scrapely-python 0.1.0__tar.gz → 0.1.2__tar.gz

{scrapely_python-0.1.0 → scrapely_python-0.1.2}/PKG-INFO

@@ -1,16 +1,15 @@
 Metadata-Version: 2.4
 Name: scrapely-python
-Version: 0.1.0
+Version: 0.1.2
 Summary: Scrapely Python SDK - A toolkit for building Actors on the Scrapely platform
 Author-email: Scrapely <support@scrape.ly>
-License: MIT
+License-Expression: MIT
 Project-URL: Homepage, https://scrape.ly
 Project-URL: Documentation, https://docs.scrape.ly
 Project-URL: Repository, https://github.com/SandeepDev1/scrapely
 Keywords: scraping,actor,serverless,apify,scrapely
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
@@ -22,7 +21,7 @@ Description-Content-Type: text/markdown
 Requires-Dist: httpx>=0.25.0
 Requires-Dist: crawlee<2.0.0,>=1.8.0
 Requires-Dist: websockets>=12.0
-Requires-Dist: scrapely-client-python<2,>=1.0.0
+Requires-Dist: scrapely-client-python<2,>=1.0.2
 Requires-Dist: pydantic>=2.0.0
 Requires-Dist: cryptography>=42.0.0
 Provides-Extra: dev
@@ -43,7 +42,7 @@ Build Python Actors for the [Scrapely](https://scrape.ly) platform with lifecycl
 Scrapely requires Python 3.9 or newer.
 
 ```bash
-python -m pip install scrapely
+python -m pip install scrapely-python
 ```
 
 Install the appropriate Crawlee/Playwright browser dependencies separately when your Actor uses a browser.

{scrapely_python-0.1.0 → scrapely_python-0.1.2}/README.md

@@ -7,7 +7,7 @@ Build Python Actors for the [Scrapely](https://scrape.ly) platform with lifecycl
 Scrapely requires Python 3.9 or newer.
 
 ```bash
-python -m pip install scrapely
+python -m pip install scrapely-python
 ```
 
 Install the appropriate Crawlee/Playwright browser dependencies separately when your Actor uses a browser.

{scrapely_python-0.1.0 → scrapely_python-0.1.2}/pyproject.toml

@@ -1,20 +1,19 @@
 [build-system]
-requires = ["setuptools>=61.0", "wheel"]
+requires = ["setuptools>=77.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [project]
 name = "scrapely-python"
-version = "0.1.0"
+version = "0.1.2"
 description = "Scrapely Python SDK - A toolkit for building Actors on the Scrapely platform"
 readme = "README.md"
-license = {text = "MIT"}
+license = "MIT"
 authors = [
     {name = "Scrapely", email = "support@scrape.ly"}
 ]
 classifiers = [
     "Development Status :: 3 - Alpha",
     "Intended Audience :: Developers",
-    "License :: OSI Approved :: MIT License",
     "Operating System :: OS Independent",
     "Programming Language :: Python :: 3",
     "Programming Language :: Python :: 3.11",
@@ -28,7 +27,7 @@ dependencies = [
     "httpx>=0.25.0",
     "crawlee>=1.8.0,<2.0.0",
     "websockets>=12.0",
-    "scrapely-client-python>=1.0.0,<2",
+    "scrapely-client-python>=1.0.2,<2",
     "pydantic>=2.0.0",
     "cryptography>=42.0.0",
 ]

{scrapely_python-0.1.0 → scrapely_python-0.1.2}/src/scrapely/__init__.py

@@ -132,7 +132,7 @@ from .errors import (
     raise_for_status,
 )
 
-__version__ = '0.1.0'
+__version__ = '0.1.2'
 __all__ = [
     # Core
     'Actor',

{scrapely_python-0.1.0 → scrapely_python-0.1.2}/src/scrapely/actor.py

@@ -1776,19 +1776,20 @@ class Actor(metaclass=_ActorMeta):
         """
         cls._ensure_initialized('create_proxy_configuration')
 
-        from .proxy_configuration import ProxyConfiguration
+        from .proxy_configuration import ProxyConfiguration, _input_use_platform_proxy
 
