def deidentify_with_replace_infotype(project, item, info_types):
"""Uses the Data Loss Prevention API to deidentify sensitive data in a
string by replacing it with the info type.
Args:
project: The Google Cloud project id to use as a parent resource.
item: The string to deidentify (will be treated as text).
info_types: A list of strings representing info types to look for.
A full list of info type categories can be fetched from the API.
Returns:
None; the response from the API is printed to the terminal.
"""
# Import the client library
import google.cloud.dlp
# Instantiate a client
dlp = google.cloud.dlp_v2.DlpServiceClient()
# Convert the project id into a full resource id.
parent = f"projects/{project}"
# Construct inspect configuration dictionary
inspect_config = {"info_types": [{"name": info_type} for info_type in info_types]}
# Construct deidentify configuration dictionary
deidentify_config = {
"info_type_transformations": {
"transformations": [
{"primitive_transformation": {"replace_with_info_type_config": {}}}
]
}
}
# Call the API
response = dlp.deidentify_content(
request={
"parent": parent,
"deidentify_config": deidentify_config,
"inspect_config": inspect_config,
"item": {"value": item},
}
)
# Print out the results.
print(response.item.value)
