PlaywrightCapture 1.28.1__tar.gz → 1.28.3__tar.gz

{playwrightcapture-1.28.1 → playwrightcapture-1.28.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: PlaywrightCapture
-Version: 1.28.1
+Version: 1.28.3
 Summary: A simple library to capture websites using playwright
 License: BSD-3-Clause
 Author: Raphaël Vinot
@@ -18,7 +18,7 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Internet
 Classifier: Topic :: Security
 Provides-Extra: recaptcha
-Requires-Dist: SpeechRecognition (>=3.14.1) ; extra == "recaptcha"
+Requires-Dist: SpeechRecognition (>=3.14.2) ; extra == "recaptcha"
 Requires-Dist: aiohttp-socks (>=0.10.1)
 Requires-Dist: aiohttp[speedups] (>=3.11.14)
 Requires-Dist: async-timeout (>=5.0.1) ; python_version < "3.11"
@@ -28,8 +28,9 @@ 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 (>=77.0.1)
-Requires-Dist: tzdata (>=2025.1)
+Requires-Dist: setuptools (>=78.1.0)
+Requires-Dist: typing-extensions (>=4.12.2,<5.0.0) ; python_version < "3.12"
+Requires-Dist: tzdata (>=2025.2)
 Requires-Dist: w3lib (>=2.3.1)
 Project-URL: Issues, https://github.com/Lookyloo/PlaywrightCapture/issues
 Project-URL: Repository, https://github.com/Lookyloo/PlaywrightCapture

{playwrightcapture-1.28.1 → playwrightcapture-1.28.3}/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
@@ -46,6 +46,11 @@ 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,
@@ -915,6 +920,7 @@ class Capture():
                            referer: str | None=None,
                            page: Page | None=None, depth: int=0,
                            rendered_hostname_only: bool=True,
+                           with_screenshot: bool=True,
                            with_favicon: bool=False,
                            allow_tracking: bool=False,
                            clock_set: bool=False
@@ -1094,7 +1100,9 @@ class Capture():
                         self.logger.warning(f'Unable to get favicons: {e}')
 
                 to_return['last_redirected_url'] = page.url
-                to_return['png'] = await self._failsafe_get_screenshot(page)
+
+                if with_screenshot:
+                    to_return['png'] = await self._failsafe_get_screenshot(page)
 
                 self._already_captured.add(url)
                 if depth > 0 and to_return.get('html') and to_return['html']:
@@ -1126,7 +1134,7 @@ class Capture():
                                         page=page, depth=depth,
                                         rendered_hostname_only=rendered_hostname_only,
                                         max_depth_capture_time=max_capture_time,
-                                        clock_set=clock_set)
+                                        clock_set=clock_set, with_screenshot=with_screenshot)
                                     to_return['children'].append(child_capture)  # type: ignore[union-attr]
                             except (TimeoutError, asyncio.TimeoutError):
                                 self.logger.info(f'Timeout error, took more than {max_capture_time}s. Unable to capture {url}.')

{playwrightcapture-1.28.1 → playwrightcapture-1.28.3}/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):
 

{playwrightcapture-1.28.1 → playwrightcapture-1.28.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PlaywrightCapture"
-version = "1.28.1"
+version = "1.28.3"
 description = "A simple library to capture websites using playwright"
 authors = [
     {name="Raphaël Vinot", email= "raphael.vinot@circl.lu"}
@@ -16,13 +16,14 @@ dependencies = [
     "dateparser (>=1.2.1)",
     "beautifulsoup4[charset-normalizer,lxml] (>=4.13.3)",
     "w3lib (>=2.3.1)",
-    "tzdata (>=2025.1)",
+    "tzdata (>=2025.2)",
     "playwright-stealth (>=1.0.6)",
-    "setuptools (>=77.0.1)",
+    "setuptools (>=78.1.0)",
     "puremagic (>=1.28)",
     "async-timeout (>=5.0.1) ; python_version < \"3.11\"",
     "aiohttp[speedups] (>=3.11.14)",
-    "aiohttp-socks (>=0.10.1)"
+    "aiohttp-socks (>=0.10.1)",
+    "typing-extensions (>=4.12.2,<5.0.0) ; python_version < \"3.12\""
 ]
 
 [project.urls]
@@ -41,7 +42,7 @@ classifiers=[
 [project.optional-dependencies]
 recaptcha = [
     "pydub (>=0.25.1)",
-    "SpeechRecognition (>=3.14.1)"
+    "SpeechRecognition (>=3.14.2)"
 ]
 
 [tool.poetry.group.dev.dependencies]
@@ -49,7 +50,7 @@ types-beautifulsoup4 = "^4.12.0.20250204"
 pytest = "^8.3.5"
 mypy = "^1.15.0"
 types-dateparser = "^1.2.0.20250208"
-types-pytz = "^2025.1.0.20250318"
+types-pytz = "^2025.2.0.20250326"
 
 
 [build-system]