scrapling 0.2.9__py3-none-any.whl → 0.2.91__py3-none-any.whl

scrapling/__init__.py

@@ -5,7 +5,7 @@ from scrapling.fetchers import (AsyncFetcher, CustomFetcher, Fetcher,
 from scrapling.parser import Adaptor, Adaptors
 
 __author__ = "Karim Shoair (karim.shoair@pm.me)"
-__version__ = "0.2.9"
+__version__ = "0.2.91"
 __copyright__ = "Copyright (c) 2024 Karim Shoair"
 
 

scrapling/core/_types.py

@@ -5,6 +5,8 @@ Type definitions for type checking purposes.
 from typing import (TYPE_CHECKING, Any, Callable, Dict, Generator, Iterable,
                     List, Literal, Optional, Pattern, Tuple, Type, Union)
 
+SelectorWaitStates = Literal["attached", "detached", "hidden", "visible"]
+
 try:
     from typing import Protocol
 except ImportError:

scrapling/engines/camo.py

@@ -3,7 +3,7 @@ from camoufox.async_api import AsyncCamoufox
 from camoufox.sync_api import Camoufox
 
 from scrapling.core._types import (Callable, Dict, List, Literal, Optional,
-                                   Union)
+                                   SelectorWaitStates, Union)
 from scrapling.core.utils import log
 from scrapling.engines.toolbelt import (Response, StatusText,
                                         async_intercept_route,
@@ -18,7 +18,7 @@ class CamoufoxEngine:
             self, headless: Optional[Union[bool, Literal['virtual']]] = True, block_images: Optional[bool] = False, disable_resources: Optional[bool] = False,
             block_webrtc: Optional[bool] = False, allow_webgl: Optional[bool] = True, network_idle: Optional[bool] = False, humanize: Optional[Union[bool, float]] = True,
             timeout: Optional[float] = 30000, page_action: Callable = None, wait_selector: Optional[str] = None, addons: Optional[List[str]] = None,
-            wait_selector_state: str = 'attached', google_search: Optional[bool] = True, extra_headers: Optional[Dict[str, str]] = None,
+            wait_selector_state: Optional[SelectorWaitStates] = 'attached', google_search: Optional[bool] = True, extra_headers: Optional[Dict[str, str]] = None,
             proxy: Optional[Union[str, Dict[str, str]]] = None, os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = True,
             geoip: Optional[bool] = False,
             adaptor_arguments: Dict = None,
@@ -84,6 +84,14 @@ class CamoufoxEngine:
         :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
         """
         addons = [] if self.disable_ads else [DefaultAddons.UBO]
+        # Store the final response
+        final_response = None
+
+        def handle_response(finished_response):
+            nonlocal final_response
+            if finished_response.request.resource_type == "document":
+                final_response = finished_response
+
         with Camoufox(
                 geoip=self.geoip,
                 proxy=self.proxy,
@@ -100,13 +108,15 @@ class CamoufoxEngine:
             page = browser.new_page()
             page.set_default_navigation_timeout(self.timeout)
             page.set_default_timeout(self.timeout)
+            # Listen for all responses
+            page.on("response", handle_response)
             if self.disable_resources:
                 page.route("**/*", intercept_route)
 
             if self.extra_headers:
                 page.set_extra_http_headers(self.extra_headers)
 
-            res = page.goto(url, referer=generate_convincing_referer(url) if self.google_search else None)
+            first_response = page.goto(url, referer=generate_convincing_referer(url) if self.google_search else None)
             page.wait_for_load_state(state="domcontentloaded")
             if self.network_idle:
                 page.wait_for_load_state('networkidle')
@@ -123,21 +133,24 @@ class CamoufoxEngine:
                 if self.network_idle:
                     page.wait_for_load_state('networkidle')
 
