chore: Further reduce retry error summary in log (#1370)

### Description

- Further reduce retry error summary in log - no more multiline
- Ignore details of `Playwrigth` internal errors in warning summary
### Issues


- Closes: #1325

Author: Pijukatel

src/crawlee/crawlers/_basic/_basic_crawler.py

@@ -1031,8 +1031,9 @@ async def _handle_request_retries(
 
         if self._should_retry_request(context, error):
             request.retry_count += 1
+            reduced_error = str(error).split('\n')[0]
             self.log.warning(
-                f'Retrying request to {context.request.url} due to: {error} \n'
+                f'Retrying request to {context.request.url} due to: {reduced_error}'
                 f'{get_one_line_error_summary_if_possible(error)}'
             )
             await self._statistics.error_tracker.add(error=error, context=context)

src/crawlee/crawlers/_basic/_logging_utils.py

@@ -49,7 +49,11 @@ def _get_traceback_parts_for_innermost_exception(error: Exception) -> list[str]:
 
 def get_one_line_error_summary_if_possible(error: Exception) -> str:
     if isinstance(error, asyncio.exceptions.TimeoutError):
-        most_relevant_part = reduce_asyncio_timeout_error_to_relevant_traceback_parts(error)[-1]
+        most_relevant_part = ',' + reduce_asyncio_timeout_error_to_relevant_traceback_parts(error)[-1]
+    elif 'playwright._impl._errors.Error' in str(error.__class__):
+        # Playwright autogenerated errors are often very long, so we do not try to summarize them at all as they anyway
+        # point to deep internals.
+        return ''
     else:
         traceback_parts = _get_traceback_parts_for_innermost_exception(error)
         # Commonly last traceback part is type of the error, and the second last part is the relevant file.

tests/unit/crawlers/_basic/test_basic_crawler.py

@@ -1368,7 +1368,7 @@ async def handler(context: BasicCrawlingContext) -> None:
     for record in caplog.records:
         if record.message and 'timed out after 1.0 seconds' in record.message:
             full_message = (record.message or '') + (record.exc_text or '')
-            assert Counter(full_message)['\n'] < 10
+            assert '\n' not in full_message
             assert '# INJECTED DELAY' in full_message
             found_timeout_message = True
             break

tests/unit/crawlers/_playwright/test_playwright_crawler.py

@@ -5,6 +5,7 @@
 from __future__ import annotations
 
 import json
+import logging
 from typing import TYPE_CHECKING, Any, Literal
 from unittest import mock
 from unittest.mock import Mock
@@ -758,3 +759,28 @@ async def request_handler(context: PlaywrightCrawlingContext) -> None:
 
     assert len(extracted_links) == 1
     assert extracted_links[0] == str(server_url / 'page_1')
+
+
+async def test_reduced_logs_from_playwright_navigation_timeout(caplog: pytest.LogCaptureFixture) -> None:
+    caplog.set_level(logging.INFO)
+    crawler = PlaywrightCrawler(configure_logging=False)
+    non_existent_page = 'https://totally-non-existing-site.com/blablablba'
+
+    # Capture all logs from the 'crawlee' logger at INFO level or higher
+    with caplog.at_level(logging.INFO, logger='crawlee'):
+        await crawler.run([Request.from_url(non_existent_page)])
+
+    expected_summarized_log = (
+        f'Retrying request to {non_existent_page} due to: Page.goto: net::ERR_NAME_NOT_RESOLVED at {non_existent_page}'
+    )
+
+    # Find the Playwright specific error message in the logs
+    found_playwright_message = False
+    for record in caplog.records:
+        if record.message and expected_summarized_log in record.message:
+            full_message = (record.message or '') + (record.exc_text or '')
+            assert '\n' not in full_message
+            found_playwright_message = True
+            break
+
+    assert found_playwright_message, 'Expected log message about request handler error was not found.'