def solve_text_captcha(image_bytes): response = rekognition.detect_text(Image='Bytes': image_bytes) detected_text = ' '.join([item['DetectedText'] for item in response['TextDetections']]) return detected_text
Better to use or EC2 for persistent browser. 9. Managing Cost and Scale | Approach | Cost | Speed | Accuracy | |----------|------|-------|----------| | AWS Rekognition | $0.001/image | Very fast | Low (only simple text) | | 2Captcha (API) | ~$1.50/1000 | 10–20 sec | High (human solvers) | | Custom ML (SageMaker) | High (training + inference) | Fast | Medium (site-specific) | | Browser automation (EC2) | $0.01/hour | Slow | Depends on solver service | aws captcha solver
# 2. Submit to 2Captcha (external service) api_key = "YOUR_2CAPTCHA_KEY" submit_res = requests.post("http://2captcha.com/in.php", data= "key": api_key, "method": "base64", "body": img_data.encode('base64'), "json": 1 ) def solve_text_captcha(image_bytes): response = rekognition
import boto3 rekognition = boto3.client('rekognition') data= "key": api_key
# 1. Download image img_data = requests.get(captcha_url).content
# 3. Poll for result captcha_id = submit_res.json()['request'] solution = None for _ in range(30): result = requests.get(f"http://2captcha.com/res.php?key=api_key&action=get&id=captcha_id&json=1") if result.json()['status'] == 1: solution = result.json()['request'] break time.sleep(2)