+            response_bytes = final_response.body() if final_response else page.content().encode('utf-8')
+            # In case we didn't catch a document type somehow
+            final_response = final_response if final_response else first_response
             # This will be parsed inside `Response`
-            encoding = res.headers.get('content-type', '') or 'utf-8'  # default encoding
+            encoding = final_response.headers.get('content-type', '') or 'utf-8'  # default encoding
             # PlayWright API sometimes give empty status text for some reason!
-            status_text = res.status_text or StatusText.get(res.status)
+            status_text = final_response.status_text or StatusText.get(final_response.status)
 
             response = Response(
-                url=res.url,
+                url=final_response.url,
                 text=page.content(),
-                body=page.content().encode('utf-8'),
-                status=res.status,
+                body=response_bytes,
+                status=final_response.status,
                 reason=status_text,
                 encoding=encoding,
                 cookies={cookie['name']: cookie['value'] for cookie in page.context.cookies()},
-                headers=res.all_headers(),
-                request_headers=res.request.all_headers(),
+                headers=final_response.all_headers(),
+                request_headers=final_response.request.all_headers(),
                 **self.adaptor_arguments
             )
             page.close()
@@ -151,6 +164,14 @@ class CamoufoxEngine:
         :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
         """
         addons = [] if self.disable_ads else [DefaultAddons.UBO]
+        # Store the final response
+        final_response = None
+
+        async def handle_response(finished_response):
+            nonlocal final_response
+            if finished_response.request.resource_type == "document":
+                final_response = finished_response
+
         async with AsyncCamoufox(
                 geoip=self.geoip,
                 proxy=self.proxy,
@@ -167,13 +188,15 @@ class CamoufoxEngine:
             page = await browser.new_page()
             page.set_default_navigation_timeout(self.timeout)
             page.set_default_timeout(self.timeout)
+            # Listen for all responses
+            page.on("response", handle_response)
             if self.disable_resources:
                 await page.route("**/*", async_intercept_route)
 
             if self.extra_headers:
                 await page.set_extra_http_headers(self.extra_headers)
 
-            res = await page.goto(url, referer=generate_convincing_referer(url) if self.google_search else None)
+            first_response = await page.goto(url, referer=generate_convincing_referer(url) if self.google_search else None)
             await page.wait_for_load_state(state="domcontentloaded")
             if self.network_idle:
                 await page.wait_for_load_state('networkidle')
@@ -190,21 +213,24 @@ class CamoufoxEngine:
                 if self.network_idle:
                     await page.wait_for_load_state('networkidle')
 
+            response_bytes = await final_response.body() if final_response else (await page.content()).encode('utf-8')
+            # In case we didn't catch a document type somehow
+            final_response = final_response if final_response else first_response
             # This will be parsed inside `Response`
-            encoding = res.headers.get('content-type', '') or 'utf-8'  # default encoding
+            encoding = final_response.headers.get('content-type', '') or 'utf-8'  # default encoding
             # PlayWright API sometimes give empty status text for some reason!
-            status_text = res.status_text or StatusText.get(res.status)
+            status_text = final_response.status_text or StatusText.get(final_response.status)
 
             response = Response(
-                url=res.url,
+                url=final_response.url,
                 text=await page.content(),
-                body=(await page.content()).encode('utf-8'),
-                status=res.status,
+                body=response_bytes,
+                status=final_response.status,
                 reason=status_text,
                 encoding=encoding,
                 cookies={cookie['name']: cookie['value'] for cookie in await page.context.cookies()},
-                headers=await res.all_headers(),
-                request_headers=await res.request.all_headers(),
+                headers=await final_response.all_headers(),
+                request_headers=await final_response.request.all_headers(),
                 **self.adaptor_arguments
             )
             await page.close()

