Skip to content

Python Example

Get text chunks

Get all the labels that match the document.

import json
import requests

api_host = 'https://api.lettria.com'
api_route = api_host + '/parse'

document_file_name = 'file.html'
document_file_location = './data/'

jwt_token_file = 'jwt_token.txt'
jwt_token = open(jwt_token_file, 'r').read()

chunks = []
with open(document_file_location + document_file_name, 'rb') as file:
    response = requests.post(
        api_route,
        files=[('file', ( document_file_name, file))],
        headers={"Authorization":"LettriaProKey " + jwt_token}
    ).json()
    chunks = response['chunks']

text_chunks = [ chunk for chunk in chunks if chunk['type'] == 'text' ]
print(json.dumps(text_chunks, indent=4, sort_keys=True))
text_content = '\n'.join([ chunk['content'] for chunk in text_chunks ])
print(text_content)

In this code, the document is sent to Lettria for parsing. ON it's return, text chunks are extracted and printed.

Next steps