         # Handle actor_proxy_input (Node SDK normalizeProxyInput/createProxyConfiguration
-        # parity): `useApifyProxy: false` explicitly disables the PLATFORM proxy only —
+        # parity): `useScrapelyProxy: false` (or the legacy `useApifyProxy: false`; a
+        # boolean useScrapelyProxy wins) explicitly disables the PLATFORM proxy only —
         # custom proxies (proxyUrls / tiered lists / new_url_function) from the same
         # input must still be used. The standard "Custom proxy URLs" input shape is
-        # {useApifyProxy: false, proxyUrls: [...]}; returning None for it would
+        # {useScrapelyProxy: false, proxyUrls: [...]}; returning None for it would
         # silently drop the user's own proxies and crawl on their real IPs. We only
         # bail when no custom proxies are given either. A MISSING key falls back to
         # platform mode when the server injected credentials — input like
         # {apifyProxyGroups: [...]} must not silently disable proxying.
         if actor_proxy_input is not None:
-            if actor_proxy_input.get('useApifyProxy') is False and not (
+            if _input_use_platform_proxy(actor_proxy_input) is False and not (
                 proxy_urls
                 or new_url_function
                 or tiered_proxy_urls

{scrapely_python-0.1.0 → scrapely_python-0.1.2}/src/scrapely/proxy_configuration.py

@@ -108,6 +108,19 @@ def _sanitize_fragment(value: str) -> str:
     return re.sub(r'[:@/?#\s]', '', value)
 
 
+def _input_use_platform_proxy(actor_proxy_input: Dict[str, Any]) -> Optional[bool]:
+    """The proxy input field's platform-proxy switch, or None when it has none.
+
+    `useScrapelyProxy` wins when it is a boolean; otherwise the legacy
+    `useApifyProxy` key of existing inputs and ported actors decides.
+    """
+    for key in ('useScrapelyProxy', 'useApifyProxy'):
+        value = actor_proxy_input.get(key)
+        if isinstance(value, bool):
+            return value
+    return None
+
+
 def _platform_env() -> Optional[Dict[str, Any]]:
     """Read platform proxy credentials from the environment (or None)."""
     hostname = os.environ.get('SCRAPELY_PROXY_HOSTNAME') or os.environ.get('APIFY_PROXY_HOSTNAME')
@@ -213,7 +226,7 @@ class ProxyConfiguration:
 
         # If actor_proxy_input is provided, extract settings from it
         if actor_proxy_input:
-            if actor_proxy_input.get('useApifyProxy', False):
+            if _input_use_platform_proxy(actor_proxy_input):
                 self._groups = actor_proxy_input.get('apifyProxyGroups', []) or []
                 self._country_code = actor_proxy_input.get('apifyProxyCountry')
                 self._subdivision_code = actor_proxy_input.get('apifyProxySubdivision')
@@ -291,7 +304,7 @@ class ProxyConfiguration:
         )
         if has_real_custom and (self._groups or self._country_code or self._subdivision_code or password):
             raise ValueError(
-                'Cannot combine custom proxies with Apify Proxy! It is not allowed to set '
+                'Cannot combine custom proxies with Scrapely Proxy! It is not allowed to set '
                 '"proxy_urls" or "new_url_function" combined with "groups", "country_code" '
                 'or "subdivision_code".'
             )
@@ -480,7 +493,8 @@ class ProxyConfiguration:
         Sends ``GET {status_url}/?format=json`` *through the platform gateway``
         so the proxy handshake itself authenticates the run's credentials.
         Mirrors the JS SDK: 4s timeout, 2 attempts, returns ``None`` when the
-        endpoint stays unreachable. Never raises.
+        endpoint stays unreachable. Never raises. ``fromPayload`` is True when
+        the gateway answered with its own status JSON rather than an HTTP error.
         """
         import urllib.error
         import urllib.request
@@ -514,6 +528,7 @@ class ProxyConfiguration:
                     'connected': payload.get('connected') is True,
                     'connectionError': payload.get('connectionError') or '',
                     'isManInTheMiddle': payload.get('isManInTheMiddle') is True,
+                    'fromPayload': True,
                 }
             except urllib.error.HTTPError as e:
                 if e.code == 407:
@@ -524,6 +539,7 @@ class ProxyConfiguration:
                             'SCRAPELY_PROXY_*/APIFY_PROXY_* credentials.'
                         ),
                         'isManInTheMiddle': False,
+                        'fromPayload': False,
                     }
                 if 590 <= e.code <= 599:
                     description = PROXY_STATUS_CODE_DESCRIPTIONS.get(e.code, 'upstream error')
@@ -531,6 +547,7 @@ class ProxyConfiguration:
                         'connected': False,
                         'connectionError': f'Platform proxy upstream error (HTTP {e.code}: {description}).',
                         'isManInTheMiddle': False,
+                        'fromPayload': False,
                     }
                 # Other HTTP errors behave like connection errors: retry.
             except Exception:  # noqa: BLE001 - retry connection errors (Apify behavior)
@@ -623,6 +640,9 @@ class ProxyConfiguration:
 