scrapling/engines/pw.py

@@ -1,6 +1,7 @@
 import json
 
-from scrapling.core._types import Callable, Dict, Optional, Union
+from scrapling.core._types import (Callable, Dict, Optional,
+                                   SelectorWaitStates, Union)
 from scrapling.core.utils import log, lru_cache
 from scrapling.engines.constants import (DEFAULT_STEALTH_FLAGS,
                                          NSTBROWSER_DEFAULT_QUERY)
@@ -23,7 +24,7 @@ class PlaywrightEngine:
             page_action: Callable = None,
             wait_selector: Optional[str] = None,
             locale: Optional[str] = 'en-US',
-            wait_selector_state: Optional[str] = 'attached',
+            wait_selector_state: SelectorWaitStates = 'attached',
             stealth: Optional[bool] = False,
             real_chrome: Optional[bool] = False,
             hide_canvas: Optional[bool] = False,
@@ -193,12 +194,21 @@ class PlaywrightEngine:
         :param url: Target url.
         :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
         """
+        from playwright.sync_api import Response as PlaywrightResponse
         if not self.stealth or self.real_chrome:
             # Because rebrowser_playwright doesn't play well with real browsers
             from playwright.sync_api import sync_playwright
         else:
             from rebrowser_playwright.sync_api import sync_playwright
 
+        # Store the final response
+        final_response = None
+
+        def handle_response(finished_response: PlaywrightResponse):
+            nonlocal final_response
+            if finished_response.request.resource_type == "document":
+                final_response = finished_response
+
         with sync_playwright() as p:
             # Creating the browser
             if self.cdp_url:
@@ -212,6 +222,8 @@ class PlaywrightEngine:
             page = context.new_page()
             page.set_default_navigation_timeout(self.timeout)
             page.set_default_timeout(self.timeout)
+            # Listen for all responses
+            page.on("response", handle_response)
 
             if self.extra_headers:
                 page.set_extra_http_headers(self.extra_headers)
@@ -223,7 +235,7 @@ class PlaywrightEngine:
                 for script in self.__stealth_scripts():
                     page.add_init_script(path=script)
 
-            res = page.goto(url, referer=generate_convincing_referer(url) if self.google_search else None)
+            first_response = page.goto(url, referer=generate_convincing_referer(url) if self.google_search else None)
             page.wait_for_load_state(state="domcontentloaded")
             if self.network_idle:
                 page.wait_for_load_state('networkidle')
@@ -240,21 +252,24 @@ class PlaywrightEngine:
                 if self.network_idle:
                     page.wait_for_load_state('networkidle')
 
+            response_bytes = final_response.body() if final_response else page.content().encode('utf-8')
+            # In case we didn't catch a document type somehow
+            final_response = final_response if final_response else first_response
             # This will be parsed inside `Response`
-            encoding = res.headers.get('content-type', '') or 'utf-8'  # default encoding
+            encoding = final_response.headers.get('content-type', '') or 'utf-8'  # default encoding
             # PlayWright API sometimes give empty status text for some reason!
-            status_text = res.status_text or StatusText.get(res.status)
+            status_text = final_response.status_text or StatusText.get(final_response.status)
 
             response = Response(
-                url=res.url,
+                url=final_response.url,
                 text=page.content(),
-                body=page.content().encode('utf-8'),
-                status=res.status,
+                body=response_bytes,
+                status=final_response.status,
                 reason=status_text,
                 encoding=encoding,
                 cookies={cookie['name']: cookie['value'] for cookie in page.context.cookies()},
-                headers=res.all_headers(),
-                request_headers=res.request.all_headers(),
+                headers=final_response.all_headers(),
+                request_headers=final_response.request.all_headers(),
                 **self.adaptor_arguments
             )
             page.close()
@@ -266,12 +281,21 @@ class PlaywrightEngine:
         :param url: Target url.
         :return: A `Response` object that is the same as `Adaptor` object except it has these added attributes: `status`, `reason`, `cookies`, `headers`, and `request_headers`
         """
+        from playwright.async_api import Response as PlaywrightResponse
         if not self.stealth or self.real_chrome:
             # Because rebrowser_playwright doesn't play well with real browsers
             from playwright.async_api import async_playwright
         else:
             from rebrowser_playwright.async_api import async_playwright
 
