PlaywrightCapture 1.27.4__tar.gz → 1.27.6__tar.gz

{playwrightcapture-1.27.4 → playwrightcapture-1.27.6}/PKG-INFO

@@ -1,13 +1,11 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: PlaywrightCapture
-Version: 1.27.4
+Version: 1.27.6
 Summary: A simple library to capture websites using playwright
-Home-page: https://github.com/Lookyloo/PlaywrightCapture
 License: BSD-3-Clause
 Author: Raphaël Vinot
 Author-email: raphael.vinot@circl.lu
-Requires-Python: >=3.9,<4.0
-Classifier: Environment :: Console
+Requires-Python: >=3.9
 Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: Telecommunications Industry
 Classifier: License :: OSI Approved :: BSD License
@@ -20,20 +18,19 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Internet
 Classifier: Topic :: Security
 Provides-Extra: recaptcha
-Requires-Dist: SpeechRecognition (>=3.11.0) ; extra == "recaptcha"
-Requires-Dist: aiohttp-socks (>=0.9,<0.10)
-Requires-Dist: aiohttp[speedups] (>=3.11.9,<4.0.0)
-Requires-Dist: async-timeout (>=4.0.3,<5.0.0) ; python_version < "3.11"
-Requires-Dist: beautifulsoup4[charset-normalizer,lxml] (>=4.12.3,<5.0.0)
-Requires-Dist: dateparser (>=1.2.0,<2.0.0)
-Requires-Dist: playwright (>=1.49.0,<2.0.0)
-Requires-Dist: playwright-stealth (>=1.0.6,<2.0.0)
-Requires-Dist: puremagic (>=1.28,<2.0)
-Requires-Dist: pydub (>=0.25.1,<0.26.0) ; extra == "recaptcha"
-Requires-Dist: setuptools (>=75.6.0,<76.0.0)
-Requires-Dist: tzdata (>=2024.2,<2025.0)
-Requires-Dist: w3lib (>=2.2.1,<3.0.0)
-Project-URL: Repository, https://github.com/Lookyloo/PlaywrightCapture
+Requires-Dist: SpeechRecognition (>=3.14.1) ; extra == "recaptcha"
+Requires-Dist: aiohttp-socks (>=0.10.1)
+Requires-Dist: aiohttp[speedups] (>=3.11.11)
+Requires-Dist: async-timeout (>=5.0.1) ; python_version < "3.11"
+Requires-Dist: beautifulsoup4[charset-normalizer,lxml] (>=4.12.3)
+Requires-Dist: dateparser (>=1.2.0)
+Requires-Dist: playwright (>=1.49.1)
+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: tzdata (>=2025.1)
+Requires-Dist: w3lib (>=2.2.1)
 Description-Content-Type: text/markdown
 
 # Playwright Capture

{playwrightcapture-1.27.4 → playwrightcapture-1.27.6}/playwrightcapture/capture.py

@@ -18,21 +18,20 @@ from io import BytesIO
 from logging import LoggerAdapter, Logger
 from tempfile import NamedTemporaryFile
 from typing import Any, TypedDict, Literal, TYPE_CHECKING
-from collections.abc import MutableMapping, Generator
+from collections.abc import MutableMapping, Iterator
 from urllib.parse import urlparse, unquote, urljoin, urlsplit, urlunsplit
 from zipfile import ZipFile
 
 import aiohttp
 import dateparser
-import urllib3
 
-from aiohttp_socks import ProxyConnector  # type: ignore[import-untyped]
+from aiohttp_socks import ProxyConnector
 from bs4 import BeautifulSoup
 from charset_normalizer import from_bytes
 from playwright._impl._errors import TargetClosedError
 from playwright.async_api import async_playwright, Frame, Error, Page, Download, Request
 from playwright.async_api import TimeoutError as PlaywrightTimeoutError
-from playwright_stealth import stealth_async, StealthConfig  # type: ignore[import-untyped]
+from playwright_stealth import stealth_async, StealthConfig  # type: ignore[attr-defined]
 from puremagic import PureError, from_string
 from w3lib.html import strip_html5_whitespace
 from w3lib.url import canonicalize_url, safe_url_string
@@ -55,15 +54,12 @@ if TYPE_CHECKING:
     BROWSER = Literal['chromium', 'firefox', 'webkit']
 
 try:
-    import pydub  # type: ignore[import-untyped]
-    from speech_recognition import Recognizer, AudioFile  # type: ignore[import-untyped]
+    from pydub import AudioSegment  # type: ignore[attr-defined]
+    from speech_recognition import Recognizer, AudioFile
     CAN_SOLVE_CAPTCHA = True
 except ImportError:
     CAN_SOLVE_CAPTCHA = False
 
-# Do not show TLS warnings from urllib3 when fetching a favicon
-urllib3.disable_warnings()
-
 
 class CaptureResponse(TypedDict, total=False):
 
@@ -99,10 +95,10 @@ class PlaywrightCaptureLogAdapter(LoggerAdapter):  # type: ignore[type-arg]
 # https://fingerprintjs.github.io/BotD/main/
 
 @dataclass
-class PCStealthConfig(StealthConfig):  # type: ignore[misc]
+class PCStealthConfig(StealthConfig):
 
     @property
-    def enabled_scripts(self) -> Generator[str]:
+    def enabled_scripts(self) -> Iterator[str]:
         self.chrome_app = True
         self.chrome_csi = True
         self.chrome_runtime = True
@@ -227,6 +223,7 @@ class Capture():
 
         self.browser = await self.playwright[self.browser_name].launch(
             proxy=self.proxy if self.proxy else None,
+            channel="chromium" if self.browser_name == "chromium" else None,
             # headless=False
         )
 
