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

refactor(browser fetchers): Make all the type hints dynamic + Faster validation

Browse Source 
+ Also renamed `custom_config` to `selector_config` so it matches the session class.
This commit is contained in:
Karim shoair
2025-11-25 22:03:45 +02:00
parent 8940bdeb55
commit 880b144af0
2 changed files with 142 additions and 358 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scrapling/fetchers/chrome.py
+70 -176
View File
@@ -1,10 +1,5 @@
from scrapling.core._types import ( from scrapling.core._types import Unpack
Callable, from scrapling.engines._browsers._types import PlaywrightSession
List,
Dict,
Optional,
SelectorWaitStates,
)
from scrapling.engines.toolbelt.custom import BaseFetcher, Response from scrapling.engines.toolbelt.custom import BaseFetcher, Response
from scrapling.engines._browsers._controllers import DynamicSession, AsyncDynamicSession from scrapling.engines._browsers._controllers import DynamicSession, AsyncDynamicSession
@@ -26,190 +21,89 @@ class DynamicFetcher(BaseFetcher):
""" """
@classmethod @classmethod
def fetch( def fetch(cls, url: str, **kwargs: Unpack[PlaywrightSession]) -> Response:
cls,
url: str,
headless: bool = True,
google_search: bool = True,
hide_canvas: bool = False,
disable_webgl: bool = False,
real_chrome: bool = False,
stealth: bool = False,
wait: int | float = 0,
page_action: Optional[Callable] = None,
proxy: Optional[str | Dict[str, str]] = None,
locale: str = "en-US",
extra_headers: Optional[Dict[str, str]] = None,
useragent: Optional[str] = None,
cdp_url: Optional[str] = None,
timeout: int | float = 30000,
disable_resources: bool = False,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
cookies: Optional[List[Dict]] = None,
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:
"""Opens up a browser and do your request based on your chosen options below. """Opens up a browser and do your request based on your chosen options below.
:param url: Target url. :param url: Target url.
:param headless: Run the browser in headless/hidden (default), or headful/visible mode. :param kwargs: Browser session configuration options including:
:param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. - headless: Run the browser in headless/hidden (default), or headful/visible mode.
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - disable_resources: Drop requests of unnecessary resources for a speed boost.
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it.
:param useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it. - cookies: Set cookies for the next request.
:param cookies: Set cookies for the next request. - network_idle: Wait for the page until there are no network connections for at least 500 ms.
:param network_idle: Wait for the page until there are no network connections for at least 500 ms. - load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute.
:param load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute. - timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000 - wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the Response object.
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object. - page_action: Added for automation. A function that takes the `page` object and does the automation you need.
:param page_action: Added for automation. A function that takes the `page` object and does the automation you need. - wait_selector: Wait for a specific CSS selector to be in a specific state.
:param wait_selector: Wait for a specific CSS selector to be in a specific state. - init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
:param init_script: An absolute path to a JavaScript file to be executed on page creation with this request. - locale: Set the locale for the browser if wanted. The default value is `en-US`.
:param locale: Set the locale for the browser if wanted. The default value is `en-US`. - wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`. - stealth: Enables stealth mode, check the documentation to see what stealth mode does currently.
:param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently. - real_chrome: If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it.
:param real_chrome: If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it. - hide_canvas: Add random noise to canvas operations to prevent fingerprinting.
:param hide_canvas: Add random noise to canvas operations to prevent fingerprinting. - disable_webgl: Disables WebGL and WebGL 2.0 support entirely.
:param disable_webgl: Disables WebGL and WebGL 2.0 support entirely. - cdp_url: Instead of launching a new browser instance, connect to this CDP URL to control real browsers through CDP.
:param cdp_url: Instead of launching a new browser instance, connect to this CDP URL to control real browsers through CDP. - 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 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. - extra_headers: A dictionary of extra headers to add to the request.
: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._ - 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 proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only. - extra_flags: A list of additional browser flags to pass to the browser on launch.
:param extra_flags: A list of additional browser flags to pass to the browser on launch. - selector_config: The arguments that will be passed in the end while creating the final Selector's class.
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values. - additional_args: Additional arguments to be passed to Playwright's context as additional settings.
: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. :return: A `Response` object.