+        # Store the final response
+        final_response = None
+
+        async def handle_response(finished_response: PlaywrightResponse):
+            nonlocal final_response
+            if finished_response.request.resource_type == "document":
+                final_response = finished_response
+
         async with async_playwright() as p:
             # Creating the browser
             if self.cdp_url:
@@ -285,6 +309,8 @@ class PlaywrightEngine:
             page = await context.new_page()
             page.set_default_navigation_timeout(self.timeout)
             page.set_default_timeout(self.timeout)
+            # Listen for all responses
+            page.on("response", handle_response)
 
             if self.extra_headers:
                 await page.set_extra_http_headers(self.extra_headers)
@@ -296,7 +322,7 @@ class PlaywrightEngine:
                 for script in self.__stealth_scripts():
                     await page.add_init_script(path=script)
 
-            res = await page.goto(url, referer=generate_convincing_referer(url) if self.google_search else None)
+            first_response = await page.goto(url, referer=generate_convincing_referer(url) if self.google_search else None)
             await page.wait_for_load_state(state="domcontentloaded")
             if self.network_idle:
                 await page.wait_for_load_state('networkidle')
@@ -313,21 +339,24 @@ class PlaywrightEngine:
                 if self.network_idle:
                     await page.wait_for_load_state('networkidle')
 
+            response_bytes = await final_response.body() if final_response else (await page.content()).encode('utf-8')
+            # In case we didn't catch a document type somehow
+            final_response = final_response if final_response else first_response
             # This will be parsed inside `Response`
-            encoding = res.headers.get('content-type', '') or 'utf-8'  # default encoding
+            encoding = final_response.headers.get('content-type', '') or 'utf-8'  # default encoding
             # PlayWright API sometimes give empty status text for some reason!
-            status_text = res.status_text or StatusText.get(res.status)
+            status_text = final_response.status_text or StatusText.get(final_response.status)
 
             response = Response(
-                url=res.url,
+                url=final_response.url,
                 text=await page.content(),
-                body=(await page.content()).encode('utf-8'),
-                status=res.status,
+                body=response_bytes,
+                status=final_response.status,
                 reason=status_text,
                 encoding=encoding,
                 cookies={cookie['name']: cookie['value'] for cookie in await page.context.cookies()},
-                headers=await res.all_headers(),
-                request_headers=await res.request.all_headers(),
+                headers=await final_response.all_headers(),
+                request_headers=await final_response.request.all_headers(),
                 **self.adaptor_arguments
             )
             await page.close()

scrapling/engines/toolbelt/custom.py

@@ -84,8 +84,6 @@ class ResponseEncoding:
 class Response(Adaptor):
     """This class is returned by all engines as a way to unify response type between different libraries."""
 
-    _is_response_result_logged = False  # Class-level flag, initialized to False
-
     def __init__(self, url: str, text: str, body: bytes, status: int, reason: str, cookies: Dict, headers: Dict, request_headers: Dict,
                  encoding: str = 'utf-8', method: str = 'GET', **adaptor_arguments: Dict):
         automatch_domain = adaptor_arguments.pop('automatch_domain', None)
@@ -99,9 +97,7 @@ class Response(Adaptor):
         # For back-ward compatibility
         self.adaptor = self
         # For easier debugging while working from a Python shell
-        if not Response._is_response_result_logged:
-            log.info(f'Fetched ({status}) <{method} {url}> (referer: {request_headers.get("referer")})')
-            Response._is_response_result_logged = True
+        log.info(f'Fetched ({status}) <{method} {url}> (referer: {request_headers.get("referer")})')
 
