{"id":72998,"library":"tika-parsers-standard-package","title":"Apache Tika Parsers Standard Package","description":"Apache Tika is a toolkit for detecting and extracting metadata and structured text content from various documents using existing parser libraries.","status":"active","version":"3.3.0","language":"java","source_language":null,"source_url":"https://github.com/apache/tika","tags":["apache","tika","parsing","content-extraction","document"],"install":[{"cmd":"<dependency>\n  <groupId>org.apache.tika</groupId>\n  <artifactId>tika-parsers-standard-package</artifactId>\n  <version>3.3.0</version>\n</dependency>","lang":"xml","label":"Maven"},{"cmd":"implementation 'org.apache.tika:tika-parsers-standard-package:3.3.0'","lang":"groovy","label":"Gradle"}],"dependencies":[],"imports":[{"symbol":"AutoDetectParser","correct":"org.apache.tika.parser.AutoDetectParser"}],"quickstart":{"code":"import org.apache.tika.parser.AutoDetectParser;\nimport org.apache.tika.metadata.Metadata;\nimport org.apache.tika.sax.BodyContentHandler;\nimport org.xml.sax.ContentHandler;\n\npublic class Main {\n    public static void main(String[] args) throws Exception {\n        AutoDetectParser parser = new AutoDetectParser();\n        ContentHandler handler = new BodyContentHandler();\n        Metadata metadata = new Metadata();\n        parser.parse(new java.io.FileInputStream(\"document.pdf\"), handler, metadata);\n        System.out.println(handler.toString());\n    }\n}","lang":"java","description":"Parses a document and extracts text."},"warnings":[],"env_vars":null,"search_vec":"'apach':1,6,27 'content':19,31 'content-extract':30 'detect':12 'document':22,33 'exist':24 'extract':14,32 'librari':26 'metadata':15 'packag':5 'pars':29 'parser':3,25 'standard':4 'structur':17 'text':18 'tika':2,7,28 'toolkit':10 'use':23 'various':21","created_at":"2026-06-17T18:46:12.930420+00:00","updated_at":"2026-06-17T18:46:12.930420+00:00","problems":[],"ecosystem":"maven","meta_description":null,"install_score":null,"quickstart_score":null,"quickstart_tag":null,"pypi_latest":null,"cli_name":null,"cli_version":null,"type":"library","homepage":"https://tika.apache.org/","github":"https://github.com/apache/tika","docs":"https://appdoc.app/artifact/org.apache.tika/tika-parsers-standard-package/","changelog":null,"pypi":null,"npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"categories":["utility"],"base_url":null,"auth_type":null,"provenance":{"verified_status":null,"verified_at":null,"last_verified":"2026-06-17","next_check":"2026-12-14","install_tag":null}}