         Raises:
             ValueError: If proxy configuration is invalid
+            ConnectionError: If the platform proxy reports that this configuration
+                cannot be used (for example an unknown proxy group), with the
+                proxy's ``connectionError`` as the message (Apify parity)
         """
         if self._initialized:
             return
@@ -639,9 +659,10 @@ class ProxyConfiguration:
         if self._proxy_urls and self._new_url_function:
             raise ValueError('Cannot specify both proxy_urls and new_url_function')
 
-        # Apify-parity access check (best-effort, never fatal): GET
-        # {status_url}/?format=json *through the platform gateway* so the proxy
-        # handshake itself authenticates the run's credentials. Parity with the
+        # Apify-parity access check: GET {status_url}/?format=json *through the
+        # platform gateway* so the proxy handshake itself authenticates the run's
+        # credentials. A "connected": false answer raises like Apify's
+        # _check_access; timeouts and HTTP errors only warn. Parity with the
         # Apify SDKs (usesApifyProxy / uses_apify_proxy) and the JS Scrapely
         # port (platformEnv): the check only applies when this configuration
         # actually uses the platform proxy — BYOP-only configurations skip it
@@ -662,6 +683,8 @@ class ProxyConfiguration:
                 )
             else:
                 self._is_man_in_the_middle = status['isManInTheMiddle']
+                if not status['connected'] and status['fromPayload']:
+                    raise ConnectionError(status['connectionError'])
                 if not status['connected']:
                     logger.warning('Platform proxy access check failed: %s', status['connectionError'])
                 else:

{scrapely_python-0.1.0 → scrapely_python-0.1.2}/src/scrapely_python.egg-info/PKG-INFO

@@ -1,16 +1,15 @@
 Metadata-Version: 2.4
 Name: scrapely-python
-Version: 0.1.0
+Version: 0.1.2
 Summary: Scrapely Python SDK - A toolkit for building Actors on the Scrapely platform
 Author-email: Scrapely <support@scrape.ly>
-License: MIT
+License-Expression: MIT
 Project-URL: Homepage, https://scrape.ly
 Project-URL: Documentation, https://docs.scrape.ly
 Project-URL: Repository, https://github.com/SandeepDev1/scrapely
 Keywords: scraping,actor,serverless,apify,scrapely
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
@@ -22,7 +21,7 @@ Description-Content-Type: text/markdown
 Requires-Dist: httpx>=0.25.0
 Requires-Dist: crawlee<2.0.0,>=1.8.0
 Requires-Dist: websockets>=12.0
-Requires-Dist: scrapely-client-python<2,>=1.0.0
+Requires-Dist: scrapely-client-python<2,>=1.0.2
 Requires-Dist: pydantic>=2.0.0
 Requires-Dist: cryptography>=42.0.0
 Provides-Extra: dev
@@ -43,7 +42,7 @@ Build Python Actors for the [Scrapely](https://scrape.ly) platform with lifecycl
 Scrapely requires Python 3.9 or newer.
 
 ```bash
-python -m pip install scrapely
+python -m pip install scrapely-python
 ```
 
 Install the appropriate Crawlee/Playwright browser dependencies separately when your Actor uses a browser.

{scrapely_python-0.1.0 → scrapely_python-0.1.2}/src/scrapely_python.egg-info/requires.txt

@@ -1,7 +1,7 @@
 httpx>=0.25.0
 crawlee<2.0.0,>=1.8.0
 websockets>=12.0
-scrapely-client-python<2,>=1.0.0
+scrapely-client-python<2,>=1.0.2
 pydantic>=2.0.0
 cryptography>=42.0.0
 

{scrapely_python-0.1.0 → scrapely_python-0.1.2}/tests/test_proxy_configuration.py

