| """Mind2Web (osunlp/Mind2Web from ModelScope) -> cases in this repo's format (page_obj with jev-style actions). |
| |
| python finetune/convert_mind2web.py finetune/data/mind2web/data/train/*.json finetune/out/m2w_cases.jsonl |
| |
| Each Mind2Web action becomes one case: goal = confirmed_task, history = previous action_reprs, gold = the positive |
| candidate; the element table = positive + up to MAX_NEG sampled negative candidates rendered like jev's snapshot.js |
| (label from text / aria-label / placeholder / alt / title / value, role from tag). |
| """ |
| import json, random, re, sys |
| from bs4 import BeautifulSoup |
|
|
| MAX_NEG = 44 |
| ROLE = {"a": "link", "button": "button", "input": "textbox", "textarea": "textbox", "select": "combobox", "option": "option", |
| "img": "img", "li": "listitem", "label": "label", "span": "generic", "div": "generic", "svg": "img", "h1": "heading", |
| "h2": "heading", "h3": "heading", "p": "text", "td": "cell", "th": "columnheader", "tr": "row", "ul": "list"} |
|
|
|
|
| def label_of(el): |
| attrs = el.attrs |
| for k in ("aria-label", "placeholder", "alt", "title"): |
| v = attrs.get(k) |
| if isinstance(v, list): v = " ".join(v) |
| if v and v.strip(): return v.strip() |
| txt = " ".join(el.get_text(" ", strip=True).split()) |
| if txt: return txt[:80] |
| v = attrs.get("value") |
| if v: return str(v).strip()[:80] |
| return (attrs.get("name") or attrs.get("id") or el.name or "")[:60] |
|
|
|
|
| def kind_of(el, op): |
| t = el.name |
| typ = (el.attrs.get("type") or "").lower() |
| if t == "select": return "select" |
| if t == "textarea" or (t == "input" and typ in ("", "text", "search", "email", "password", "number", "tel", "url")) or el.attrs.get("contenteditable"): |
| return "fill" |
| return "click" |
|
|
|
|
| def convert_action(task, ai, action, rng): |
| soup = BeautifulSoup(action["cleaned_html"], "lxml") |
| by_id = {} |
| for el in soup.find_all(attrs={"backend_node_id": True}): |
| by_id[el.attrs["backend_node_id"]] = el |
| pos = action["pos_candidates"] |
| if not pos: return None |
| gold_el = by_id.get(pos[0]["backend_node_id"]) |
| if gold_el is None: return None |
| negs = [c for c in action["neg_candidates"] if c["backend_node_id"] in by_id] |
| rng.shuffle(negs) |
| cands = [pos[0]] + negs[:MAX_NEG] |
| rng.shuffle(cands) |
| op = action["operation"]["op"] |
| |
| filled = {} |
| for r in task["action_reprs"][:ai]: |
| m = re.match(r"\[(\w+)\]\s+(.*?)\s+->\s+(TYPE|SELECT):\s*(.*)$", r) |
| if m: filled[" ".join(m.group(2).split()).lower()] = m.group(4).strip() |
| actions, gold_id, node = [], None, 0 |
| for c in cands: |
| el = by_id[c["backend_node_id"]] |
| lab = label_of(el) |
| if not lab: continue |
| node += 1 |
| is_gold = c["backend_node_id"] == pos[0]["backend_node_id"] |
| kind = {"CLICK": "click", "TYPE": "fill", "SELECT": "select"}[op] if is_gold else kind_of(el, op) |
| role = ROLE.get(el.name, "generic") |
| base = {"node": node, "label": lab, "role": role} |
| if kind == "select": |
| opts = [o.get_text(" ", strip=True) for o in el.find_all("option")][:8] or [action["operation"]["value"] or "option"] |
| if is_gold and action["operation"]["value"] and action["operation"]["value"] not in opts: |
| opts = [action["operation"]["value"]] + opts[:7] |
| for oi, o in enumerate(opts): |
| a = {**base, "id": f"select:{node}:{oi}", "kind": "select", "value": o, "label": f"{lab} → {o}", "current_value": ""} |
| actions.append(a) |
| if is_gold and (o == action["operation"]["value"] or (oi == 0 and not action["operation"]["value"])): gold_id = a["id"] |
| continue |
| a = {**base, "id": f"{kind}:{node}", "kind": kind} |
| if kind == "fill": |
| a["value"] = filled.get(lab.lower(), "") |
| a["current_value"] = a["value"] |
| actions.append(a) |
| if is_gold: gold_id = a["id"] |
| if gold_id is None: return None |
| for k, lab in (("wait", "Wait for the page to update"), ("scroll_down", "Scroll down"), ("scroll_up", "Scroll up")): |
| actions.append({"id": k, "kind": "wait" if k == "wait" else "scroll", "label": lab, "node": None, "delta": 600 if k == "scroll_down" else -600}) |
| text = " ".join(soup.get_text(" ", strip=True).split())[:6000] |
| hist = [] |
| for r in task["action_reprs"][:ai]: |
| lab_, _, opv = r.rpartition(" -> ") |
| kind_, _, val = opv.partition(": ") |
| hist.append({"action": lab_.strip(), "kind": {"CLICK": "click", "TYPE": "fill", "SELECT": "select"}.get(kind_, kind_.lower()), |
| "text": val or None, "page_changed": kind_ == "CLICK"}) |
| gold_op = {"CLICK": "CLICK", "TYPE": "TYPE_TEXT", "SELECT": "SELECT"}[op] |
| return {"page": -1, "url": f"https://{task['website']}.com/", "title": task["website"], "goal": task["confirmed_task"], "gold_op": gold_op, |
| "gold_id": gold_id, "kind": {"CLICK": "click", "TYPE": "fill", "SELECT": "select"}[op], "label": label_of(gold_el), "history": hist, |
| "source": "mind2web", "task_id": task["annotation_id"], "website": task["website"], |
| "page_obj": {"url": f"https://{task['website']}.com/", "title": task["website"], "text": text, "actions": actions}} |
|
|
|
|
| def main(): |
| files, out = sys.argv[1:-1], sys.argv[-1] |
| rng = random.Random(0); n = 0; skipped = 0 |
| with open(out, "w") as f: |
| for fn in files: |
| tasks = json.load(open(fn)) |
| for t in tasks: |
| for ai, a in enumerate(t["actions"]): |
| c = convert_action(t, ai, a, rng) |
| if c is None: skipped += 1; continue |
| f.write(json.dumps(c, ensure_ascii=False) + "\n"); n += 1 |
| print(f"{fn}: total {n} cases, skipped {skipped}", flush=True) |
| print("wrote", n) |
|
|
| if __name__ == "__main__": |
| main() |
|
|
