fix: Set default desired concurrency for non-browser crawlers to 10

Author: vdusek

src/crawlee/_types.py

@@ -110,9 +110,9 @@ class ConcurrencySettings:
     def __init__(
         self,
         min_concurrency: int = 1,
-        max_concurrency: int = 200,
+        max_concurrency: int = 100,
         max_tasks_per_minute: float = float('inf'),
-        desired_concurrency: int | None = None,
+        desired_concurrency: int = 10,
     ) -> None:
         """Initialize a new instance.
 
@@ -125,21 +125,21 @@ def __init__(
             desired_concurrency: The desired number of tasks that should be running parallel on the start of the pool,
                 if there is a large enough supply of them. By default, it is `min_concurrency`.
         """
-        if desired_concurrency is not None and desired_concurrency < 1:
-            raise ValueError('desired_concurrency must be 1 or larger')
-
         if min_concurrency < 1:
             raise ValueError('min_concurrency must be 1 or larger')
 
         if max_concurrency < min_concurrency:
             raise ValueError('max_concurrency cannot be less than min_concurrency')
 
+        if desired_concurrency < min_concurrency:
+            raise ValueError('desired_concurrency cannot be less than min_concurrency')
+
         if max_tasks_per_minute <= 0:
             raise ValueError('max_tasks_per_minute must be positive')
 
         self.min_concurrency = min_concurrency
         self.max_concurrency = max_concurrency
-        self.desired_concurrency = desired_concurrency if desired_concurrency is not None else min_concurrency
+        self.desired_concurrency = desired_concurrency
         self.max_tasks_per_minute = max_tasks_per_minute
 
 

src/crawlee/crawlers/_adaptive_playwright/_adaptive_playwright_crawler.py

@@ -12,7 +12,7 @@
 from parsel import Selector
 from typing_extensions import Self, TypeVar, override
 
-from crawlee._types import BasicCrawlingContext, JsonSerializable, RequestHandlerRunResult
+from crawlee._types import BasicCrawlingContext, ConcurrencySettings, JsonSerializable, RequestHandlerRunResult
 from crawlee._utils.docs import docs_group
 from crawlee._utils.wait import wait_for
 from crawlee.crawlers import (
@@ -158,6 +158,10 @@ def __init__(
         self.result_checker = result_checker or (lambda _: True)
         self.result_comparator = result_comparator or create_default_comparator(result_checker)
 
+        # Set default concurrency settings for browser crawlers if not provided
+        if 'concurrency_settings' not in kwargs or kwargs['concurrency_settings'] is None:
+            kwargs['concurrency_settings'] = ConcurrencySettings(desired_concurrency=1)
+
         super().__init__(statistics=statistics, **kwargs)
 
         # Sub crawlers related.

src/crawlee/crawlers/_basic/_basic_crawler.py

@@ -30,6 +30,7 @@
 from crawlee._service_locator import ServiceLocator
 from crawlee._types import (
     BasicCrawlingContext,
+    ConcurrencySettings,
     EnqueueLinksKwargs,
     GetKeyValueStoreFromRequestHandlerFunction,
     HttpHeaders,
@@ -75,7 +76,6 @@
     from contextlib import AbstractAsyncContextManager
 
     from crawlee._types import (
-        ConcurrencySettings,
         EnqueueLinksFunction,
         ExtractLinksFunction,
         GetDataKwargs,

src/crawlee/crawlers/_playwright/_playwright_crawler.py

@@ -12,6 +12,7 @@
 
 from crawlee import service_locator
 from crawlee._request import Request, RequestOptions
+from crawlee._types import ConcurrencySettings
 from crawlee._utils.blocked import RETRY_CSS_SELECTORS
 from crawlee._utils.docs import docs_group
 from crawlee._utils.robots import RobotsTxtFile
@@ -194,6 +195,10 @@ def __init__(
 
         kwargs['http_client'] = PlaywrightHttpClient() if not kwargs.get('http_client') else kwargs['http_client']
 
+        # Set default concurrency settings for browser crawlers if not provided
+        if 'concurrency_settings' not in kwargs or kwargs['concurrency_settings'] is None:
+            kwargs['concurrency_settings'] = ConcurrencySettings(desired_concurrency=1)
+
         super().__init__(**kwargs)
 
     async def _open_page(