Search a hash

Create a Webrisk client and search for a hash

Explore further

For detailed documentation that includes this code sample, see the following:

• Using the Update API

Code sample

Java

To authenticate to Web Risk, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import com.google.cloud.webrisk.v1.WebRiskServiceClient;
import com.google.protobuf.ByteString;
import com.google.webrisk.v1.SearchHashesRequest;
import com.google.webrisk.v1.SearchHashesResponse;
import com.google.webrisk.v1.SearchHashesResponse.ThreatHash;
import com.google.webrisk.v1.ThreatType;
import java.io.IOException;
import java.nio.charset.StandardCharsets;
import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;
import java.util.Arrays;
import java.util.Base64;
import java.util.List;

public class SearchHashes {

  public static void main(String[] args) throws IOException, NoSuchAlgorithmException {
    // TODO(developer): Replace these variables before running the sample.
    // A hash prefix, consisting of the most significant 4-32 bytes of a SHA256 hash.
    // For JSON requests, this field is base64-encoded. Note that if this parameter is provided
    // by a URI, it must be encoded using the web safe base64 variant (RFC 4648).
    String uri = "http://example.com";
    String encodedUri = Base64.getUrlEncoder().encodeToString(uri.getBytes(StandardCharsets.UTF_8));
    MessageDigest digest = MessageDigest.getInstance("SHA-256");
    byte[] encodedHashPrefix = digest.digest(encodedUri.getBytes(StandardCharsets.UTF_8));

    // The ThreatLists to search in. Multiple ThreatLists may be specified.
    // For the list on threat types, see: https://cloud.google.com/web-risk/docs/reference/rpc/google.cloud.webrisk.v1#threattype
    List<ThreatType> threatTypes = Arrays.asList(ThreatType.MALWARE, ThreatType.SOCIAL_ENGINEERING);

    searchHash(ByteString.copyFrom(encodedHashPrefix), threatTypes);
  }

  // Gets the full hashes that match the requested hash prefix.
  // This is used after a hash prefix is looked up in a threatList and there is a match.
  // The client side threatList only holds partial hashes so the client must query this method
  // to determine if there is a full hash match of a threat.
  public static void searchHash(ByteString encodedHashPrefix, List<ThreatType> threatTypes)
      throws IOException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the `webRiskServiceClient.close()` method on the client to safely
    // clean up any remaining background resources.
    try (WebRiskServiceClient webRiskServiceClient = WebRiskServiceClient.create()) {

      // Set the hashPrefix and the threat types to search in.
      SearchHashesResponse response = webRiskServiceClient.searchHashes(
          SearchHashesRequest.newBuilder()
              .setHashPrefix(encodedHashPrefix)
              .addAllThreatTypes(threatTypes)
              .build());

      // Get all the hashes that match the prefix. Cache the returned hashes until the time
      // specified in threatHash.getExpireTime()
      // For more information on response type, see: https://cloud.google.com/web-risk/docs/reference/rpc/google.cloud.webrisk.v1#threathash
      for (ThreatHash threatHash : response.getThreatsList()) {
        System.out.println(threatHash.getHash());
      }
      System.out.println("Completed searching threat hashes.");
    }
  }
}

Python

To authenticate to Web Risk, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

from google.cloud import webrisk_v1


def search_hashes(hash_prefix: bytes, threat_type: webrisk_v1.ThreatType) -> list:
    """Gets the full hashes that match the requested hash prefix.

    This is used after a hash prefix is looked up in a threatList and there is a match.
    The client side threatList only holds partial hashes so the client must query this method
    to determine if there is a full hash match of a threat.

    Args:
        hash_prefix: A hash prefix, consisting of the most significant 4-32 bytes of a SHA256 hash.
            For JSON requests, this field is base64-encoded. Note that if this parameter is provided
            by a URI, it must be encoded using the web safe base64 variant (RFC 4648).
            Example:
                uri = "http://example.com"
                sha256 = sha256()
                sha256.update(base64.urlsafe_b64encode(bytes(uri, "utf-8")))
                hex_string = sha256.digest()

        threat_type: The ThreatLists to search in. Multiple ThreatLists may be specified.
            For the list on threat types, see:
            https://cloud.google.com/web-risk/docs/reference/rpc/google.cloud.webrisk.v1#threattype
            threat_type = [webrisk_v1.ThreatType.MALWARE, webrisk_v1.ThreatType.SOCIAL_ENGINEERING]

    Returns:
        A hash list that contain all hashes that matches the given hash prefix.
    """
    webrisk_client = webrisk_v1.WebRiskServiceClient()

    # Set the hashPrefix and the threat types to search in.
    request = webrisk_v1.SearchHashesRequest()
    request.hash_prefix = hash_prefix
    request.threat_types = [threat_type]

    response = webrisk_client.search_hashes(request)

    # Get all the hashes that match the prefix. Cache the returned hashes until the time
    # specified in threat_hash.expire_time
    # For more information on response type, see:
    # https://cloud.google.com/web-risk/docs/reference/rpc/google.cloud.webrisk.v1#threathash
    hash_list = []
    for threat_hash in response.threats:
        hash_list.append(threat_hash.hash)
    return hash_list

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.