PlaywrightCapture 1.28.0__tar.gz → 1.28.2__tar.gz

{playwrightcapture-1.28.0 → playwrightcapture-1.28.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: PlaywrightCapture
-Version: 1.28.0
+Version: 1.28.2
 Summary: A simple library to capture websites using playwright
 License: BSD-3-Clause
 Author: Raphaël Vinot
@@ -20,15 +20,16 @@ Classifier: Topic :: Security
 Provides-Extra: recaptcha
 Requires-Dist: SpeechRecognition (>=3.14.1) ; extra == "recaptcha"
 Requires-Dist: aiohttp-socks (>=0.10.1)
-Requires-Dist: aiohttp[speedups] (>=3.11.12)
+Requires-Dist: aiohttp[speedups] (>=3.11.14)
 Requires-Dist: async-timeout (>=5.0.1) ; python_version < "3.11"
 Requires-Dist: beautifulsoup4[charset-normalizer,lxml] (>=4.13.3)
 Requires-Dist: dateparser (>=1.2.1)
-Requires-Dist: playwright (>=1.50.0)
+Requires-Dist: playwright (>=1.51.0)
 Requires-Dist: playwright-stealth (>=1.0.6)
 Requires-Dist: puremagic (>=1.28)
 Requires-Dist: pydub (>=0.25.1) ; extra == "recaptcha"
-Requires-Dist: setuptools (>=75.8.0)
+Requires-Dist: setuptools (>=77.0.1)
+Requires-Dist: typing-extensions (>=4.12.2,<5.0.0) ; python_version < "3.12"
 Requires-Dist: tzdata (>=2025.1)
 Requires-Dist: w3lib (>=2.3.1)
 Project-URL: Issues, https://github.com/Lookyloo/PlaywrightCapture/issues

{playwrightcapture-1.28.0 → playwrightcapture-1.28.2}/playwrightcapture/capture.py

@@ -17,7 +17,7 @@ from dataclasses import dataclass
 from io import BytesIO
 from logging import LoggerAdapter, Logger
 from tempfile import NamedTemporaryFile
-from typing import Any, TypedDict, Literal, TYPE_CHECKING
+from typing import Any, Literal, TYPE_CHECKING
 from collections.abc import MutableMapping, Iterator
 from urllib.parse import urlparse, unquote, urljoin, urlsplit, urlunsplit
 from zipfile import ZipFile
@@ -46,11 +46,16 @@ if sys.version_info < (3, 11):
 else:
     from asyncio import timeout
 
+if sys.version_info < (3, 12):
+    from typing_extensions import TypedDict
+else:
+    from typing import TypedDict
+
 if TYPE_CHECKING:
     from playwright._impl._api_structures import (SetCookieParam, Geolocation,
                                                   HttpCredentials, Headers,
                                                   ViewportSize, Cookie,
-                                                  ProxySettings)
+                                                  ProxySettings, StorageState)
     BROWSER = Literal['chromium', 'firefox', 'webkit']
 
 try:
@@ -66,6 +71,7 @@ class CaptureResponse(TypedDict, total=False):
     last_redirected_url: str
     har: dict[str, Any] | None
     cookies: list[Cookie] | None
+    storage: StorageState | None
     error: str | None
     error_name: str | None
     html: str | None
@@ -186,6 +192,7 @@ class Capture():
         self.should_retry: bool = False
         self.__network_not_idle: int = 2  # makes sure we do not wait for network idle the max amount of time the capture is allowed to take
         self._cookies: list[SetCookieParam] = []
+        self._storage: StorageState = {}
         self._http_credentials: HttpCredentials = {}
         self._geolocation: Geolocation = {}
         self._headers: Headers = {}
@@ -358,6 +365,18 @@ class Capture():
                 path = cookie.get("path")
                 self.logger.warning(f'The cookie must have a URL ({url}) or a domain ({domain}) and a path ({path})')
 
