  # Delayed response to increase chance of contention
-        "https://httpbin.org/delay/2",  # Delayed response to increase chance of contention
-        "https://httpbin.org/uuid",  # Fast response
-        "https://httpbin.org/json",  # Fast response
-    ]
-
-    async with AsyncWebCrawler() as crawler:
-        print(
-            f"Testing concurrent crawling of {len(test_urls)} URLs (including delayed responses)..."
-        )
-        print(
-            "This test would have failed before the concurrency fix due to page contention."
-        )
-
-        # This should work correctly with our fix
-        results = await crawler.arun_many(urls=test_urls, config=config)
-
-        # Simple verification - if we get here without exception, the fix works
-        print("✓ arun_many completed successfully with concurrent crawling")
-        print("✓ No page contention issues detected")
-        return True
-
-
-# =============================================================================
-# TEST 6: Reference Pattern Test
-# =============================================================================
-
-
-async def test_reference_pattern():
-    """Main test function following reference pattern."""
-    print("\n=== TEST 6: Reference pattern test ===")
-
-    # Configure crawler settings
-    crawler_cfg = CrawlerRunConfig(
-        cache_mode=CacheMode.BYPASS,
-        page_timeout=60000,
-        wait_until="domcontentloaded",
-    )
-
-    # Define URLs to crawl
-    URLS = [
-        "https://httpbin.org/html",
-        "https://httpbin.org/json",
-        "https://httpbin.org/uuid",
-    ]
-
-    # Crawl all URLs using arun_many
-    async with AsyncWebCrawler() as crawler:
-        print(f"Testing concurrent crawling of {len(URLS)} URLs...")
-        results = await crawler.arun_many(urls=URLS, config=crawler_cfg)
-
-        # Simple verification - if we get here without exception, the fix works
-        print("✓ arun_many completed successfully with concurrent crawling")
-        print("✅ Reference pattern test completed successfully!")
-
-
-# =============================================================================
-# MAIN EXECUTION
-# =============================================================================
-
-
-async def main():
-    """Run all tests."""
-    print("Running compact CDP concurrency test suite...")
-    print("=" * 60)
-
-    tests = [
-        test_basic_arun_many,
-        test_arun_many_with_managed_cdp_browser,
-        test_concurrent_crawling,
-        test_concurrency_fix,
-        test_before_after_behavior,
-        test_reference_pattern,
-    ]
-
-    passed = 0
-    failed = 0
-
-    for test_func in tests:
-        try:
-            await test_func()
-            passed += 1
-        except Exception as e:
-            print(f"❌ Test failed: {str(e)}")
-            failed += 1
-
-    print("\n" + "=" * 60)
-    print(f"Test Results: {passed} passed, {failed} failed")
-
-    if failed == 0:
-        print("🎉 All tests passed! The CDP concurrency fix is working correctly.")
-        return True
-    else:
-        print(f"❌ {failed} test(s) failed!")
-        return False
-
-
-if __name__ == "__main__":
-    success = asyncio.run(main())
-    sys.exit(0 if success else 1)

tests/test_llm_extraction_parallel_issue_1055.py

@@ -0,0 +1,220 @@
+"""
+Final verification test for Issue #1055 fix
+
+This test demonstrates that LLM extraction now runs in parallel
+when using arun_many with multiple URLs.
+"""
+
+import os
+import sys
+import time
+import asyncio
+
+grandparent_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+sys.path.append(grandparent_dir)
+
+from crawl4ai import (
+    AsyncWebCrawler,
+    BrowserConfig,
+    CrawlerRunConfig,
+    CacheMode,
+    LLMExtractionStrategy,
+    LLMConfig,
+)
+
+from pydantic import BaseModel
+
+
+class SimpleData(BaseModel):
+    title: str
+    summary: str
+
+
+def print_section(title):
+    print("\n" + "=" * 80)
+    print(title)
+    print("=" * 80 + "\n")
+
+
+async def test_without_llm():
+    """Baseline: Test crawling without LLM extraction"""
+    print_section("TEST 1: Crawling WITHOUT LLM Extraction")
+
+    config = CrawlerRunConfig(
+        cache_mode=CacheMode.BYPASS,
+    )
+
+    browser_config = BrowserConfig(headless=True, verbose=False)
+
+    urls = [
+        "https://www.example.com",
+        "https://www.iana.org",
+        "https://www.wikipedia.org",
+    ]
+
+    print(f"Crawling {len(urls)} URLs without LLM extraction...")
+    print("Expected: Fast and parallel\n")
+
+    start_time = time.time()
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        results = await crawler.arun_many(urls=urls, config=config)
+
+    duration = time.time() - start_time
+
+    print(f"\n✅ Completed in {duration:.2f}s")
+    print(f"   Successful: {sum(1 for r in results if r.success)}/{len(urls)}")
+    print(f"   Average: {duration/len(urls):.2f}s per URL")
+
+    return duration
+
+
+async def test_with_llm_before_fix():
+    """Demonstrate the problem: Sequential execution with LLM"""
+    print_section("TEST 2: What Issue #1055 Reported (LLM Sequential Behavior)")
+
+    print("The issue reported that with LLM extraction, URLs would crawl")
+    print("one after another instead of in parallel.")
