crawlee 1.0.0__py3-none-any.whl → 1.0.1__py3-none-any.whl

crawlee/browsers/_playwright_browser_controller.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+from asyncio import Lock
 from datetime import datetime, timedelta, timezone
 from typing import TYPE_CHECKING, Any, cast
 
@@ -77,6 +78,19 @@ class PlaywrightBrowserController(BrowserController):
 
         self._total_opened_pages = 0
 
+        self._context_creation_lock: Lock | None = None
+
+    async def _get_context_creation_lock(self) -> Lock:
+        """Get context checking and creation lock.
+
+        It should be done with lock to prevent multiple concurrent attempts to create context, which could lead to
+        memory leak as one of the two concurrently created contexts will become orphaned and not properly closed.
+        """
+        if self._context_creation_lock:
+            return self._context_creation_lock
+        self._context_creation_lock = Lock()
+        return self._context_creation_lock
+
     @property
     @override
     def pages(self) -> list[Page]:
@@ -137,12 +151,6 @@ class PlaywrightBrowserController(BrowserController):
         Raises:
             ValueError: If the browser has reached the maximum number of open pages.
         """
-        if not self._browser_context:
-            self._browser_context = await self._create_browser_context(
-                browser_new_context_options=browser_new_context_options,
-                proxy_info=proxy_info,
-            )
-
         if not self.has_free_capacity:
             raise ValueError('Cannot open more pages in this browser.')
 
@@ -154,11 +162,12 @@ class PlaywrightBrowserController(BrowserController):
             )
             page = await new_context.new_page()
         else:
-            if not self._browser_context:
-                self._browser_context = await self._create_browser_context(
-                    browser_new_context_options=browser_new_context_options,
-                    proxy_info=proxy_info,
-                )
+            async with await self._get_context_creation_lock():
+                if not self._browser_context:
+                    self._browser_context = await self._create_browser_context(
+                        browser_new_context_options=browser_new_context_options,
+                        proxy_info=proxy_info,
+                    )
             page = await self._browser_context.new_page()
 
         # Handle page close event
@@ -169,7 +178,6 @@ class PlaywrightBrowserController(BrowserController):
         self._last_page_opened_at = datetime.now(timezone.utc)
 
         self._total_opened_pages += 1
-
         return page
 
     @override
@@ -206,7 +214,6 @@ class PlaywrightBrowserController(BrowserController):
         `self._fingerprint_generator` is available.
         """
         browser_new_context_options = dict(browser_new_context_options) if browser_new_context_options else {}
-
         if proxy_info:
             if browser_new_context_options.get('proxy'):
                 logger.warning("browser_new_context_options['proxy'] overriden by explicit `proxy_info` argument.")
@@ -244,5 +251,4 @@ class PlaywrightBrowserController(BrowserController):
         browser_new_context_options['extra_http_headers'] = browser_new_context_options.get(
             'extra_http_headers', extra_http_headers
         )
-
         return await self._browser.new_context(**browser_new_context_options)

crawlee/project_template/{{cookiecutter.project_name}}/pyproject.toml

@@ -5,8 +5,8 @@
 # % endif
 # % if cookiecutter.http_client == 'curl-impersonate'
 # % do extras.append('curl-impersonate')
-# % elif cookiecutter.http_client == 'impit'
-# % do extras.append('impit')
+# % elif cookiecutter.http_client == 'httpx'
+# % do extras.append('httpx')
 # % endif
 
 [project]

crawlee/project_template/{{cookiecutter.project_name}}/requirements.txt

@@ -10,4 +10,7 @@ apify
 # % if cookiecutter.http_client == 'curl-impersonate'
 # % do extras.append('curl-impersonate')
 # % endif
+# % if cookiecutter.http_client == 'httpx'
+# % do extras.append('httpx')
+# % endif
 crawlee[{{ extras | join(',') }}]

{crawlee-1.0.0.dist-info → crawlee-1.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: crawlee
-Version: 1.0.0
+Version: 1.0.1
 Summary: Crawlee for Python
 Project-URL: Apify Homepage, https://apify.com
 Project-URL: Changelog, https://crawlee.dev/python/docs/changelog
@@ -336,8 +336,6 @@ Description-Content-Type: text/markdown
 
 Crawlee covers your crawling and scraping end-to-end and **helps you build reliable scrapers. Fast.**
 
-> 🚀 Crawlee for Python is open to early adopters!
-
 Your crawlers will appear almost human-like and fly under the radar of modern bot protections even with the default configuration. Crawlee gives you the tools to crawl the web for links, scrape data and persistently store it in machine-readable formats, without having to worry about the technical details. And thanks to rich configuration options, you can tweak almost any aspect of Crawlee to suit your project's needs if the default settings don't cut it.
 