""" """
if not custom_config: # Get selector_config from kwargs if provided, otherwise use empty dict
custom_config = {} selector_config = kwargs.get("selector_config", {})
elif not isinstance(custom_config, dict): if not isinstance(selector_config, dict):
raise ValueError(f"The custom parser config must be of type dictionary, got {cls.__class__}") raise TypeError("Argument `selector_config` must be a dictionary.")
with DynamicSession( # Merge selector_config with class defaults
wait=wait, kwargs["selector_config"] = {**cls._generate_parser_arguments(), **selector_config}
proxy=proxy,
locale=locale, with DynamicSession(**kwargs) as session:
timeout=timeout,
stealth=stealth,
cdp_url=cdp_url,
cookies=cookies,
headless=headless,
load_dom=load_dom,
useragent=useragent,
real_chrome=real_chrome,
page_action=page_action,
hide_canvas=hide_canvas,
init_script=init_script,
network_idle=network_idle,
google_search=google_search,
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,
selector_config={**cls._generate_parser_arguments(), **custom_config},
) as session:
return session.fetch(url) return session.fetch(url)
@classmethod @classmethod
async def async_fetch( async def async_fetch(cls, url: str, **kwargs: Unpack[PlaywrightSession]) -> Response:
cls,
url: str,
headless: bool = True,
google_search: bool = True,
hide_canvas: bool = False,
disable_webgl: bool = False,
real_chrome: bool = False,
stealth: bool = False,
wait: int | float = 0,
page_action: Optional[Callable] = None,
proxy: Optional[str | Dict[str, str]] = None,
locale: str = "en-US",
extra_headers: Optional[Dict[str, str]] = None,
useragent: Optional[str] = None,
cdp_url: Optional[str] = None,
timeout: int | float = 30000,
disable_resources: bool = False,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
cookies: Optional[List[Dict]] = None,
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:
"""Opens up a browser and do your request based on your chosen options below. """Opens up a browser and do your request based on your chosen options below.
:param url: Target url. :param url: Target url.
:param headless: Run the browser in headless/hidden (default), or headful/visible mode. :param kwargs: Browser session configuration options including:
:param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. - headless: Run the browser in headless/hidden (default), or headful/visible mode.
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - disable_resources: Drop requests of unnecessary resources for a speed boost.
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it.
:param useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it. - cookies: Set cookies for the next request.
:param cookies: Set cookies for the next request. - network_idle: Wait for the page until there are no network connections for at least 500 ms.
:param network_idle: Wait for the page until there are no network connections for at least 500 ms. - load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute.
:param load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute. - timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000 - wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the Response object.
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object. - page_action: Added for automation. A function that takes the `page` object and does the automation you need.
:param page_action: Added for automation. A function that takes the `page` object and does the automation you need. - wait_selector: Wait for a specific CSS selector to be in a specific state.
:param wait_selector: Wait for a specific CSS selector to be in a specific state. - init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
:param init_script: An absolute path to a JavaScript file to be executed on page creation with this request. - locale: Set the locale for the browser if wanted. The default value is `en-US`.
:param locale: Set the locale for the browser if wanted. The default value is `en-US`. - wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`. - stealth: Enables stealth mode, check the documentation to see what stealth mode does currently.
:param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently. - real_chrome: If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it.
:param real_chrome: If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it. - hide_canvas: Add random noise to canvas operations to prevent fingerprinting.
:param hide_canvas: Add random noise to canvas operations to prevent fingerprinting. - disable_webgl: Disables WebGL and WebGL 2.0 support entirely.
:param disable_webgl: Disables WebGL and WebGL 2.0 support entirely. - cdp_url: Instead of launching a new browser instance, connect to this CDP URL to control real browsers through CDP.
:param cdp_url: Instead of launching a new browser instance, connect to this CDP URL to control real browsers through CDP. - 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 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. - extra_headers: A dictionary of extra headers to add to the request.
: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._ - 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 proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only. - extra_flags: A list of additional browser flags to pass to the browser on launch.
:param extra_flags: A list of additional browser flags to pass to the browser on launch. - selector_config: The arguments that will be passed in the end while creating the final Selector's class.
:param custom_config: A dictionary of custom parser arguments to use with this request. Any argument passed will override any class parameters values. - additional_args: Additional arguments to be passed to Playwright's context as additional settings.
: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. :return: A `Response` object.