+    print("\nWithout our fix, this would show:")
+    print("  - URL 1 fetches → extracts → completes")
+    print("  - URL 2 fetches → extracts → completes")
+    print("  - URL 3 fetches → extracts → completes")
+    print("\nTotal time would be approximately sum of all individual times.")
+
+
+async def test_with_llm_after_fix():
+    """Demonstrate the fix: Parallel execution with LLM"""
+    print_section("TEST 3: After Fix - LLM Extraction in Parallel")
+
+    config = CrawlerRunConfig(
+        cache_mode=CacheMode.BYPASS,
+        extraction_strategy=LLMExtractionStrategy(
+            llm_config=LLMConfig(provider="openai/gpt-4o-mini"),
+            schema=SimpleData.model_json_schema(),
+            extraction_type="schema",
+            instruction="Extract title and summary",
+        )
+    )
+
+    browser_config = BrowserConfig(headless=True, verbose=False)
+
+    urls = [
+        "https://www.example.com",
+        "https://www.iana.org",
+        "https://www.wikipedia.org",
+    ]
+
+    print(f"Crawling {len(urls)} URLs WITH LLM extraction...")
+    print("Expected: Parallel execution with our fix\n")
+
+    completion_times = {}
+    start_time = time.time()
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        results = await crawler.arun_many(urls=urls, config=config)
+        for result in results:
+            elapsed = time.time() - start_time
+            completion_times[result.url] = elapsed
+            print(f"  [{elapsed:5.2f}s] ✓ {result.url[:50]}")
+
+    duration = time.time() - start_time
+
+    print(f"\n✅ Total time: {duration:.2f}s")
+    print(f"   Successful: {sum(1 for url in urls if url in completion_times)}/{len(urls)}")
+
+    # Analyze parallelism
+    times = list(completion_times.values())
+    if len(times) >= 2:
+        # If parallel, completion times should be staggered, not evenly spaced
+        time_diffs = [times[i+1] - times[i] for i in range(len(times)-1)]
+        avg_diff = sum(time_diffs) / len(time_diffs)
+
+        print(f"\nParallelism Analysis:")
+        print(f"   Completion time differences: {[f'{d:.2f}s' for d in time_diffs]}")
+        print(f"   Average difference: {avg_diff:.2f}s")
+
+        # In parallel mode, some tasks complete close together
+        # In sequential mode, they're evenly spaced (avg ~2-3s apart)
+        if avg_diff < duration / len(urls):
+            print(f"   ✅ PARALLEL: Tasks completed with overlapping execution")
+        else:
+            print(f"   ⚠️  SEQUENTIAL: Tasks completed one after another")
+
+    return duration
+
+
+async def test_multiple_arun_calls():
+    """Test multiple individual arun() calls in parallel"""
+    print_section("TEST 4: Multiple arun() Calls with asyncio.gather")
+
+    config = CrawlerRunConfig(
+        cache_mode=CacheMode.BYPASS,
+        extraction_strategy=LLMExtractionStrategy(
+            llm_config=LLMConfig(provider="openai/gpt-4o-mini"),
+            schema=SimpleData.model_json_schema(),
+            extraction_type="schema",
+            instruction="Extract title and summary",
+        )
+    )
+
+    browser_config = BrowserConfig(headless=True, verbose=False)
+
+    urls = [
+        "https://www.example.com",
+        "https://www.iana.org",
+        "https://www.wikipedia.org",
+    ]
+
+    print(f"Running {len(urls)} arun() calls with asyncio.gather()...")
+    print("Expected: True parallel execution\n")
+
+    start_time = time.time()
+
+    async with AsyncWebCrawler(config=browser_config) as crawler:
+        tasks = [crawler.arun(url, config=config) for url in urls]
+        results = await asyncio.gather(*tasks)
+
+    duration = time.time() - start_time
+
+    print(f"\n✅ Completed in {duration:.2f}s")
+    print(f"   Successful: {sum(1 for r in results if r.success)}/{len(urls)}")
+    print(f"   This proves the async LLM extraction works correctly")
+
+    return duration
+
+
+async def main():
+    print("\n" + "🚀" * 40)
+    print("ISSUE #1055 FIX VERIFICATION")
+    print("Testing: Sequential → Parallel LLM Extraction")
+    print("🚀" * 40)
+
+    # Run tests
+    await test_without_llm()
+
+    await test_with_llm_before_fix()
+
+    time_with_llm = await test_with_llm_after_fix()
+
+    time_gather = await test_multiple_arun_calls()
+
+    # Final summary
+    print_section("FINAL VERDICT")
+
+    print("✅ Fix Verified!")
