🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
Python aiai-scrapingautomationcrawlercrawlingcrawling-pythondatadata-extractionmcpmcp-serverplaywrightpythonscrapingselectorsstealthweb-scraperweb-scrapingweb-scraping-pythonwebscrapingxpath
feat(cookies): The ability to pass cookies to browser fetchers
Karim shoairbf72678480a5
diff --git a/scrapling/engines/camo.py b/scrapling/engines/camo.pyindex f3ba36b..64b690a 100644--- a/scrapling/engines/camo.py+++ b/scrapling/engines/camo.py@@ -14,6 +14,7 @@ from scrapling.core._types import (Optional,SelectorWaitStates,Union,+ Iterable,)from scrapling.core.utils import logfrom scrapling.engines.toolbelt import (@@ -45,6 +46,7 @@ class CamoufoxEngine:wait_selector: Optional[str] = None,addons: Optional[List[str]] = None,wait_selector_state: SelectorWaitStates = "attached",+ cookies: Optional[Iterable[Dict]] = None,google_search: bool = True,extra_headers: Optional[Dict[str, str]] = None,proxy: Optional[Union[str, Dict[str, str]]] = None,@@ -63,6 +65,7 @@ class CamoufoxEngine:Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.:param block_webrtc: Blocks WebRTC entirely.+ :param cookies: Set cookies for the next request.:param addons: List of Firefox addons to use. Must be paths to extracted addons.: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.:param solve_cloudflare: Solves all 3 types of the Cloudflare's Turnstile wait page before returning the response to you.@@ -97,6 +100,7 @@ class CamoufoxEngine:self.additional_arguments = additional_arguments or {}self.proxy = construct_proxy_dict(proxy)self.addons = addons or []+ self.cookies = cookies or []self.humanize = humanizeself.solve_cloudflare = solve_cloudflareself.timeout = check_type_validity(timeout, [int, float], 30_000)@@ -378,6 +382,9 @@ class CamoufoxEngine:with Camoufox(**self._get_camoufox_options()) as browser:context = browser.new_context()+ if self.cookies:+ context.add_cookies(self.cookies)+page = context.new_page()page.set_default_navigation_timeout(self.timeout)page.set_default_timeout(self.timeout)@@ -480,6 +487,9 @@ class CamoufoxEngine:async with AsyncCamoufox(**self._get_camoufox_options()) as browser:context = await browser.new_context()+ if self.cookies:+ await context.add_cookies(self.cookies)+page = await context.new_page()page.set_default_navigation_timeout(self.timeout)page.set_default_timeout(self.timeout)diff --git a/scrapling/engines/pw.py b/scrapling/engines/pw.pyindex 80b033b..d2d488e 100644--- a/scrapling/engines/pw.py+++ b/scrapling/engines/pw.py@@ -1,6 +1,13 @@import json-from scrapling.core._types import Callable, Dict, Optional, SelectorWaitStates, Union+from scrapling.core._types import (+ Callable,+ Dict,+ Optional,+ SelectorWaitStates,+ Union,+ Iterable,+)from scrapling.core.utils import log, lru_cachefrom scrapling.engines.constants import DEFAULT_STEALTH_FLAGS, NSTBROWSER_DEFAULT_QUERYfrom scrapling.engines.toolbelt import (@@ -30,6 +37,7 @@ class PlaywrightEngine:wait_selector: Optional[str] = None,locale: Optional[str] = "en-US",wait_selector_state: SelectorWaitStates = "attached",+ cookies: Optional[Iterable[Dict]] = None,stealth: bool = False,real_chrome: bool = False,hide_canvas: bool = False,@@ -49,6 +57,7 @@ class PlaywrightEngine:Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.:param useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it.+ :param cookies: Set cookies for the next request.:param network_idle: Wait for the page until there are no network connections for at least 500 ms.:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.@@ -81,6 +90,7 @@ class PlaywrightEngine:self.proxy = construct_proxy_dict(proxy)self.cdp_url = cdp_urlself.useragent = useragent+ self.cookies = cookies or []self.timeout = check_type_validity(timeout, [int, float], 30000)self.wait = check_type_validity(wait, [int, float], 0)if page_action is not None:@@ -337,6 +347,9 @@ class PlaywrightEngine:browser = p.chromium.launch(**self.__launch_kwargs())context = browser.new_context(**self.__context_kwargs())+ if self.cookies:+ context.add_cookies(self.cookies)+page = context.new_page()page.set_default_navigation_timeout(self.timeout)page.set_default_timeout(self.timeout)@@ -449,6 +462,9 @@ class PlaywrightEngine:browser = await p.chromium.launch(**self.__launch_kwargs())context = await browser.new_context(**self.