harivansh-afk/sandbox-agent
1
0
Fork 0
mirror of https://github.com/harivansh-afk/sandbox-agent.git synced 2026-04-15 06:04:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: [US-030] - Fix crawl page load: replace sleep with readyState polling

Browse source 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Nathan Flurry 2026-03-17 15:15:35 -07:00
parent b582555b7c
commit 117b9c2c42
1 changed files with 30 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

32
server/packages/sandbox-agent/src/browser_crawl.rs
View file

@ -57,8 +57,36 @@ pub async fn crawl_pages(
let status = nav_result.get("frameId").map(|_| 200u16);
// Wait for load.
tokio::time::sleep(std::time::Duration::from_millis(500)).await;
// Wait for page load by polling document.readyState until "complete".
// Polls every 100ms with a 10s timeout; proceeds with extraction if timeout reached.
let poll_interval = std::time::Duration::from_millis(100);
let load_timeout = std::time::Duration::from_secs(10);
let start_time = std::time::Instant::now();
loop {
if start_time.elapsed() >= load_timeout {
break;
}
let ready_result = cdp
.send(
"Runtime.evaluate",
Some(serde_json::json!({
"expression": "document.readyState",
"returnByValue": true
})),
)
.await;
if let Ok(val) = ready_result {
let state = val
.get("result")
.and_then(|r| r.get("value"))
.and_then(|v| v.as_str())
.unwrap_or("");
if state == "complete" {
break;
}
}
tokio::time::sleep(poll_interval).await;
}
// Get page info.
let (page_url, title) = get_page_info(cdp).await?;