Add pytesseract OCR, click_text interact action, and interact verify endpoint

examples/quickstart.py

@@ -35,6 +35,50 @@ def main():
     print("region:", payload["meta"]["region"])
     print("grid:", payload["meta"].get("grid", {}))
 
+    see_ocr = requests.post(
+        f"{BASE_URL}/see",
+        headers=headers,
+        json={"screen": SCREEN, "ocr": True, "with_grid": False, "ocr_min_confidence": 40},
+        timeout=30,
+    )
+    see_ocr.raise_for_status()
+    ocr_items = see_ocr.json()["data"]["meta"].get("ocr", [])
+    print("ocr_items:", len(ocr_items))
+
+    if ocr_items:
+        label = ocr_items[0]["text"]
+        click_text = requests.post(
+            f"{BASE_URL}/interact",
+            headers=headers,
+            json={
+                "screen": SCREEN,
+                "action": {"action": "click_text", "click_text": {"text": label, "match": "exact", "occurrence": "first"}},
+            },
+            timeout=30,
+        )
+        click_text.raise_for_status()
+        click_data = click_text.json()["data"]
+        target = click_data["resolved_target"]
+        verify = requests.post(
+            f"{BASE_URL}/interact/verify",
+            headers=headers,
+            json={
+                "action": {"screen": SCREEN, "action": {"action": "click", "target": {"mode": "pixel", "x": target["x"], "y": target["y"]}}},
+                "verify": {
+                    "type": "ocr_text_near_point",
+                    "text": label,
+                    "x": target["x"],
+                    "y": target["y"],
+                    "radius": 150,
+                    "screen": SCREEN,
+                },
+                "timeout_ms": 1500,
+            },
+            timeout=30,
+        )
+        verify.raise_for_status()
+        print("verify:", verify.json()["data"]["verified"])
+
 
 if __name__ == "__main__":
     main()