     # def __repr__(self):
     #     return f'<{self.__class__.__name__} [{self.status} {self.reason}]>'

scrapling/fetchers.py

@@ -1,5 +1,5 @@
 from scrapling.core._types import (Callable, Dict, List, Literal, Optional,
-                                   Union)
+                                   SelectorWaitStates, Union)
 from scrapling.engines import (CamoufoxEngine, PlaywrightEngine, StaticEngine,
                                check_if_engine_usable)
 from scrapling.engines.toolbelt import BaseFetcher, Response
@@ -176,8 +176,8 @@ class StealthyFetcher(BaseFetcher):
             self, url: str, headless: Optional[Union[bool, Literal['virtual']]] = True, block_images: Optional[bool] = False, disable_resources: Optional[bool] = False,
             block_webrtc: Optional[bool] = False, allow_webgl: Optional[bool] = True, network_idle: Optional[bool] = False, addons: Optional[List[str]] = None,
             timeout: Optional[float] = 30000, page_action: Callable = None, wait_selector: Optional[str] = None, humanize: Optional[Union[bool, float]] = True,
-            wait_selector_state: str = 'attached', google_search: Optional[bool] = True, extra_headers: Optional[Dict[str, str]] = None, proxy: Optional[Union[str, Dict[str, str]]] = None,
-            os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = True, geoip: Optional[bool] = False,
+            wait_selector_state: SelectorWaitStates = 'attached', google_search: Optional[bool] = True, extra_headers: Optional[Dict[str, str]] = None,
+            proxy: Optional[Union[str, Dict[str, str]]] = None, os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = True, geoip: Optional[bool] = False,
     ) -> Response:
         """
         Opens up a browser and do your request based on your chosen options below.
@@ -234,8 +234,8 @@ class StealthyFetcher(BaseFetcher):
             self, url: str, headless: Optional[Union[bool, Literal['virtual']]] = True, block_images: Optional[bool] = False, disable_resources: Optional[bool] = False,
             block_webrtc: Optional[bool] = False, allow_webgl: Optional[bool] = True, network_idle: Optional[bool] = False, addons: Optional[List[str]] = None,
             timeout: Optional[float] = 30000, page_action: Callable = None, wait_selector: Optional[str] = None, humanize: Optional[Union[bool, float]] = True,
-            wait_selector_state: str = 'attached', google_search: Optional[bool] = True, extra_headers: Optional[Dict[str, str]] = None, proxy: Optional[Union[str, Dict[str, str]]] = None,
-            os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = True, geoip: Optional[bool] = False,
+            wait_selector_state: SelectorWaitStates = 'attached', google_search: Optional[bool] = True, extra_headers: Optional[Dict[str, str]] = None,
+            proxy: Optional[Union[str, Dict[str, str]]] = None, os_randomize: Optional[bool] = None, disable_ads: Optional[bool] = True, geoip: Optional[bool] = False,
     ) -> Response:
         """
         Opens up a browser and do your request based on your chosen options below.
@@ -308,7 +308,7 @@ class PlayWrightFetcher(BaseFetcher):
     def fetch(
             self, url: str, headless: Union[bool, str] = True, disable_resources: bool = None,
             useragent: Optional[str] = None, network_idle: Optional[bool] = False, timeout: Optional[float] = 30000,
-            page_action: Optional[Callable] = None, wait_selector: Optional[str] = None, wait_selector_state: Optional[str] = 'attached',
+            page_action: Optional[Callable] = None, wait_selector: Optional[str] = None, wait_selector_state: SelectorWaitStates = 'attached',
             hide_canvas: Optional[bool] = False, disable_webgl: Optional[bool] = False, extra_headers: Optional[Dict[str, str]] = None, google_search: Optional[bool] = True,
             proxy: Optional[Union[str, Dict[str, str]]] = None, locale: Optional[str] = 'en-US',
             stealth: Optional[bool] = False, real_chrome: Optional[bool] = False,
@@ -368,7 +368,7 @@ class PlayWrightFetcher(BaseFetcher):
     async def async_fetch(
             self, url: str, headless: Union[bool, str] = True, disable_resources: bool = None,
             useragent: Optional[str] = None, network_idle: Optional[bool] = False, timeout: Optional[float] = 30000,
-            page_action: Optional[Callable] = None, wait_selector: Optional[str] = None, wait_selector_state: Optional[str] = 'attached',
+            page_action: Optional[Callable] = None, wait_selector: Optional[str] = None, wait_selector_state: SelectorWaitStates = 'attached',
             hide_canvas: Optional[bool] = False, disable_webgl: Optional[bool] = False, extra_headers: Optional[Dict[str, str]] = None, google_search: Optional[bool] = True,
             proxy: Optional[Union[str, Dict[str, str]]] = None, locale: Optional[str] = 'en-US',
             stealth: Optional[bool] = False, real_chrome: Optional[bool] = False,

scrapling/parser.py

@@ -155,7 +155,7 @@ class Adaptor(SelectorsGeneration):
         else:
             if issubclass(type(element), html.HtmlMixin):
 