+    print("\nWhat changed:")
+    print("  • Created aperform_completion_with_backoff() using litellm.acompletion")
+    print("  • Added arun() method to ExtractionStrategy base class")
+    print("  • Implemented parallel arun() in LLMExtractionStrategy")
+    print("  • Updated AsyncWebCrawler to use arun() when available")
+    print("\nResult:")
+    print("  • LLM extraction now runs in parallel across multiple URLs")
+    print("  • Backward compatible - existing strategies still work")
+    print("  • No breaking changes to the API")
+    print("\n✨ Issue #1055 is RESOLVED!")
+
+    print("\n" + "=" * 80 + "\n")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

tests/unit/test_sitemap_namespace_parsing.py

@@ -0,0 +1,134 @@
+import sys
+from types import SimpleNamespace
+
+import pytest
+
+# Provide a lightweight stub for rank_bm25 before importing the seeder to avoid
+# optional dependency issues (e.g., incompatible wheels in CI).
+class _FakeBM25:
+    def __init__(self, corpus):
+        self._scores = [1.0] * len(corpus)
+
+    def get_scores(self, tokens):
+        return self._scores
+
+
+sys.modules.setdefault("rank_bm25", SimpleNamespace(BM25Okapi=_FakeBM25))
+
+from crawl4ai.async_url_seeder import AsyncUrlSeeder
+
+
+class DummyResponse:
+    def __init__(self, request_url: str, text: str):
+        self.status_code = 200
+        self._content = text.encode("utf-8")
+        self.url = request_url
+
+    def raise_for_status(self):
+        return None
+
+    @property
+    def content(self):
+        return self._content
+
+    @property
+    def text(self):
+        return self._content.decode("utf-8")
+
+
+class DummyAsyncClient:
+    def __init__(self, response_map):
+        self._responses = response_map
+
+    async def get(self, url, **kwargs):
+        payload = self._responses[url]
+        if callable(payload):
+            payload = payload()
+        return DummyResponse(url, payload)
+
+
+@pytest.mark.asyncio
+async def test_iter_sitemap_handles_namespace_less_sitemaps():
+    xml = """<?xml version="1.0"?>
+    <urlset>
+        <url><loc>https://example.com/a</loc></url>
+        <url><loc>https://example.com/b</loc></url>
+    </urlset>
+    """
+    seeder = AsyncUrlSeeder(client=DummyAsyncClient({"https://example.com/sitemap.xml": xml}))
+
+    urls = []
+    async for u in seeder._iter_sitemap("https://example.com/sitemap.xml"):
+        urls.append(u)
+
+    assert urls == ["https://example.com/a", "https://example.com/b"]
+
+
+@pytest.mark.asyncio
+async def test_iter_sitemap_handles_custom_namespace():
+    xml = """<?xml version="1.0"?>
+    <urlset xmlns="https://custom.namespace/schema">
+        <url><loc>https://example.com/ns</loc></url>
+    </urlset>
+    """
+    seeder = AsyncUrlSeeder(client=DummyAsyncClient({"https://example.com/ns-sitemap.xml": xml}))
+
+    urls = []
+    async for u in seeder._iter_sitemap("https://example.com/ns-sitemap.xml"):
+        urls.append(u)
+
+    assert urls == ["https://example.com/ns"]
+
+
+@pytest.mark.asyncio
+async def test_iter_sitemap_handles_namespace_index_and_children():
+    index_xml = """<?xml version="1.0"?>
+    <sitemapindex xmlns="http://another.example/ns">
+        <sitemap>
+            <loc>https://example.com/child-1.xml</loc>
+        </sitemap>
+        <sitemap>
+            <loc>https://example.com/child-2.xml</loc>
+        </sitemap>
+    </sitemapindex>
+    """
+    child_xml = """<?xml version="1.0"?>
+    <urlset xmlns="http://irrelevant">
+        <url><loc>https://example.com/page-{n}</loc></url>
+    </urlset>
+    """
+    responses = {
+        "https://example.com/index.xml": index_xml,
+        "https://example.com/child-1.xml": child_xml.format(n=1),
+        "https://example.com/child-2.xml": child_xml.format(n=2),
+    }
+    seeder = AsyncUrlSeeder(client=DummyAsyncClient(responses))
+
+    urls = []
+    async for u in seeder._iter_sitemap("https://example.com/index.xml"):
+        urls.append(u)
+
+    assert sorted(urls) == [
+        "https://example.com/page-1",
+        "https://example.com/page-2",
+    ]
+
+
+@pytest.mark.asyncio
+async def test_iter_sitemap_normalizes_relative_locations():
+    xml = """<?xml version="1.0"?>
+    <urlset>
+        <url><loc>/relative-path</loc></url>
+        <url><loc>https://example.com/absolute</loc></url>
+    </urlset>
+    """
+    seeder = AsyncUrlSeeder(client=DummyAsyncClient({"https://example.com/sitemap.xml": xml}))
+
+    urls = []
+    async for u in seeder._iter_sitemap("https://example.com/sitemap.xml"):
+        urls.append(u)
+
+    assert urls == [
+        "https://example.com/relative-path",
+        "https://example.com/absolute",
+    ]