@@ -698,6 +695,8 @@ class Capture():
             "Accept all",
             "Accept",
             "Agree and close",
+            "I agree",
+            "Agree",
             # Dutch
             "Accepteer",
             # Spanish
@@ -1358,12 +1357,12 @@ class Capture():
                     mp3_content = await response.read()
                 with NamedTemporaryFile() as mp3_file, NamedTemporaryFile() as wav_file:
                     mp3_file.write(mp3_content)
-                    pydub.AudioSegment.from_mp3(mp3_file.name).export(wav_file.name, format="wav")
-                    recognizer = Recognizer()
-                    recaptcha_audio = AudioFile(wav_file.name)
+                    AudioSegment.from_mp3(mp3_file.name).export(wav_file.name, format="wav")  # type: ignore[no-untyped-call]
+                    recognizer = Recognizer()  # type: ignore[no-untyped-call]
+                    recaptcha_audio = AudioFile(wav_file.name)  # type: ignore[no-untyped-call]
                     with recaptcha_audio as source:
-                        audio = recognizer.record(source)
-                    text = recognizer.recognize_google(audio)
+                        audio = recognizer.record(source)  # type: ignore[no-untyped-call]
+                    text = recognizer.recognize_google(audio)  # type: ignore[attr-defined]
                 await main_frame.get_by_role("textbox", name="Enter what you hear").fill(text)
                 await main_frame.get_by_role("button", name="Verify").click()
                 await self._safe_wait(page, 5)
@@ -1416,6 +1415,8 @@ class Capture():
             'Error receiving data: Connection reset by peer',
             'Internal SOCKSv5 proxy server error.',
             'Host unreachable through SOCKSv5 server.',
+            # JS stuff
+            'TurnstileError: [Cloudflare Turnstile] Error: 300030.',
             # The browser barfed
             'Target page, context or browser has been closed',
         ]:

playwrightcapture-1.27.6/pyproject.toml

@@ -0,0 +1,55 @@
+[project]
+name = "PlaywrightCapture"
+version = "1.27.6"
+description = "A simple library to capture websites using playwright"
+authors = [
+    {name="Raphaël Vinot", email= "raphael.vinot@circl.lu"}
+]
+license = "BSD-3-Clause"
+repository = "https://github.com/Lookyloo/PlaywrightCapture"
+readme = "README.md"
+requires-python = ">=3.9"
+
+dynamic = [ "classifiers" ]
+
+dependencies = [
+    "playwright (>=1.49.1)",
+    "dateparser (>=1.2.0)",
+    "beautifulsoup4 [lxml,charset_normalizer] (>=4.12.3)",
+    "w3lib (>=2.2.1)",
+    "tzdata (>=2025.1)",
+    "playwright-stealth (>=1.0.6)",
+    "setuptools (>=75.8.0)",
+    "puremagic (>=1.28)",
+    "async-timeout (>=5.0.1) ; python_version < \"3.11\"",
+    "aiohttp [speedups] (>=3.11.11)",
+    "aiohttp-socks (>=0.10.1)"
+]
+
+
+[tool.poetry]
+classifiers=[
+    'Intended Audience :: Science/Research',
+    'Intended Audience :: Telecommunications Industry',
+    'Topic :: Security',
+    'Topic :: Internet',
+]
+
+
+[project.optional-dependencies]
+recaptcha = [
+    "pydub (>=0.25.1)",
+    "SpeechRecognition (>=3.14.1)"
+]
+
+[tool.poetry.group.dev.dependencies]
+types-beautifulsoup4 = "^4.12.0.20241020"
+pytest = "^8.3.4"
+mypy = "^1.14.1"
+types-dateparser = "^1.2.0.20240420"
+types-pytz = "^2024.2.0.20241221"
+
+
+[build-system]
+requires = ["poetry-core>=2.0"]
+build-backend = "poetry.core.masonry.api"

playwrightcapture-1.27.4/pyproject.toml

@@ -1,52 +0,0 @@
-[tool.poetry]
-name = "PlaywrightCapture"
-version = "1.27.4"
-description = "A simple library to capture websites using playwright"
-authors = ["Raphaël Vinot <raphael.vinot@circl.lu>"]
-license = "BSD-3-Clause"
-repository = "https://github.com/Lookyloo/PlaywrightCapture"
-readme = "README.md"
-
-classifiers=[
-    'License :: OSI Approved :: BSD License',
-    'Environment :: Console',
-    'Intended Audience :: Science/Research',
-    'Intended Audience :: Telecommunications Industry',
-    'Programming Language :: Python :: 3',
-    'Topic :: Security',
-    'Topic :: Internet',
-]
-
-[tool.poetry.dependencies]
-python = "^3.9"
-playwright = "^1.49.0"
-dateparser = "^1.2.0"
-beautifulsoup4 = {version= "^4.12.3", extras = ["lxml", "charset_normalizer"]}
-w3lib = "^2.2.1"
-pydub = {version = "^0.25.1", optional = true}
-SpeechRecognition =  {version = ">=3.11.0", optional = true}
-tzdata = "^2024.2"
-playwright-stealth = "^1.0.6"
-setuptools = "^75.6.0"
-puremagic = "^1.28"
-async-timeout = {version = "^4.0.3", python = "<3.11"}
-aiohttp = {version = "^3.11.9", extras = ["speedups"]}
-aiohttp-socks = "^0.9"
-
-[tool.poetry.extras]
-recaptcha = ["pydub", "SpeechRecognition"]
-
-[tool.poetry.group.dev]
-optional = true
-
-[tool.poetry.group.dev.dependencies]
-types-beautifulsoup4 = "^4.12.0.20241020"
-pytest = "^8.3.4"
-mypy = "^1.13.0"
-types-dateparser = "^1.2.0.20240420"
-types-pytz = "^2024.2.0.20241003"
-
-
-[build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"