freedak/Scrapling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(DynamicSession): New option to add extra browser flags

Browse Source
This commit is contained in:
Karim shoair
2025-10-26 16:53:27 +03:00
parent f9a514cc64
commit 13b9a4668c
6 changed files with 26 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/fetching/dynamic.md
+1
View File
@@ -89,6 +89,7 @@ Scrapling provides many options with this fetcher and its session classes. To ma
| locale | Set the locale for the browser if wanted. The default value is `en-US`. | ✔️ |
| cdp_url | Instead of launching a new browser instance, connect to this CDP URL to control real browsers through CDP. | ✔️ |
| user_data_dir | Path to a User Data Directory, which stores browser session data like cookies and local storage. The default is to create a temporary directory. **Only Works with sessions** | ✔️ |
| extra_flags | A list of additional browser flags to pass to the browser on launch. | ✔️ |
| additional_args | Additional arguments to be passed to Playwright's context as additional settings, and they take higher priority than Scrapling's settings. | ✔️ |
| selector_config | A dictionary of custom parsing arguments to be used when creating the final `Selector`/`Response` class. | ✔️ |
scrapling/engines/_browsers/_base.py
+2
View File
@@ -276,6 +276,7 @@ class DynamicSessionMixin:
self.wait_selector = config.wait_selector
self.init_script = config.init_script
self.wait_selector_state = config.wait_selector_state
self.extra_flags = config.extra_flags
self.selector_config = config.selector_config
self.additional_args = config.additional_args
self.page_action = config.page_action
@@ -300,6 +301,7 @@ class DynamicSessionMixin:
self.stealth,
self.hide_canvas,
self.disable_webgl,
tuple(self.extra_flags) if self.extra_flags else tuple(),
)
)
self.launch_options["extra_http_headers"] = dict(self.launch_options["extra_http_headers"])
scrapling/engines/_browsers/_config_tools.py
+8 -2
View File
@@ -70,12 +70,17 @@ def _launch_kwargs(
stealth,
hide_canvas,
disable_webgl,
extra_flags: Tuple,
) -> Tuple:
"""Creates the arguments we will use while launching playwright's browser"""
base_args = DEFAULT_FLAGS
if extra_flags:
base_args = base_args + extra_flags
launch_kwargs = {
"locale": locale,
"headless": headless,
"args": DEFAULT_FLAGS,
"args": base_args,
"color_scheme": "dark", # Bypasses the 'prefersLightColor' check in creepjs
"proxy": proxy or tuple(),
"device_scale_factor": 2,
@@ -85,9 +90,10 @@ def _launch_kwargs(
"user_agent": useragent or __default_useragent__,
}
if stealth:
stealth_args = base_args + _set_flags(hide_canvas, disable_webgl)
launch_kwargs.update(
{
"args": DEFAULT_FLAGS + _set_flags(hide_canvas, disable_webgl),
"args": stealth_args,
"chromium_sandbox": True,
"is_mobile": False,
"has_touch": False,
scrapling/engines/_browsers/_controllers.py
+6
View File
@@ -95,6 +95,7 @@ class DynamicSession(DynamicSessionMixin, SyncSession):
load_dom: bool = True,
wait_selector_state: SelectorWaitStates = "attached",
user_data_dir: str = "",
extra_flags: Optional[List[str]] = None,
selector_config: Optional[Dict] = None,
additional_args: Optional[Dict] = None,
):
@@ -124,6 +125,7 @@ class DynamicSession(DynamicSessionMixin, SyncSession):
:param extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._
:param proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only.
:param user_data_dir: Path to a User Data Directory, which stores browser session data like cookies and local storage. The default is to create a temporary directory.
:param extra_flags: A list of additional browser flags to pass to the browser on launch.
:param selector_config: The arguments that will be passed in the end while creating the final Selector's class.
:param additional_args: Additional arguments to be passed to Playwright's context as additional settings, and it takes higher priority than Scrapling's settings.