@@ -2,6 +2,8 @@
 
 from __future__ import annotations
 
+import json
+
 import pytest
 
 from scrapely.proxy_configuration import ProxyConfiguration
@@ -87,7 +89,7 @@ async def test_sentinel_without_env_raises(monkeypatch: pytest.MonkeyPatch) -> N
 
 
 async def test_real_custom_plus_groups_rejected() -> None:
-    with pytest.raises(ValueError, match='Cannot combine custom proxies with Apify Proxy'):
+    with pytest.raises(ValueError, match='Cannot combine custom proxies with Scrapely Proxy'):
         ProxyConfiguration(proxy_urls=['http://user:pass@byok.example.com:8080'], groups=['RESIDENTIAL'])
     # Sentinel-only list may combine with groups (platform slot options).
     pc = ProxyConfiguration(proxy_urls=['auto'], groups=['RESIDENTIAL'])
@@ -222,7 +224,7 @@ async def test_subdivision_and_country_validation() -> None:
     with pytest.raises(ValueError, match='1-3 character ISO 3166-2'):
         ProxyConfiguration(country_code='US', subdivision_code='ca')
     # Subdivision combined with real BYOP URLs is a conflicting combination.
-    with pytest.raises(ValueError, match='Cannot combine custom proxies with Apify Proxy'):
+    with pytest.raises(ValueError, match='Cannot combine custom proxies with Scrapely Proxy'):
         ProxyConfiguration(
             proxy_urls=['http://byok.example.com:8080'],
             country_code='US',
@@ -500,6 +502,50 @@ async def test_access_check_runs_for_mixed_byop_and_sentinel(
     assert any('access check succeeded' in r.message for r in caplog.records)
 
 
+UNKNOWN_GROUP_ERROR = (
+    'Proxy group "GOOGLE_SERP" is not available on Scrapely. Available groups: RESIDENTIAL, DATACENTER.'
+)
+REFUSED_PAYLOAD = json.dumps({'connected': False, 'connectionError': UNKNOWN_GROUP_ERROR, 'isManInTheMiddle': False})
+CONNECTED_PAYLOAD = '{"connected": true, "isManInTheMiddle": false}'
+
+
+def _proxy_username(auth: str | None) -> str:
+    import base64
+
+    return base64.b64decode((auth or '').removeprefix('Basic ')).decode().split(':')[0]
+
+
+async def test_access_check_raises_gateway_connection_error(monkeypatch: pytest.MonkeyPatch) -> None:
+    with FakeGateway(200, REFUSED_PAYLOAD) as gateway:
+        _point_env_at_gateway(monkeypatch, gateway)
+        pc = ProxyConfiguration(groups=['GOOGLE_SERP'])
+        with pytest.raises(ConnectionError) as excinfo:
+            await pc.initialize()
+
+    assert str(excinfo.value) == UNKNOWN_GROUP_ERROR
+    assert [_proxy_username(auth) for _, auth in gateway.requests] == ['sub1,groups-GOOGLE_SERP']
+
+
+async def test_access_check_known_groups_succeed(
+    monkeypatch: pytest.MonkeyPatch, caplog: pytest.LogCaptureFixture
+) -> None:
+    import logging
+
+    with FakeGateway(200, CONNECTED_PAYLOAD) as gateway:
+        _point_env_at_gateway(monkeypatch, gateway)
+        with caplog.at_level(logging.INFO, logger='scrapely.proxy_configuration'):
+            for groups in (None, ['RESIDENTIAL'], ['DATACENTER']):
+                await ProxyConfiguration(groups=groups).initialize()
+
+    assert [_proxy_username(auth) for _, auth in gateway.requests] == [
+        'sub1',
+        'sub1,groups-RESIDENTIAL',
+        'sub1,groups-DATACENTER',
+    ]
+    assert sum('access check succeeded' in r.message for r in caplog.records) == 3
+    assert not any(r.levelno >= logging.WARNING for r in caplog.records)
+
+
 
 # ── Actor.create_proxy_configuration useApifyProxy semantics (Node parity) ────
 
@@ -567,6 +613,56 @@ async def test_actor_create_use_apify_proxy_false_with_explicit_kwarg_keeps_byop
     assert await pc.new_url() == 'http://byop-b:8080'
 