""" """
if not custom_config: # Get selector_config from kwargs if provided, otherwise use empty dict
custom_config = {} selector_config = kwargs.get("selector_config", {})
elif not isinstance(custom_config, dict): if not isinstance(selector_config, dict):
raise ValueError(f"The custom parser config must be of type dictionary, got {cls.__class__}") raise TypeError("Argument `selector_config` must be a dictionary.")
async with AsyncDynamicSession( # Merge selector_config with class defaults
wait=wait, kwargs["selector_config"] = {**cls._generate_parser_arguments(), **selector_config}
max_pages=1,
proxy=proxy, async with AsyncDynamicSession(**kwargs) as session:
locale=locale,
timeout=timeout,
stealth=stealth,
cdp_url=cdp_url,
cookies=cookies,
headless=headless,
load_dom=load_dom,
useragent=useragent,
real_chrome=real_chrome,
page_action=page_action,
hide_canvas=hide_canvas,
init_script=init_script,
network_idle=network_idle,
google_search=google_search,
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,
selector_config={**cls._generate_parser_arguments(), **custom_config},
) as session:
return await session.fetch(url) return await session.fetch(url)
scrapling/fetchers/firefox.py
+72 -182
View File
@@ -1,10 +1,5 @@
from scrapling.core._types import ( from scrapling.core._types import Unpack
Callable, from scrapling.engines._browsers._types import CamoufoxSession
Dict,
List,
Optional,
SelectorWaitStates,
)
from scrapling.engines.toolbelt.custom import BaseFetcher, Response from scrapling.engines.toolbelt.custom import BaseFetcher, Response
from scrapling.engines._browsers._camoufox import StealthySession, AsyncStealthySession from scrapling.engines._browsers._camoufox import StealthySession, AsyncStealthySession
@@ -17,196 +12,91 @@ class StealthyFetcher(BaseFetcher):
""" """
@classmethod @classmethod
def fetch( def fetch(cls, url: str, **kwargs: Unpack[CamoufoxSession]) -> Response:
cls,
url: str,
headless: bool = True, # noqa: F821
block_images: bool = False,
disable_resources: bool = False,
block_webrtc: bool = False,
allow_webgl: bool = True,
network_idle: bool = False,
load_dom: bool = True,
humanize: bool | float = True,
solve_cloudflare: bool = False,
wait: int | float = 0,
timeout: int | float = 30000,
page_action: Optional[Callable] = None,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
addons: Optional[List[str]] = None,
wait_selector_state: SelectorWaitStates = "attached",
cookies: Optional[List[Dict]] = None,
google_search: bool = True,
extra_headers: Optional[Dict[str, str]] = None,
proxy: Optional[str | Dict[str, str]] = None,
os_randomize: bool = False,
disable_ads: bool = False,
geoip: bool = False,
custom_config: Optional[Dict] = None,
additional_args: Optional[Dict] = None,
) -> Response:
""" """
Opens up a browser and do your request based on your chosen options below. Opens up a browser and do your request based on your chosen options below.
:param url: Target url. :param url: Target url.
:param headless: Run the browser in headless/hidden (default), or headful/visible mode. :param kwargs: Browser session configuration options including:
:param block_images: Prevent the loading of images through Firefox preferences. - headless: Run the browser in headless/hidden (default), or headful/visible mode.
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - block_images: Prevent the loading of images through Firefox preferences.
:param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. - disable_resources: Drop requests of unnecessary resources for a speed boost.
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - block_webrtc: Blocks WebRTC entirely.
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - allow_webgl: Enabled by default. Disabling WebGL is not recommended as many WAFs now check if WebGL is enabled.
:param block_webrtc: Blocks WebRTC entirely. - network_idle: Wait for the page until there are no network connections for at least 500 ms.
:param cookies: Set cookies for the next request. - load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute.
:param addons: List of Firefox addons to use. Must be paths to extracted addons. - humanize: Humanize the cursor movement. Takes either True or the MAX duration in seconds of the cursor movement.
:param humanize: Humanize the cursor movement. Takes either True or the MAX duration in seconds of the cursor movement. The cursor typically takes up to 1.5 seconds to move across the window. - solve_cloudflare: Solves all types of the Cloudflare's Turnstile/Interstitial challenges before returning the response to you.
:param solve_cloudflare: Solves all types of the Cloudflare's Turnstile/Interstitial challenges before returning the response to you. - wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the Response object.
