scriptoriumadmin/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-10-05 02:41:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

fix: close Playwright pages per-URL and browser in finally block

Browse source 
Pages created by browser.new_page() were not being closed after each
URL was processed. If an exception occurred during page.goto(), route
handling, or evaluation, the page remained open, leaking resources.

The browser was also only closed after the URL loop completed normally.
With continue_on_failure=False, an early exit would skip cleanup.

Changes:
- Add per-URL finally block to close each page after use
- Wrap the URL loop in try/finally to ensure browser.close() runs
  even when an exception propagates

Fixes #25880
This commit is contained in:
michaelxer 2026-06-10 06:23:19 +07:00
parent b1d40f3409
commit ceba1ee70c
1 changed files with 46 additions and 34 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

80
backend/open_webui/retrieval/web/utils.py
View file

@ -567,24 +567,30 @@ class SafePlaywrightURLLoader(PlaywrightURLLoader, RateLimitMixin, URLProcessing
else:
browser = p.chromium.launch(headless=self.headless, proxy=self.proxy)
for url in self.urls:
try:
self._safe_process_url_sync(url)
page = browser.new_page()
page.route('**/*', self._intercept_navigation_sync)
response = page.goto(url, timeout=self.playwright_timeout)
if response is None:
raise ValueError(f'page.goto() returned None for url {url}')
try:
for url in self.urls:
page = None
try:
self._safe_process_url_sync(url)
page = browser.new_page()
page.route('**/*', self._intercept_navigation_sync)
response = page.goto(url, timeout=self.playwright_timeout)
if response is None:
raise ValueError(f'page.goto() returned None for url {url}')
text = self.evaluator.evaluate(page, browser, response)
metadata = {'source': url}
yield Document(page_content=text, metadata=metadata)
except Exception as e:
if self.continue_on_failure:
log.exception(f'Error loading {url}: {e}')
continue
raise e
browser.close()
text = self.evaluator.evaluate(page, browser, response)
metadata = {'source': url}
yield Document(page_content=text, metadata=metadata)
except Exception as e:
if self.continue_on_failure:
log.exception(f'Error loading {url}: {e}')
continue
raise e
finally:
if page:
page.close()
finally:
browser.close()
async def alazy_load(self) -> AsyncIterator[Document]:
"""Safely load URLs asynchronously with support for remote browser."""
@ -597,24 +603,30 @@ class SafePlaywrightURLLoader(PlaywrightURLLoader, RateLimitMixin, URLProcessing
else:
browser = await p.chromium.launch(headless=self.headless, proxy=self.proxy)
for url in self.urls:
try:
await self._safe_process_url(url)
page = await browser.new_page()
await page.route('**/*', self._intercept_navigation)
response = await page.goto(url, timeout=self.playwright_timeout)
if response is None:
raise ValueError(f'page.goto() returned None for url {url}')
try:
for url in self.urls:
page = None
try:
await self._safe_process_url(url)
page = await browser.new_page()
await page.route('**/*', self._intercept_navigation)
response = await page.goto(url, timeout=self.playwright_timeout)
if response is None:
raise ValueError(f'page.goto() returned None for url {url}')
text = await self.evaluator.evaluate_async(page, browser, response)
metadata = {'source': url}
yield Document(page_content=text, metadata=metadata)
except Exception as e:
if self.continue_on_failure:
log.exception(f'Error loading {url}: {e}')
continue
raise e
await browser.close()
text = await self.evaluator.evaluate_async(page, browser, response)
metadata = {'source': url}
yield Document(page_content=text, metadata=metadata)
except Exception as e:
if self.continue_on_failure:
log.exception(f'Error loading {url}: {e}')
continue
raise e
finally:
if page:
await page.close()
finally:
await browser.close()
class SafeWebBaseLoader(WebBaseLoader):