Reuse shared page batch accessors in paginated managers

cursoragent · shrisukhani · cursoragent · commit d100327ddf84 · 2026-02-14T12:47:09.000Z
Co-authored-by: Shri Sukhani &lt;shrisukhani@users.noreply.github.com&gt;
diff --git a/hyperbrowser/client/managers/async_manager/crawl.py b/hyperbrowser/client/managers/async_manager/crawl.py
@@ -7,6 +7,8 @@
 from ..job_fetch_utils import (
     collect_paginated_results_with_defaults_async,
     fetch_job_result_with_defaults_async,
+    read_page_current_batch,
+    read_page_total_batches,
 )
 from ..page_params_utils import build_page_batch_params
 from ..job_pagination_utils import (
@@ -119,12 +121,8 @@ async def start_and_wait(
                     page=page,
                 ),
             ),
-            get_current_page_batch=lambda page_response: (
-                page_response.current_page_batch
-            ),
-            get_total_page_batches=lambda page_response: (
-                page_response.total_page_batches
-            ),
+            get_current_page_batch=read_page_current_batch,
+            get_total_page_batches=read_page_total_batches,
             on_page_success=build_job_paginated_page_merge_callback(
                 job_response=job_response,
                 total_counter_attr="total_crawled_pages",
diff --git a/hyperbrowser/client/managers/async_manager/scrape.py b/hyperbrowser/client/managers/async_manager/scrape.py
@@ -7,6 +7,8 @@
 from ..job_fetch_utils import (
     collect_paginated_results_with_defaults_async,
     fetch_job_result_with_defaults_async,
+    read_page_current_batch,
+    read_page_total_batches,
 )
 from ..page_params_utils import build_page_batch_params
 from ..job_pagination_utils import (
@@ -129,12 +131,8 @@ async def start_and_wait(
                     page=page,
                 ),
             ),
-            get_current_page_batch=lambda page_response: (
-                page_response.current_page_batch
-            ),
-            get_total_page_batches=lambda page_response: (
-                page_response.total_page_batches
-            ),
+            get_current_page_batch=read_page_current_batch,
+            get_total_page_batches=read_page_total_batches,
             on_page_success=build_job_paginated_page_merge_callback(
                 job_response=job_response,
                 total_counter_attr="total_scraped_pages",
diff --git a/hyperbrowser/client/managers/async_manager/web/batch_fetch.py b/hyperbrowser/client/managers/async_manager/web/batch_fetch.py
@@ -19,6 +19,8 @@
 from ...job_fetch_utils import (
     collect_paginated_results_with_defaults_async,
     fetch_job_result_with_defaults_async,
+    read_page_current_batch,
+    read_page_total_batches,
 )
 from ....polling import (
     poll_until_terminal_status_async,
@@ -115,12 +117,8 @@ async def start_and_wait(
                     page=page,
                 ),
             ),
-            get_current_page_batch=lambda page_response: (
-                page_response.current_page_batch
-            ),
-            get_total_page_batches=lambda page_response: (
-                page_response.total_page_batches
-            ),
+            get_current_page_batch=read_page_current_batch,
+            get_total_page_batches=read_page_total_batches,
             on_page_success=build_paginated_page_merge_callback(
                 job_response=job_response,
             ),
diff --git a/hyperbrowser/client/managers/async_manager/web/crawl.py b/hyperbrowser/client/managers/async_manager/web/crawl.py
@@ -19,6 +19,8 @@
 from ...job_fetch_utils import (
     collect_paginated_results_with_defaults_async,
     fetch_job_result_with_defaults_async,
+    read_page_current_batch,
+    read_page_total_batches,
 )
 from ....polling import (
     poll_until_terminal_status_async,
@@ -113,12 +115,8 @@ async def start_and_wait(
                     page=page,
                 ),
             ),
-            get_current_page_batch=lambda page_response: (
-                page_response.current_page_batch
-            ),
-            get_total_page_batches=lambda page_response: (
-                page_response.total_page_batches
-            ),
+            get_current_page_batch=read_page_current_batch,
+            get_total_page_batches=read_page_total_batches,
             on_page_success=build_paginated_page_merge_callback(
                 job_response=job_response,
             ),
diff --git a/hyperbrowser/client/managers/job_fetch_utils.py b/hyperbrowser/client/managers/job_fetch_utils.py
@@ -1,4 +1,4 @@
-from typing import Awaitable, Callable, Optional, TypeVar
+from typing import Any, Awaitable, Callable, Optional, TypeVar
 
 from hyperbrowser.models.consts import POLLING_ATTEMPTS
 
@@ -62,6 +62,14 @@ async def fetch_job_result_with_defaults_async(
     )
 