:param allow_webgl: Enabled by default. Disabling WebGL is not recommended as many WAFs now check if WebGL is enabled. - timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
:param network_idle: Wait for the page until there are no network connections for at least 500 ms. - page_action: Added for automation. A function that takes the `page` object and does the automation you need.
:param load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute. - wait_selector: Wait for a specific CSS selector to be in a specific state.
:param disable_ads: Disabled by default, this installs the `uBlock Origin` addon on the browser if enabled. - init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
:param os_randomize: If enabled, Scrapling will randomize the OS fingerprints used. The default is Scrapling matching the fingerprints with the current OS. - addons: List of Firefox addons to use. Must be paths to extracted addons.
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object. - wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000 - cookies: Set cookies for the next request.
:param page_action: Added for automation. A function that takes the `page` object and does the automation you need. - 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 wait_selector: Wait for a specific CSS selector to be in a specific state. - extra_headers: A dictionary of extra headers to add to the request.
:param init_script: An absolute path to a JavaScript file to be executed on page creation with this request. - 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 geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and spoof the WebRTC IP address. - os_randomize: If enabled, Scrapling will randomize the OS fingerprints used.
It will also calculate and spoof the browser's language based on the distribution of language speakers in the target region. - disable_ads: Disabled by default, this installs the `uBlock Origin` addon on the browser if enabled.
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`. - geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and spoof the WebRTC IP address.
: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. - selector_config: The arguments that will be passed in the end while creating the final Selector's class.
: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._ - additional_args: Additional arguments to be passed to Camoufox as additional settings.
: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 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 Camoufox as additional settings, and it takes higher priority than Scrapling's settings.
:return: A `Response` object. :return: A `Response` object.
""" """
if not custom_config: # Get selector_config from kwargs if provided, otherwise use empty dict
custom_config = {} selector_config = kwargs.get("selector_config", {})
if not isinstance(selector_config, dict):
raise TypeError("Argument `selector_config` must be a dictionary.")
with StealthySession( # Merge selector_config with class defaults
wait=wait, kwargs["selector_config"] = {**cls._generate_parser_arguments(), **selector_config}
proxy=proxy,
geoip=geoip, with StealthySession(**kwargs) as engine:
addons=addons,
timeout=timeout,
cookies=cookies,
headless=headless,
humanize=humanize,
load_dom=load_dom,
disable_ads=disable_ads,
allow_webgl=allow_webgl,
page_action=page_action,
init_script=init_script,
network_idle=network_idle,
block_images=block_images,
block_webrtc=block_webrtc,
os_randomize=os_randomize,
wait_selector=wait_selector,
google_search=google_search,
extra_headers=extra_headers,
solve_cloudflare=solve_cloudflare,
disable_resources=disable_resources,
wait_selector_state=wait_selector_state,
selector_config={**cls._generate_parser_arguments(), **custom_config},
additional_args=additional_args or {},
) as engine:
return engine.fetch(url) return engine.fetch(url)
@classmethod @classmethod
async def async_fetch( async def async_fetch(cls, url: str, **kwargs: Unpack[CamoufoxSession]) -> Response:
cls,
url: str,
headless: bool = True, # noqa: F821
block_images: bool = False,
disable_resources: bool = False,
block_webrtc: bool = False,
allow_webgl: bool = True,
network_idle: bool = False,
load_dom: bool = True,
humanize: bool | float = True,
solve_cloudflare: bool = False,
wait: int | float = 0,
timeout: int | float = 30000,
page_action: Optional[Callable] = None,
wait_selector: Optional[str] = None,
init_script: Optional[str] = None,
addons: Optional[List[str]] = None,
wait_selector_state: SelectorWaitStates = "attached",
cookies: Optional[List[Dict]] = None,
google_search: bool = True,
extra_headers: Optional[Dict[str, str]] = None,
proxy: Optional[str | Dict[str, str]] = None,
os_randomize: bool = False,
disable_ads: bool = False,
geoip: bool = False,
custom_config: Optional[Dict] = None,
additional_args: Optional[Dict] = None,
) -> Response:
""" """
Opens up a browser and do your request based on your chosen options below. Opens up a browser and do your request based on your chosen options below.
:param url: Target url. :param url: Target url.
:param headless: Run the browser in headless/hidden (default), or headful/visible mode. :param kwargs: Browser session configuration options including:
:param block_images: Prevent the loading of images through Firefox preferences. - headless: Run the browser in headless/hidden (default), or headful/visible mode.