 > 👉 **View full documentation, guides and examples on the [Crawlee project website](https://crawlee.dev/python/)** 👈

{crawlee-1.0.0.dist-info → crawlee-1.0.1.dist-info}/RECORD

@@ -45,7 +45,7 @@ crawlee/browsers/_browser_controller.py,sha256=-g0pB5Nx5q67eMZVka49x-HMfQqJYoI6k
 crawlee/browsers/_browser_plugin.py,sha256=Wuojop___8ZO9eDoMs4JFmwMAFe5mZaTl0-Vz1PjkD8,3057
 crawlee/browsers/_browser_pool.py,sha256=2pT4m_g0DfopjTHYXb-piN6GqxvkayOeb4gmOtn1QNM,15634
 crawlee/browsers/_playwright_browser.py,sha256=1yXD6cXuLefZZGUG1m0CT38xXYSwIC7n95bJBdMOxbo,3820
-crawlee/browsers/_playwright_browser_controller.py,sha256=IJ6UGD7n99WmyvDCc4RbjURfdAay_R9ymqPbcI2f4Q8,9764
+crawlee/browsers/_playwright_browser_controller.py,sha256=YaY19slRj8gIKrZy0M8rzF_zy2Z1Ym6d0S_vXcMX108,10215
 crawlee/browsers/_playwright_browser_plugin.py,sha256=axZa_yZNCPHyM3Ijx9jW4CzzRXQTVzYAswcGAZHP3Hk,8106
 crawlee/browsers/_types.py,sha256=eWgpoLMWu103hMQQTObkA01sVc_7hdPESl-TCyDMMV0,426
 crawlee/browsers/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -126,8 +126,8 @@ crawlee/project_template/templates/routes_playwright_camoufox.py,sha256=XtXWbPZ4
 crawlee/project_template/{{cookiecutter.project_name}}/.dockerignore,sha256=PCDXvENlrMmYleuQULduBiw8ipXmE_iYJtCmeZVuz1I,6
 crawlee/project_template/{{cookiecutter.project_name}}/Dockerfile,sha256=NRSdHgEnCjBWE0lU3y-qHNEUJg_OH3zhoo0fPzkIs58,4138
 crawlee/project_template/{{cookiecutter.project_name}}/README.md,sha256=kEwhjWKqnSbg3gtGsuEiqWFGoqMdf4W7TZ0Lu0omwHk,1753
-crawlee/project_template/{{cookiecutter.project_name}}/pyproject.toml,sha256=E89kToOVOEclt5OB8YOg7fJM5o4TAEYlwz3-O1kpPi4,970
-crawlee/project_template/{{cookiecutter.project_name}}/requirements.txt,sha256=xOeHqX5Bi2Iw1nkmBqbawX5A0qHo4CjQLn6JB-BNeUw,377
+crawlee/project_template/{{cookiecutter.project_name}}/pyproject.toml,sha256=rfzarAQB8H93clog9xnqVThCIR7ltKqasMHX0-9PIMw,970
+crawlee/project_template/{{cookiecutter.project_name}}/requirements.txt,sha256=HTiM50HxLguBgqKKLFR9DjsfrWgo13n8cAAJ9xhEmw8,460
 crawlee/project_template/{{cookiecutter.project_name}}/{{cookiecutter.__package_name}}/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 crawlee/project_template/{{cookiecutter.project_name}}/{{cookiecutter.__package_name}}/__main__.py,sha256=7YQVjE3HdCnoU055kLcKUcqXvbp3C2rtAY2TSJaItts,867
 crawlee/project_template/{{cookiecutter.project_name}}/{{cookiecutter.__package_name}}/main.py,sha256=mb3Wo_FpXGdIzWABJ0Y6CE-eXKxqSM_k__tnYYM1rF4,55
@@ -186,8 +186,8 @@ crawlee/storages/_key_value_store.py,sha256=3oI5hVoM_NpTQVKXCbQCmb0sZhW7vN2oXQo-
 crawlee/storages/_request_queue.py,sha256=jt-d-NkI9lAorLssoI2r_lZjeEipe-5Cn6z9bfQqY3k,13154
 crawlee/storages/_storage_instance_manager.py,sha256=iFX3ymsIXyTg8tMHtx5Wn9XyaC77dIf15GpuggsJPDM,7821
 crawlee/storages/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-crawlee-1.0.0.dist-info/METADATA,sha256=w6JIDE37hFDroKUw6Kc5KjhH93KLk4jK3I1aeHwrHBI,29366
-crawlee-1.0.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-crawlee-1.0.0.dist-info/entry_points.txt,sha256=1p65X3dA-cYvzjtlxLL6Kn1wpY-3uEDVqJLp53uNPeo,45
-crawlee-1.0.0.dist-info/licenses/LICENSE,sha256=AsFjHssKjj4LGd2ZCqXn6FBzMqcWdjQre1byPPSypVw,11355
-crawlee-1.0.0.dist-info/RECORD,,
+crawlee-1.0.1.dist-info/METADATA,sha256=TUu48Ck-aNjxG2Kyn7Dampj6RZ_rGWV0MZcIUSf7rf0,29312
+crawlee-1.0.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+crawlee-1.0.1.dist-info/entry_points.txt,sha256=1p65X3dA-cYvzjtlxLL6Kn1wpY-3uEDVqJLp53uNPeo,45
+crawlee-1.0.1.dist-info/licenses/LICENSE,sha256=AsFjHssKjj4LGd2ZCqXn6FBzMqcWdjQre1byPPSypVw,11355
+crawlee-1.0.1.dist-info/RECORD,,