 
+def read_page_current_batch(page_response: Any) -> int:
+    return page_response.current_page_batch
+
+
+def read_page_total_batches(page_response: Any) -> int:
+    return page_response.total_page_batches
+
+
 def collect_paginated_results_with_defaults(
     *,
     operation_name: str,
diff --git a/hyperbrowser/client/managers/sync_manager/crawl.py b/hyperbrowser/client/managers/sync_manager/crawl.py
@@ -7,6 +7,8 @@
 from ..job_fetch_utils import (
     collect_paginated_results_with_defaults,
     fetch_job_result_with_defaults,
+    read_page_current_batch,
+    read_page_total_batches,
 )
 from ..page_params_utils import build_page_batch_params
 from ..job_pagination_utils import (
@@ -119,12 +121,8 @@ def start_and_wait(
                     page=page,
                 ),
             ),
-            get_current_page_batch=lambda page_response: (
-                page_response.current_page_batch
-            ),
-            get_total_page_batches=lambda page_response: (
-                page_response.total_page_batches
-            ),
+            get_current_page_batch=read_page_current_batch,
+            get_total_page_batches=read_page_total_batches,
             on_page_success=build_job_paginated_page_merge_callback(
                 job_response=job_response,
                 total_counter_attr="total_crawled_pages",
diff --git a/hyperbrowser/client/managers/sync_manager/scrape.py b/hyperbrowser/client/managers/sync_manager/scrape.py
@@ -7,6 +7,8 @@
 from ..job_fetch_utils import (
     collect_paginated_results_with_defaults,
     fetch_job_result_with_defaults,
+    read_page_current_batch,
+    read_page_total_batches,
 )
 from ..page_params_utils import build_page_batch_params
 from ..job_pagination_utils import (
@@ -127,12 +129,8 @@ def start_and_wait(
                     page=page,
                 ),
             ),
-            get_current_page_batch=lambda page_response: (
-                page_response.current_page_batch
-            ),
-            get_total_page_batches=lambda page_response: (
-                page_response.total_page_batches
-            ),
+            get_current_page_batch=read_page_current_batch,
+            get_total_page_batches=read_page_total_batches,
             on_page_success=build_job_paginated_page_merge_callback(
                 job_response=job_response,
                 total_counter_attr="total_scraped_pages",
diff --git a/hyperbrowser/client/managers/sync_manager/web/batch_fetch.py b/hyperbrowser/client/managers/sync_manager/web/batch_fetch.py
@@ -19,6 +19,8 @@
 from ...job_fetch_utils import (
     collect_paginated_results_with_defaults,
     fetch_job_result_with_defaults,
+    read_page_current_batch,
+    read_page_total_batches,
 )
 from ....polling import (
     poll_until_terminal_status,
@@ -113,12 +115,8 @@ def start_and_wait(
                     page=page,
                 ),
             ),
-            get_current_page_batch=lambda page_response: (
-                page_response.current_page_batch
-            ),
-            get_total_page_batches=lambda page_response: (
-                page_response.total_page_batches
-            ),
+            get_current_page_batch=read_page_current_batch,
+            get_total_page_batches=read_page_total_batches,
             on_page_success=build_paginated_page_merge_callback(
                 job_response=job_response,
             ),
diff --git a/hyperbrowser/client/managers/sync_manager/web/crawl.py b/hyperbrowser/client/managers/sync_manager/web/crawl.py
@@ -19,6 +19,8 @@
 from ...job_fetch_utils import (
     collect_paginated_results_with_defaults,
     fetch_job_result_with_defaults,
+    read_page_current_batch,
+    read_page_total_batches,
 )
 from ....polling import (
     poll_until_terminal_status,
@@ -113,12 +115,8 @@ def start_and_wait(
                     page=page,
                 ),
             ),
-            get_current_page_batch=lambda page_response: (
-                page_response.current_page_batch
-            ),
-            get_total_page_batches=lambda page_response: (
-                page_response.total_page_batches
-            ),
+            get_current_page_batch=read_page_current_batch,
+            get_total_page_batches=read_page_total_batches,
             on_page_success=build_paginated_page_merge_callback(
                 job_response=job_response,
             ),
diff --git a/tests/test_job_fetch_helper_usage.py b/tests/test_job_fetch_helper_usage.py
@@ -25,9 +25,13 @@ def test_sync_managers_use_job_fetch_helpers_with_defaults():
         module_text = Path(module_path).read_text(encoding="utf-8")
         assert "fetch_job_result_with_defaults(" in module_text
         assert "collect_paginated_results_with_defaults(" in module_text
+        assert "read_page_current_batch" in module_text
+        assert "read_page_total_batches" in module_text
         assert "retry_operation(" not in module_text
         assert "collect_paginated_results(" not in module_text
         assert "build_fetch_operation_name(" not in module_text
+        assert "get_current_page_batch=lambda page_response:" not in module_text
+        assert "get_total_page_batches=lambda page_response:" not in module_text
         assert "max_attempts=POLLING_ATTEMPTS" not in module_text
         assert "retry_delay_seconds=0.5" not in module_text
 
@@ -37,8 +41,12 @@ def test_async_managers_use_job_fetch_helpers_with_defaults():
         module_text = Path(module_path).read_text(encoding="utf-8")
         assert "fetch_job_result_with_defaults_async(" in module_text
         assert "collect_paginated_results_with_defaults_async(" in module_text
+        assert "read_page_current_batch" in module_text
+        assert "read_page_total_batches" in module_text
         assert "retry_operation_async(" not in module_text
         assert "collect_paginated_results_async(" not in module_text
         assert "build_fetch_operation_name(" not in module_text
+        assert "get_current_page_batch=lambda page_response:" not in module_text
+        assert "get_total_page_batches=lambda page_response:" not in module_text
         assert "max_attempts=POLLING_ATTEMPTS" not in module_text
         assert "retry_delay_seconds=0.5" not in module_text
diff --git a/tests/test_job_fetch_utils.py b/tests/test_job_fetch_utils.py
@@ -1,4 +1,5 @@
 import asyncio
+from types import SimpleNamespace
 
 import hyperbrowser.client.managers.job_fetch_utils as job_fetch_utils
 
@@ -159,3 +160,19 @@ async def _fake_retry_operation_with_defaults_async(**kwargs):
 
     assert result == {"ok": True}
     assert captured_kwargs["operation_name"] == "Fetching crawl job abc"
+
+
+def test_read_page_current_batch_reads_attribute() -> None:
+    response = SimpleNamespace(current_page_batch=3)
+
+    result = job_fetch_utils.read_page_current_batch(response)
+
+    assert result == 3
+
+
+def test_read_page_total_batches_reads_attribute() -> None:
+    response = SimpleNamespace(total_page_batches=7)
+
+    result = job_fetch_utils.read_page_total_batches(response)
+
+    assert result == 7