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - block_images: Prevent the loading of images through Firefox preferences.
:param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. - disable_resources: Drop requests of unnecessary resources for a speed boost.
Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - block_webrtc: Blocks WebRTC entirely.
This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - allow_webgl: Enabled by default. Disabling WebGL is not recommended as many WAFs now check if WebGL is enabled.
:param block_webrtc: Blocks WebRTC entirely. - network_idle: Wait for the page until there are no network connections for at least 500 ms.
:param cookies: Set cookies for the next request. - load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute.
:param addons: List of Firefox addons to use. Must be paths to extracted addons. - humanize: Humanize the cursor movement. Takes either True or the MAX duration in seconds of the cursor movement.
:param humanize: Humanize the cursor movement. Takes either True or the MAX duration in seconds of the cursor movement. The cursor typically takes up to 1.5 seconds to move across the window. - solve_cloudflare: Solves all types of the Cloudflare's Turnstile/Interstitial challenges before returning the response to you.
:param solve_cloudflare: Solves all types of the Cloudflare's Turnstile/Interstitial challenges before returning the response to you. - wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the Response object.
:param allow_webgl: Enabled by default. Disabling WebGL is not recommended as many WAFs now check if WebGL is enabled. - timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
:param network_idle: Wait for the page until there are no network connections for at least 500 ms. - page_action: Added for automation. A function that takes the `page` object and does the automation you need.
:param load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute. - wait_selector: Wait for a specific CSS selector to be in a specific state.
:param disable_ads: Disabled by default, this installs the `uBlock Origin` addon on the browser if enabled. - init_script: An absolute path to a JavaScript file to be executed on page creation with this request.
:param os_randomize: If enabled, Scrapling will randomize the OS fingerprints used. The default is Scrapling matching the fingerprints with the current OS. - addons: List of Firefox addons to use. Must be paths to extracted addons.
:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object. - wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000 - cookies: Set cookies for the next request.
:param page_action: Added for automation. A function that takes the `page` object and does the automation you need. - 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 wait_selector: Wait for a specific CSS selector to be in a specific state. - extra_headers: A dictionary of extra headers to add to the request.
:param init_script: An absolute path to a JavaScript file to be executed on page creation with this request. - 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 geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and spoof the WebRTC IP address. - os_randomize: If enabled, Scrapling will randomize the OS fingerprints used.
It will also calculate and spoof the browser's language based on the distribution of language speakers in the target region. - disable_ads: Disabled by default, this installs the `uBlock Origin` addon on the browser if enabled.
:param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`. - geoip: Recommended to use with proxies; Automatically use IP's longitude, latitude, timezone, country, locale, and spoof the WebRTC IP address.
: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. - selector_config: The arguments that will be passed in the end while creating the final Selector's class.
: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._ - additional_args: Additional arguments to be passed to Camoufox as additional settings.
: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 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 Camoufox as additional settings, and it takes higher priority than Scrapling's settings.
:return: A `Response` object. :return: A `Response` object.
""" """
if not custom_config: # Get selector_config from kwargs if provided, otherwise use empty dict
custom_config = {} selector_config = kwargs.get("selector_config", {})
if not isinstance(selector_config, dict):
raise TypeError("Argument `selector_config` must be a dictionary.")
async with AsyncStealthySession( # Merge selector_config with class defaults
wait=wait, kwargs["selector_config"] = {**cls._generate_parser_arguments(), **selector_config}
max_pages=1,
proxy=proxy, async with AsyncStealthySession(**kwargs) as engine:
geoip=geoip,
addons=addons,
timeout=timeout,
cookies=cookies,
headless=headless,
humanize=humanize,
load_dom=load_dom,
disable_ads=disable_ads,
allow_webgl=allow_webgl,
page_action=page_action,
init_script=init_script,
network_idle=network_idle,
block_images=block_images,
block_webrtc=block_webrtc,
os_randomize=os_randomize,
wait_selector=wait_selector,
google_search=google_search,
extra_headers=extra_headers,
solve_cloudflare=solve_cloudflare,
disable_resources=disable_resources,
wait_selector_state=wait_selector_state,
selector_config={**cls._generate_parser_arguments(), **custom_config},
additional_args=additional_args or {},
) as engine:
return await engine.fetch(url) return await engine.fetch(url)