fix(crawler): handle navigation aborts during file downloads in AsyncPlaywrightCrawlerStrategy
This commit is contained in:
@@ -582,7 +582,17 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
|
|||||||
)
|
)
|
||||||
redirected_url = page.url
|
redirected_url = page.url
|
||||||
except Error as e:
|
except Error as e:
|
||||||
raise RuntimeError(f"Failed on navigating ACS-GOTO:\n{str(e)}")
|
# Allow navigation to be aborted when downloading files
|
||||||
|
# This is expected behavior for downloads in some browser engines
|
||||||
|
if 'net::ERR_ABORTED' in str(e) and self.browser_config.accept_downloads:
|
||||||
|
self.logger.info(
|
||||||
|
message=f"Navigation aborted, likely due to file download: {url}",
|
||||||
|
tag="GOTO",
|
||||||
|
params={"url": url},
|
||||||
|
)
|
||||||
|
response = None
|
||||||
|
else:
|
||||||
|
raise RuntimeError(f"Failed on navigating ACS-GOTO:\n{str(e)}")
|
||||||
|
|
||||||
await self.execute_hook(
|
await self.execute_hook(
|
||||||
"after_goto", page, context=context, url=url, response=response, config=config
|
"after_goto", page, context=context, url=url, response=response, config=config
|
||||||
|
|||||||
Reference in New Issue
Block a user