Java
CsvFileCrawler crawler = new CsvFileCrawler();
crawler.setProperty("file", "file/example_utf8.csv");
List<Document> docs = crawler.crawlDocuments();
System.err.println(DocumentUtil.toJsonPrettyString(docs));
CSV File
DOCUMENTID,DATE,ITEM1,TEXT
001,2020-01-01,AAA,THIS IS TEST1.
002,2020-01-02,BBB,THIS IS TEST2.
003,2020-01-01,AAA,THIS IS TEST3.
Result
[
{
"DOCUMENTID": "001",
"DATE": "2020-01-01",
"ITEM1": "AAA",
"TEXT": "THIS IS TEST1.",
"keywords": []
},
{
"DOCUMENTID": "002",
"DATE": "2020-01-02",
"ITEM1": "BBB",
"TEXT": "THIS IS TEST2.",
"keywords": []
},
{
"DOCUMENTID": "003",
"DATE": "2020-01-01",
"ITEM1": "AAA",
"TEXT": "THIS IS TEST3.",
"keywords": []
}
]
Java Full Code
import java.util.List;
import nlp4j.Document;
import nlp4j.crawler.CsvFileCrawler;
import nlp4j.util.DocumentUtil;
public class CsvFileCrawlerExample {
public static void main(String[] args) throws Exception {
CsvFileCrawler crawler = new CsvFileCrawler();
crawler.setProperty("file", "file/example_utf8.csv");
List<Document> docs = crawler.crawlDocuments();
System.err.println(DocumentUtil.toJsonPrettyString(docs));
}
}
Comments