def main():
args = get_args()
tika = TikaApp(args.jar or os.environ.get("TIKA_APP_JAR", None))
parameters = {
"path": args.file,
"payload": args.payload,
"objectInput": sys.stdin if args.stdin else None
}
try:
if args.detect:
print(tika.detect_content_type(**parameters))
if args.text:
print(tika.extract_only_content(**parameters))
if args.language:
print(tika.detect_language(**parameters))
if args.all:
parameters["pretty_print"] = True
print(tika.extract_all_content(**parameters))
if args.metadata:
parameters["pretty_print"] = True
print(tika.extract_only_metadata(**parameters))
except IOError:
pass
def main():
args = get_args()
command_line = dict()
if args.jar:
command_line = {"TIKA_APP_JAR": args.jar}
defaults = {"TIKA_APP_JAR": "/opt/tika/tika-app-1.15.jar"}
options = ChainMap(command_line, os.environ, defaults)
tika = TikaApp(options['TIKA_APP_JAR'])
try:
if args.file:
f = args.file
if args.detect:
print(tika.detect_content_type(path=f))
if args.text:
print(tika.extract_only_content(path=f))
if args.language:
print(tika.detect_language(path=f))
if args.all:
print(tika.extract_all_content(path=f, pretty_print=True))
elif args.payload:
p = args.payload
if args.detect:
print(tika.detect_content_type(payload=p))
if args.text:
print(tika.extract_only_content(payload=p))
if args.language:
print(tika.detect_language(payload=p))
if args.all:
print(tika.extract_all_content(payload=p, pretty_print=True))
except IOError:
pass
class TikaReader(object):
def __init__(self, path):
self.tika_client = TikaApp(file_jar=path)
def detect_type(self, doc):
return self.tika_client.detect_content_type(doc)
def detect_language(self, doc):
return self.tika_client.detect_language(doc)
def content(self, doc):
return self.tika_client.extract_all_content(doc)
class TikaReader:
# Iniciador de la clase.
def __init__(self, file_process):
# Cliente Tika que utiliza que carga el fichero jar cliente.
self.tika_client = TikaApp(file_jar="tika-app-1.20.jar")
self.file_process = file_process
# Detector del tipo de contenido MIME.
def detect_document_type(self):
return self.tika_client.detect_content_type(self.file_process)
# Detector de lenguaje utilizado en el documento.
def detect_language(self):
return self.tika_client.detect_language(self.file_process)
# Extractor del contenido completo del documento.
def extract_complete_info(self, value=False):
return self.tika_client.extract_all_content(self.file_process,
convert_to_obj=value)
# Extractor de solo el contenido del documento.
def extract_content_info(self):
return self.tika_client.extract_only_content(self.file_process)
from tikapp import TikaApp
tika_client = TikaApp(
file_jar="/Users/yma2/Documents/_garage/python/cxm/tika/tika-app-1.20.jar")
analyzeFile = "/Users/yma2/Downloads/Azure_Developer_Guide_eBook_ja-JP.pdf"
print(tika_client.detect_content_type(analyzeFile))
print(tika_client.detect_language(analyzeFile))
print(tika_client.extract_only_content(analyzeFile))
print(tika_client.extract_only_metadata(analyzeFile))
def tika_detect_language():
tika_client = TikaApp(file_jar=TIKA_APP_JAR)
output = tika_client.detect_language(path=test_zip)
return output