github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-22 19:09:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

community: PlaywrightURLLoader should wait for page load event before attempting to extract data (#30043)

Browse Source 
## Description

The PlaywrightURLLoader should wait for a page to be loaded before
attempting to extract data.
This commit is contained in:
Daniel Rauber
2025-02-28 14:45:51 +01:00
committed by GitHub
parent 46908ee3da
commit 186cd7f1a1
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
libs/community/langchain_community/document_loaders/url_playwright.py
View File

@@ -177,6 +177,8 @@ class PlaywrightURLLoader(BaseLoader):
if response is None: if response is None:
raise ValueError(f"page.goto() returned None for url {url}") raise ValueError(f"page.goto() returned None for url {url}")
page.wait_for_load_state("load")
text = self.evaluator.evaluate(page, browser, response) text = self.evaluator.evaluate(page, browser, response)
metadata = {"source": url} metadata = {"source": url}
yield Document(page_content=text, metadata=metadata) yield Document(page_content=text, metadata=metadata)
@@ -216,6 +218,8 @@ class PlaywrightURLLoader(BaseLoader):
if response is None: if response is None:
raise ValueError(f"page.goto() returned None for url {url}") raise ValueError(f"page.goto() returned None for url {url}")
await page.wait_for_load_state("load")
text = await self.evaluator.evaluate_async(page, browser, response) text = await self.evaluator.evaluate_async(page, browser, response)
metadata = {"source": url} metadata = {"source": url}
yield Document(page_content=text, metadata=metadata) yield Document(page_content=text, metadata=metadata)