Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
Python ai-agentsai-toolsbrowser-agentbrowser-automationbrowser-usecdpcloud-browsercomputer-useheadless-browserllmmcpplaywrightpythonremote-browserstealth-browserweb-automationweb-scraping
Document repeated item extraction helper
Magnus Müller37f5b669b4e9
diff --git a/RUST_AGENT_INTEGRATION_FEATURES.md b/RUST_AGENT_INTEGRATION_FEATURES.mdindex e719704d6..f6f9d6ed9 100644--- a/RUST_AGENT_INTEGRATION_FEATURES.md+++ b/RUST_AGENT_INTEGRATION_FEATURES.md@@ -251,6 +251,11 @@ Terminal core branch: `magnus/browser-use-rust-integration` at latest pulled mai- The helper fetches multiple URLs concurrently in the loaded page context, preserves input order, returns per-URL JSON/text/binary records, and converts BrowserProfile-blocked absolute URLs into per-row errors without sending them to page JavaScript.- Proof: `browser_script_browser_fetch_many_preserves_order_errors_and_binary`.+49. Browser-script repeated item extraction helper+ - Terminal browser scripts now expose `repeated_items_snapshot(min_count=3, limit=8, include_prices=True)` and `extract_repeated_items(selector, limit=50, include_html=False)`.+ - The helper finds repeated visible cards/list items using stable selectors and extracts actionable records with attributes, headings, labels, prices, row/cell headers, links/buttons, and image/lazy-load metadata.+ - Proof: `browser_script_repeated_item_helpers_surface_actionable_records`.+## Current Verification- `python3 -m py_compile browser_use/rust/service.py browser_use/rust/__init__.py browser_use/__init__.py tests/ci/test_rust_agent.py examples/rust_agent/basic.py examples/rust_agent/real_v8_smoke.py`@@ -277,6 +282,7 @@ Terminal core branch: `magnus/browser-use-rust-integration` at latest pulled mai- `CARGO_INCREMENTAL=0 cargo test -q -p browser-use-browser browser_script_http_get_many_preserves_order_errors_and_binary -- --nocapture`- `CARGO_INCREMENTAL=0 cargo test -q -p browser-use-browser browser_script_browser_fetch_uses_page_context_credentials -- --nocapture`- `CARGO_INCREMENTAL=0 cargo test -q -p browser-use-browser browser_script_browser_fetch_many_preserves_order_errors_and_binary -- --nocapture`+- `CARGO_INCREMENTAL=0 cargo test -q -p browser-use-browser browser_script_repeated_item_helpers_surface_actionable_records -- --nocapture`- Managed-headless end-to-end:- `BROWSER_USE_TERMINAL_BINARY=/home/exedev/Developer/terminal/target/debug/browser-use-terminal BROWSER_USE_RUST_BROWSER_MODE=managed-headless BU_TASK='Open https://example.com and report the page title only.' BU_MAX_STEPS=12 timeout 300 uv run python examples/rust_agent/basic.py`- Output: `Example Domain`