+    @property
+    def storage(self) -> StorageState:
+        return self._storage
+
+    @storage.setter
+    def storage(self, storage: dict[str, Any] | None) -> None:
+        if not storage:
+            return
+        if 'cookies' in storage and 'origins' in storage:
+            self._storage['cookies'] = storage['cookies']
+            self._storage['origins'] = storage['origins']
+
     @property
     def headers(self) -> Headers:
         return self._headers
@@ -458,6 +477,7 @@ class Capture():
             timezone_id=self.timezone_id if self.timezone_id else None,
             color_scheme=self.color_scheme if self.color_scheme else None,
             viewport=vp,
+            storage_state=self.storage if self.storage else None,
             # For debug only
             # record_video_dir='./videos/',
             **device_context_settings
@@ -1177,6 +1197,7 @@ class Capture():
             self.logger.debug('Finishing up capture.')
             if not capturing_sub:
                 try:
+                    to_return['storage'] = await self.context.storage_state(indexed_db=True)
                     to_return['cookies'] = await self.context.cookies()
                     self.logger.debug('Done with cookies.')
                 except Exception as e:

{playwrightcapture-1.28.0 → playwrightcapture-1.28.2}/playwrightcapture/helpers.py

@@ -2,13 +2,19 @@
 
 from __future__ import annotations
 
+import sys
+
 from collections import defaultdict
-from typing import TypedDict
 
 from playwright.sync_api import sync_playwright
 
 from .exceptions import UnknownPlaywrightDeviceType
 
+if sys.version_info < (3, 12):
+    from typing_extensions import TypedDict
+else:
+    from typing import TypedDict
+
 
 class PlaywrightDevice(TypedDict):
 
@@ -22,9 +28,8 @@ class PlaywrightDevice(TypedDict):
 
 def get_devices(in_testsuite: bool=False) -> dict[str, dict[str, dict[str, PlaywrightDevice]]]:
     to_return: dict[str, dict[str, dict[str, PlaywrightDevice]]] = {'desktop': defaultdict(dict), 'mobile': defaultdict(dict)}
-    playwright = sync_playwright().start()
-    devices: dict[str, PlaywrightDevice] = playwright.devices
-    playwright.stop()
+    with sync_playwright() as playwright:
+        devices: dict[str, PlaywrightDevice] = playwright.devices
     for device_name, settings in devices.items():
         splitted_name = device_name.split(' ')
         if splitted_name[0] == 'Desktop':

{playwrightcapture-1.28.0 → playwrightcapture-1.28.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PlaywrightCapture"
-version = "1.28.0"
+version = "1.28.2"
 description = "A simple library to capture websites using playwright"
 authors = [
     {name="Raphaël Vinot", email= "raphael.vinot@circl.lu"}
@@ -12,17 +12,18 @@ requires-python = ">=3.9"
 dynamic = [ "classifiers" ]
 
 dependencies = [
-    "playwright (>=1.50.0)",
+    "playwright (>=1.51.0)",
     "dateparser (>=1.2.1)",
     "beautifulsoup4[charset-normalizer,lxml] (>=4.13.3)",
     "w3lib (>=2.3.1)",
     "tzdata (>=2025.1)",
     "playwright-stealth (>=1.0.6)",
-    "setuptools (>=75.8.0)",
+    "setuptools (>=77.0.1)",
     "puremagic (>=1.28)",
     "async-timeout (>=5.0.1) ; python_version < \"3.11\"",
-    "aiohttp[speedups] (>=3.11.12)",
-    "aiohttp-socks (>=0.10.1)"
+    "aiohttp[speedups] (>=3.11.14)",
+    "aiohttp-socks (>=0.10.1)",
+    "typing-extensions (>=4.12.2,<5.0.0) ; python_version < \"3.12\""
 ]
 
 [project.urls]
@@ -46,10 +47,10 @@ recaptcha = [
 
 [tool.poetry.group.dev.dependencies]
 types-beautifulsoup4 = "^4.12.0.20250204"
-pytest = "^8.3.4"
+pytest = "^8.3.5"
 mypy = "^1.15.0"
 types-dateparser = "^1.2.0.20250208"
-types-pytz = "^2025.1.0.20250204"
+types-pytz = "^2025.1.0.20250318"
 
 
 [build-system]