 
+# useScrapelyProxy is the canonical key; a boolean useScrapelyProxy wins over useApifyProxy.
+
+async def test_actor_create_use_scrapely_proxy_true_uses_platform(initialized_actor) -> None:
+    pc = await initialized_actor.create_proxy_configuration(
+        actor_proxy_input={'useScrapelyProxy': True, 'apifyProxyGroups': ['RESIDENTIAL']},
+        check_access=False,
+    )
+    assert pc is not None
+    assert 'groups-RESIDENTIAL' in await pc.new_url()
+
+
+async def test_actor_create_use_scrapely_proxy_false_disables(initialized_actor) -> None:
+    pc = await initialized_actor.create_proxy_configuration(
+        actor_proxy_input={'useScrapelyProxy': False, 'apifyProxyGroups': ['RESIDENTIAL']},
+        check_access=False,
+    )
+    assert pc is None
+
+
+async def test_actor_create_use_scrapely_proxy_false_with_proxy_urls_keeps_byop(initialized_actor) -> None:
+    pc = await initialized_actor.create_proxy_configuration(
+        actor_proxy_input={'useScrapelyProxy': False, 'proxyUrls': ['http://byop-a:8080']},
+        check_access=False,
+    )
+    assert pc is not None
+    assert await pc.new_url() == 'http://byop-a:8080'
+
+
+async def test_actor_create_use_scrapely_proxy_wins_over_use_apify_proxy(initialized_actor) -> None:
+    off = await initialized_actor.create_proxy_configuration(
+        actor_proxy_input={'useScrapelyProxy': False, 'useApifyProxy': True},
+        check_access=False,
+    )
+    assert off is None
+    on = await initialized_actor.create_proxy_configuration(
+        actor_proxy_input={'useScrapelyProxy': True, 'useApifyProxy': False, 'apifyProxyGroups': ['RESIDENTIAL']},
+        check_access=False,
+    )
+    assert on is not None
+    assert 'groups-RESIDENTIAL' in await on.new_url()
+
+
+def test_proxy_configuration_actor_input_use_scrapely_proxy() -> None:
+    pc = ProxyConfiguration(actor_proxy_input={'useScrapelyProxy': True, 'apifyProxyGroups': ['RESIDENTIAL']})
+    assert pc._groups == ['RESIDENTIAL']
+    custom = ProxyConfiguration(actor_proxy_input={'useScrapelyProxy': False, 'proxyUrls': ['http://byop-c:8080']})
+    assert custom._proxy_urls == ['http://byop-c:8080']
+    assert custom._groups == []
+
+
 async def test_actor_create_no_options_without_env_returns_none(
     initialized_actor, monkeypatch: pytest.MonkeyPatch
 ) -> None:
@@ -577,6 +673,37 @@ async def test_actor_create_no_options_without_env_returns_none(
     assert pc is None
 
 
+async def test_actor_create_refused_group_raises(initialized_actor, monkeypatch: pytest.MonkeyPatch) -> None:
+    with FakeGateway(200, REFUSED_PAYLOAD) as gateway:
+        _point_env_at_gateway(monkeypatch, gateway)
+        with pytest.raises(ConnectionError, match='Proxy group "GOOGLE_SERP" is not available'):
+            await initialized_actor.create_proxy_configuration(groups=['GOOGLE_SERP'])
+        with pytest.raises(ConnectionError, match='Proxy group "GOOGLE_SERP" is not available'):
+            await initialized_actor.create_proxy_configuration(
+                actor_proxy_input={'useApifyProxy': True, 'apifyProxyGroups': ['GOOGLE_SERP']}
+            )
+
+    assert [_proxy_username(auth) for _, auth in gateway.requests] == [
+        'sub1,groups-GOOGLE_SERP',
+        'sub1,groups-GOOGLE_SERP',
+    ]
+
+
+async def test_actor_create_http_errors_and_timeouts_only_warn(
+    initialized_actor, monkeypatch: pytest.MonkeyPatch, caplog: pytest.LogCaptureFixture
+) -> None:
+    import logging
+
+    with caplog.at_level(logging.WARNING, logger='scrapely.proxy_configuration'):
+        with FakeGateway(407, '') as gateway:
+            _point_env_at_gateway(monkeypatch, gateway)
+            assert await initialized_actor.create_proxy_configuration(groups=['GOOGLE_SERP']) is not None
+        assert await initialized_actor.create_proxy_configuration(groups=['GOOGLE_SERP']) is not None
+
+    assert any('authentication failed (HTTP 407)' in r.message for r in caplog.records)
+    assert any('access check timed out' in r.message for r in caplog.records)
+
+
 async def test_actor_create_proxy_urls_from_input_without_flag(initialized_actor) -> None:
     pc = await initialized_actor.create_proxy_configuration(
         actor_proxy_input={'proxyUrls': ['http://byop-a:8080']},