-                return self.__class__(
+                return Adaptor(
                     root=element,
                     text='', body=b'',  # Since root argument is provided, both `text` and `body` will be ignored so this is just a filler
                     url=self.url, encoding=self.encoding, auto_match=self.__auto_match_enabled,

{scrapling-0.2.9.dist-info → scrapling-0.2.91.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: scrapling
-Version: 0.2.9
+Version: 0.2.91
 Summary: Scrapling is a powerful, flexible, and high-performance web scraping library for Python. It
 Home-page: https://github.com/D4Vinci/Scrapling
 Author: Karim Shoair
@@ -21,7 +21,6 @@ Classifier: Topic :: Text Processing :: Markup :: HTML
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
@@ -38,7 +37,7 @@ Requires-Dist: cssselect>=1.2
 Requires-Dist: w3lib
 Requires-Dist: orjson>=3
 Requires-Dist: tldextract
-Requires-Dist: httpx[brotli,zstd]
+Requires-Dist: httpx[brotli,socks,zstd]
 Requires-Dist: playwright>=1.49.1
 Requires-Dist: rebrowser-playwright>=1.49.1
 Requires-Dist: camoufox[geoip]>=0.4.9

{scrapling-0.2.9.dist-info → scrapling-0.2.91.dist-info}/RECORD

@@ -1,22 +1,22 @@
-scrapling/__init__.py,sha256=4adit4xM1Io6mBz-VnnSHcPCQxIYhvDmDVMhbXu8VF4,499
+scrapling/__init__.py,sha256=pfbhEm1kcriA9pFR3JUUFEE3v4_ykB35SYbeHKzFxHw,500
 scrapling/defaults.py,sha256=tJAOMB-PMd3aLZz3j_yr6haBxxaklAvWdS_hP-GFFdU,331
-scrapling/fetchers.py,sha256=I_N32DMjCzNCMmrkGYoX480x1Eh5Lka6cMJ-EcSfszk,35342
-scrapling/parser.py,sha256=NKwOsGR6TB7XC9lMkA418_DRWE6pyUqK0XtmTAA51ic,55215
+scrapling/fetchers.py,sha256=K3MKBqKDOXItJNwxFY2fe1C21Vz6QSd91fFtN98Mpg4,35402
+scrapling/parser.py,sha256=Fl9cdbR58GuoPbWN5hZI6ToPSl0_rQFXMskTdzpoxWs,55208
 scrapling/py.typed,sha256=frcCV1k9oG9oKj3dpUqdJg1PxRT2RSN_XKdLCPjaYaY,2
 scrapling/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-scrapling/core/_types.py,sha256=__HJ2JTk5vx5eg_7HAJmDjaHrMDIaoxNG8fadLLyKV8,566
+scrapling/core/_types.py,sha256=OcsP1WeQEOlEVo9OzTrLQfgZZfXuJ0civVs31SynwGA,641
 scrapling/core/custom_types.py,sha256=ZRzpoT6qQ4vU_ejhLXa7WYuYLGl5HwAjLPe01xdhuvM,10808
 scrapling/core/mixins.py,sha256=sozbpaGL1_O_x3U-ABM5aYWpnxpCLfdbcA9SG3P7weY,3532
 scrapling/core/storage_adaptors.py,sha256=l_ZYcdn1y69AcoPuRrPoaxqKysN62pMExrwJWYdu5MA,6220
 scrapling/core/translator.py,sha256=ojDmNi5pFZE6Ke-AiSsTilXiPRdR8yhX3o-uVGMkap8,5236
