PlaywrightCapture 1.25.1__tar.gz → 1.25.3__tar.gz

{playwrightcapture-1.25.1 → playwrightcapture-1.25.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PlaywrightCapture
-Version: 1.25.1
+Version: 1.25.3
 Summary: A simple library to capture websites using playwright
 Home-page: https://github.com/Lookyloo/PlaywrightCapture
 License: BSD-3-Clause
@@ -28,7 +28,7 @@ Requires-Dist: beautifulsoup4[charset-normalizer,lxml] (>=4.12.3,<5.0.0)
 Requires-Dist: dateparser (>=1.2.0,<2.0.0)
 Requires-Dist: playwright (>=1.45.0,<2.0.0)
 Requires-Dist: playwright-stealth (>=1.0.6,<2.0.0)
-Requires-Dist: puremagic (>=1.25,<2.0)
+Requires-Dist: puremagic (>=1.26,<2.0)
 Requires-Dist: pydub (>=0.25.1,<0.26.0) ; extra == "recaptcha"
 Requires-Dist: pytz (>=2024.1,<2025.0) ; python_version < "3.9"
 Requires-Dist: setuptools (>=70.3.0,<71.0.0)

{playwrightcapture-1.25.1 → playwrightcapture-1.25.3}/playwrightcapture/capture.py

@@ -32,7 +32,7 @@ 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 puremagic import PureError, from_string  # type: ignore[import-untyped]
+from puremagic import PureError, from_string
 from w3lib.html import strip_html5_whitespace
 from w3lib.url import canonicalize_url, safe_url_string
 
@@ -683,6 +683,7 @@ class Capture():
             try:
                 page = await self.context.new_page()
                 await page.clock.install()
+                page.on("dialog", lambda dialog: dialog.accept())
             except Error as e:
                 self.logger.warning(f'The context is in a broken state: {e}')
                 self.should_retry = True
@@ -805,12 +806,6 @@ class Capture():
                         except Exception as e:
                             self.logger.warning(f'Could not find body: {e}')
 
-                    # fast forward 30s
-                    await page.clock.run_for(10000)
-                    await page.clock.resume()
-                    await self._wait_for_random_timeout(page, 5)  # Wait 5 sec
-                    self.logger.warning('Moved time forward.')
-
                     if parsed_url.fragment:
                         # We got a fragment, make sure we go to it and scroll only a little bit.
                         fragment = unquote(parsed_url.fragment)
@@ -870,6 +865,10 @@ class Capture():
                                 z.writestr(f'{i}_{filename}', file_content)
                         to_return["downloaded_file"] = mem_zip.getvalue()
 
+                # fast forward 30s
+                await page.clock.run_for("30")
+                self.logger.debug('Moved time forward.')
+
                 self.logger.debug('Done with instrumentation, waiting for network idle.')
                 await self._wait_for_random_timeout(page, 5)  # Wait 5 sec after instrumentation
                 await self._safe_wait(page)

{playwrightcapture-1.25.1 → playwrightcapture-1.25.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "PlaywrightCapture"
-version = "1.25.1"
+version = "1.25.3"
 description = "A simple library to capture websites using playwright"
 authors = ["Raphaël Vinot <raphael.vinot@circl.lu>"]
 license = "BSD-3-Clause"
@@ -29,7 +29,7 @@ pytz = {"version" = "^2024.1", python = "<3.9"}
 tzdata = "^2024.1"
 playwright-stealth = "^1.0.6"
 setuptools = "^70.3.0"
-puremagic = "^1.25"
+puremagic = "^1.26"
 async-timeout = {version = "^4.0.3", python = "<3.11"}
 aiohttp = {extras = ["speedups"], version = "^3.9.5"}
 aiohttp-socks = "^0.8.4"