__context_kwargs())+ if self.cookies:+ await context.add_cookies(self.cookies)+page = await context.new_page()page.set_default_navigation_timeout(self.timeout)page.set_default_timeout(self.timeout)diff --git a/scrapling/fetchers.py b/scrapling/fetchers.pyindex 41e5eed..bbd4b9f 100644--- a/scrapling/fetchers.py+++ b/scrapling/fetchers.py@@ -6,6 +6,7 @@ from scrapling.core._types import (Optional,SelectorWaitStates,Union,+ Iterable,)from scrapling.engines import (CamoufoxEngine,@@ -484,6 +485,7 @@ class StealthyFetcher(BaseFetcher):allow_webgl: bool = True,network_idle: bool = False,addons: Optional[List[str]] = None,+ cookies: Optional[Iterable[Dict]] = None,wait: Optional[int] = 0,timeout: Optional[float] = 30000,page_action: Callable = None,@@ -511,6 +513,7 @@ class StealthyFetcher(BaseFetcher):Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.:param block_webrtc: Blocks WebRTC entirely.+ :param cookies: Set cookies for the next request.:param addons: List of Firefox addons to use. Must be paths to extracted addons.: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.:param solve_cloudflare: Solves all 3 types of the Cloudflare's Turnstile wait page before returning the response to you.@@ -545,6 +548,7 @@ class StealthyFetcher(BaseFetcher):geoip=geoip,addons=addons,timeout=timeout,+ cookies=cookies,headless=headless,humanize=humanize,disable_ads=disable_ads,@@ -573,6 +577,7 @@ class StealthyFetcher(BaseFetcher):block_images: bool = False,disable_resources: bool = False,block_webrtc: bool = False,+ cookies: Optional[Iterable[Dict]] = None,allow_webgl: bool = True,network_idle: bool = False,addons: Optional[List[str]] = None,@@ -603,6 +608,7 @@ class StealthyFetcher(BaseFetcher):Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.:param block_webrtc: Blocks WebRTC entirely.+ :param cookies: Set cookies for the next request.:param addons: List of Firefox addons to use. Must be paths to extracted addons.: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.:param solve_cloudflare: Solves all 3 types of the Cloudflare's Turnstile wait page before returning the response to you.@@ -637,6 +643,7 @@ class StealthyFetcher(BaseFetcher):geoip=geoip,addons=addons,timeout=timeout,+ cookies=cookies,headless=headless,humanize=humanize,disable_ads=disable_ads,@@ -685,6 +692,7 @@ class PlayWrightFetcher(BaseFetcher):network_idle: bool = False,timeout: Optional[float] = 30000,wait: Optional[int] = 0,+ cookies: Optional[Iterable[Dict]] = None,page_action: Optional[Callable] = None,wait_selector: Optional[str] = None,wait_selector_state: SelectorWaitStates = "attached",@@ -712,6 +720,7 @@ class PlayWrightFetcher(BaseFetcher)::param network_idle: Wait for the page until there are no network connections for at least 500 ms.:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.+ :param cookies: Set cookies for the next request.:param page_action: Added for automation. A function that takes the `page` object, does the automation you need, then returns `page` again.:param wait_selector: Wait for a specific CSS selector to be in a specific state.:param locale: Set the locale for the browser if wanted. The default value is `en-US`.@@ -743,6 +752,7 @@ class PlayWrightFetcher(BaseFetcher):timeout=timeout,stealth=stealth,cdp_url=cdp_url,+ cookies=cookies,headless=headless,useragent=useragent,real_chrome=real_chrome,@@ -771,6 +781,7 @@ class PlayWrightFetcher(BaseFetcher):network_idle: bool = False,timeout: Optional[float] = 30000,wait: Optional[int] = 0,+ cookies: Optional[Iterable[Dict]] = None,page_action: Optional[Callable] = None,wait_selector: Optional[str] = None,wait_selector_state: SelectorWaitStates = "attached",@@ -796,6 +807,7 @@ class PlayWrightFetcher(BaseFetcher):This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.:param useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it.:param 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.:param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000:param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.:param page_action: Added for automation. A function that takes the `page` object, does the automation you need, then returns `page` again.@@ -829,6 +841,7 @@ class PlayWrightFetcher(BaseFetcher):timeout=timeout,stealth=stealth,cdp_url=cdp_url,+ cookies=cookies,headless=headless,useragent=useragent,real_chrome=real_chrome,