feat(text): frame-aware text extraction — get text --all-frames / --main + frames (#27)

On listing/marketplace pages (Yahoo Auctions, Rakuten, Mercari shops) the
seller's description lives in a child frame or under a related-items sidebar,
so 'get text body' returned only header/nav boilerplate.

- get text --all-frames: aggregate visible text across every reachable frame.
  Same-process child frames are read via Page.createIsolatedWorld; OOPIFs via
  their auto-attached debugger session (iframe_sessions). Each non-top frame is
  labelled with a '----- frame [kind] url -----' separator.
- get text --main: readability-lite — prefer the densest <main>/<article>
  region over the whole body, dropping global header/nav/footer chrome.
- frames: enumerate frames (kind + url + per-frame text length) so an agent can
  see where a page's text actually lives and pick the right read.

Verified live: inline srcdoc frame text aggregated through --all-frames; Yahoo
Auctions <main> (2881 chars) extracted via --main, stripping the Yahoo header.
This commit is contained in:
leeguooooo
2026-06-15 12:51:59 +09:00
parent f7a657ac46
commit 2707ceb1c4
5 changed files with 370 additions and 1 deletions
+63 -1
View File
@@ -1296,6 +1296,11 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
// === Get ===
"get" => parse_get(&rest, &id),
// List every frame the session can reach (top + same-process child
// frames + out-of-process iframes), with a text-length per frame so you
// can see where a listing's description actually lives (issue #27).
"frames" => Ok(json!({ "id": id, "action": "frames" })),
// Top-level shortcuts for `get <x>` status reads — users naturally type
// `chrome-use url` / `cdp-url` / `title` without the `get` prefix
// (and expect `cdp-url`/`cdp_url` to work interchangeably).
@@ -2388,10 +2393,32 @@ fn parse_get(rest: &[&str], id: &str) -> Result<Value, ParseError> {
match rest.first().copied() {
Some("text") => {
// `get text --all-frames` aggregates visible text across every
// frame, including out-of-process iframes invisible to the top
// document (issue #27). The selector is ignored in this mode.
let all_frames = rest[1..]
.iter()
.any(|a| matches!(*a, "--all-frames" | "--frames" | "-a"));
if all_frames {
return Ok(json!({ "id": id, "action": "gettext", "allFrames": true }));
}
// `get text --main` returns the main-content region (readability),
// skipping header/nav/footer/sidebar boilerplate (issue #27).
let main = rest[1..]
.iter()
.any(|a| matches!(*a, "--main" | "--readable" | "-m"));
if main {
return Ok(json!({ "id": id, "action": "gettext", "main": true }));
}
// `get text` with no selector returns the whole page's text (body) —
// a common convenience; previously it errored without a selector
// (issue #24-D).
let sel = rest.get(1).copied().unwrap_or("body");
let sel = rest
.iter()
.skip(1)
.find(|a| !a.starts_with("--"))
.copied()
.unwrap_or("body");
Ok(json!({ "id": id, "action": "gettext", "selector": sel }))
}
Some("html") => {
@@ -4761,6 +4788,41 @@ mod tests {
assert_eq!(cmd2["selector"], "h1");
}
#[test]
fn test_get_text_all_frames() {
// `--all-frames` switches to whole-page, cross-frame aggregation and
// drops the selector (issue #27).
for variant in ["get text --all-frames", "get text --frames", "text -a"] {
let cmd = parse_command(&args(variant), &default_flags()).unwrap();
assert_eq!(cmd["action"], "gettext", "{variant}");
assert_eq!(cmd["allFrames"], true, "{variant}");
assert!(cmd.get("selector").is_none(), "{variant}");
}
// A flag mixed with a selector still triggers all-frames.
let cmd = parse_command(&args("get text body --all-frames"), &default_flags()).unwrap();
assert_eq!(cmd["allFrames"], true);
// Without the flag, a leading flag-like token is skipped for the selector.
let cmd = parse_command(&args("get text main"), &default_flags()).unwrap();
assert_eq!(cmd["selector"], "main");
assert!(cmd.get("allFrames").is_none());
}
#[test]
fn test_frames_command() {
let cmd = parse_command(&args("frames"), &default_flags()).unwrap();
assert_eq!(cmd["action"], "frames");
}
#[test]
fn test_get_text_main() {
for variant in ["get text --main", "get text --readable", "text -m"] {
let cmd = parse_command(&args(variant), &default_flags()).unwrap();
assert_eq!(cmd["action"], "gettext", "{variant}");
assert_eq!(cmd["main"], true, "{variant}");
assert!(cmd.get("selector").is_none(), "{variant}");
}
}
#[test]
fn test_tab_activate_flag() {
let plain = parse_command(&args("tab t3"), &default_flags()).unwrap();