Wrapper for NLP library Natasha (txt2json + http server )
depends on https://github.com/natasha
ner2json.py [filename] - converts text file to json with names
ner2json_server.py [port] - listens for requests https://xxx:port/?text=... with reply in json - for running on multiply servers/parallel processing
Example:
request:
reply:
{"items":[{"normal":"\u041a\u0430\u043c\u0430\u043b\u0430 \u0425\u0430\u0440\u0440\u0438\u0441","first":"\u041a\u0430\u043c\u0430\u043b\u0430","last":"\u0425\u0430\u0440\u0440\u0438\u0441"}]}
Used for russian youtube/rutube video descriptoin processing