"""
@@ -149,6 +151,7 @@ class DynamicSession(DynamicSessionMixin, SyncSession):
extra_headers=extra_headers,
wait_selector=wait_selector,
disable_webgl=disable_webgl,
extra_flags=extra_flags,
selector_config=selector_config,
additional_args=additional_args,
disable_resources=disable_resources,
@@ -306,6 +309,7 @@ class AsyncDynamicSession(DynamicSessionMixin, AsyncSession):
load_dom: bool = True,
wait_selector_state: SelectorWaitStates = "attached",
user_data_dir: str = "",
extra_flags: Optional[List[str]] = None,
selector_config: Optional[Dict] = None,
additional_args: Optional[Dict] = None,
):
@@ -336,6 +340,7 @@ class AsyncDynamicSession(DynamicSessionMixin, AsyncSession):
:param proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only.
:param max_pages: The maximum number of tabs to be opened at the same time. It will be used in rotation through a PagePool.
:param user_data_dir: Path to a User Data Directory, which stores browser session data like cookies and local storage. The default is to create a temporary directory.
:param extra_flags: A list of additional browser flags to pass to the browser on launch.
:param selector_config: The arguments that will be passed in the end while creating the final Selector's class.
:param additional_args: Additional arguments to be passed to Playwright's context as additional settings, and it takes higher priority than Scrapling's settings.
"""
@@ -362,6 +367,7 @@ class AsyncDynamicSession(DynamicSessionMixin, AsyncSession):
extra_headers=extra_headers,
wait_selector=wait_selector,
disable_webgl=disable_webgl,
extra_flags=extra_flags,
selector_config=selector_config,
additional_args=additional_args,
disable_resources=disable_resources,
scrapling/engines/_browsers/_validators.py
+3
View File
@@ -88,6 +88,7 @@ class PlaywrightConfig(Struct, kw_only=True, frozen=False):
load_dom: bool = True
wait_selector_state: SelectorWaitStates = "attached"
user_data_dir: str = ""
extra_flags: Optional[List[str]] = None
selector_config: Optional[Dict] = {}
additional_args: Optional[Dict] = {}
@@ -102,6 +103,8 @@ class PlaywrightConfig(Struct, kw_only=True, frozen=False):
if not self.cookies:
self.cookies = []
if not self.extra_flags:
self.extra_flags = []
if not self.selector_config:
self.selector_config = {}
if not self.additional_args:
scrapling/fetchers/chrome.py
+6
View File
@@ -50,6 +50,7 @@ class DynamicFetcher(BaseFetcher):
network_idle: bool = False,
load_dom: bool = True,
wait_selector_state: SelectorWaitStates = "attached",
extra_flags: Optional[List[str]] = None,
additional_args: Optional[Dict] = None,
custom_config: Optional[Dict] = None,
) -> Response:
@@ -79,6 +80,7 @@ class DynamicFetcher(BaseFetcher):
:param google_search: Enabled by default, Scrapling will set the referer header to be as if this request came from a Google search of this website's domain name.
:param extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._
:param proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only.
:param extra_flags: A list of additional browser flags to pass to the browser on launch.
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
:param additional_args: Additional arguments to be passed to Playwright's context as additional settings, and it takes higher priority than Scrapling's settings.
:return: A `Response` object.
@@ -108,6 +110,7 @@ class DynamicFetcher(BaseFetcher):
extra_headers=extra_headers,
wait_selector=wait_selector,
disable_webgl=disable_webgl,
extra_flags=extra_flags,
additional_args=additional_args,
disable_resources=disable_resources,
wait_selector_state=wait_selector_state,
@@ -140,6 +143,7 @@ class DynamicFetcher(BaseFetcher):
network_idle: bool = False,
load_dom: bool = True,
wait_selector_state: SelectorWaitStates = "attached",
extra_flags: Optional[List[str]] = None,
additional_args: Optional[Dict] = None,
custom_config: Optional[Dict] = None,
) -> Response:
@@ -169,6 +173,7 @@ class DynamicFetcher(BaseFetcher):
:param google_search: Enabled by default, Scrapling will set the referer header to be as if this request came from a Google search of this website's domain name.
:param extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._
:param proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only.
:param extra_flags: A list of additional browser flags to pass to the browser on launch.
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values.
:param additional_args: Additional arguments to be passed to Playwright's context as additional settings, and it takes higher priority than Scrapling's settings.
:return: A `Response` object.
@@ -199,6 +204,7 @@ class DynamicFetcher(BaseFetcher):
extra_headers=extra_headers,
wait_selector=wait_selector,
disable_webgl=disable_webgl,
extra_flags=extra_flags,
additional_args=additional_args,
disable_resources=disable_resources,
wait_selector_state=wait_selector_state,