 scrapling/core/utils.py,sha256=03LzCDzmeK1TXPjIKVzHSUgSfhpe36XE8AwxlgxzJoU,3705
 scrapling/engines/__init__.py,sha256=zA7tzqcDXP0hllwmjVewNHWipIA4JSU9mRG4J-cud0c,267
-scrapling/engines/camo.py,sha256=L5jRNUgJSAY5hE8KCD-tz4SFrx7ZjowJoWpHrl7havI,12359
+scrapling/engines/camo.py,sha256=g12IVIPy4Uyp_jngtu8Qcvy7PSMHjURAHUGXdM58Kks,13778
 scrapling/engines/constants.py,sha256=Gb_nXFoBB4ujJkd05SKkenMe1UDiRYQA3dkmA3DunLg,3723
-scrapling/engines/pw.py,sha256=0vCDaodve_WcOdbGqBdyRwMECPZmQ0eGLQikh4WHKFc,17011
+scrapling/engines/pw.py,sha256=Eq4_oQA5eX666chiNpXsBqhWONzleniyXjKdmCpXj_Y,18630
 scrapling/engines/static.py,sha256=7SVEfeigCPfwC1ukx0zIFFe96Bo5fox6qOq2IWrP6P8,10319
 scrapling/engines/toolbelt/__init__.py,sha256=VQDdYm1zY9Apno6d8UrULk29vUjllZrQqD8mXL1E2Fc,402
-scrapling/engines/toolbelt/custom.py,sha256=FbWTUC0Z8NTmTLFDiiCchs4W0_Q40lz2ONnhInRNuvA,12947
+scrapling/engines/toolbelt/custom.py,sha256=d3qyeCg_qHm1RRE7yv5hyU9b17Y7YDPGBOVhEH1CAT0,12754
 scrapling/engines/toolbelt/fingerprints.py,sha256=ajEHdXHr7W4hw9KcNS7XlyxNBZu37p1bRj18TiICLzU,2929
 scrapling/engines/toolbelt/navigation.py,sha256=xEfZRJefuxOCGxQOSI2llS0du0Y2XmoIPdVGUSHOd7k,4567
 scrapling/engines/toolbelt/bypasses/navigator_plugins.js,sha256=tbnnk3nCXB6QEQnOhDlu3n-s7lnUTAkrUsjP6FDQIQg,2104
@@ -40,8 +40,8 @@ tests/fetchers/sync/test_playwright.py,sha256=5eZdPwk3JGeaO7GuExv_QsByLyWDE9joxn
 tests/parser/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/parser/test_automatch.py,sha256=SxsNdExE8zz8AcPRQFBUjZ3Q_1-tPOd9dzVvMSZpOYQ,4908
 tests/parser/test_general.py,sha256=dyfOsc8lleoY4AxcfDUBUaD1i95xecfYuTUhKBsYjwo,12100
-scrapling-0.2.9.dist-info/LICENSE,sha256=XHgu8DRuT7_g3Hb9Q18YGg8eShp6axPBacbnQxT_WWQ,1499
-scrapling-0.2.9.dist-info/METADATA,sha256=Wg6lcRo_5LcyotrB1ZXagT5-gToAyRmtNKsq6TJoNk4,68382
-scrapling-0.2.9.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-scrapling-0.2.9.dist-info/top_level.txt,sha256=ub7FkOEXeYmmYTUxd4pCrwXfBfAMIpZ1sCGmXCc14tI,16
-scrapling-0.2.9.dist-info/RECORD,,
+scrapling-0.2.91.dist-info/LICENSE,sha256=XHgu8DRuT7_g3Hb9Q18YGg8eShp6axPBacbnQxT_WWQ,1499
+scrapling-0.2.91.dist-info/METADATA,sha256=ajc8n5Hjl--ZdGXwHxmfMEWyCMgbw1waZNovoPFxrUc,68339
+scrapling-0.2.91.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+scrapling-0.2.91.dist-info/top_level.txt,sha256=ub7FkOEXeYmmYTUxd4pCrwXfBfAMIpZ1sCGmXCc14tI,16
+scrapling-0.2.91.dist-info/RECORD,,