Я использую Tika для чтения PDF-файлов, и мой код работал до вчерашнего дня. Теперь, когда я запускаю один и тот же код, я получаю ошибки, и, видимо, Тика не может найти файл jar сервера Тика. Я использую следующий код для чтения PDF
import tika
from tika import parser
tika.initVM()
parsed = parser.from_file('my_pdf_file.pdf')
Ошибка трассировки ниже
2019-06-22 05:54:08,735 [MainThread ] [INFO ] Retrieving http://search.maven.org/remotecontent?filepath=org/apache/tika/tika-server/1.19/tika-server-1.19.jar to /tmp/tika-server.jar.
---------------------------------------------------------------------------
HTTPError Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/tika/tika.py in getRemoteJar(urlOrPath, destPath)
715 try:
--> 716 urlretrieve(urlOrPath, destPath)
717 except IOError:
19 frames
/usr/lib/python3.6/urllib/request.py in urlretrieve(url, filename, reporthook, data)
247
--> 248 with contextlib.closing(urlopen(url, data)) as fp:
249 headers = fp.info()
/usr/lib/python3.6/urllib/request.py in urlopen(url, data, timeout, cafile, capath, cadefault, context)
222 opener = _opener
--> 223 return opener.open(url, data, timeout)
224
/usr/lib/python3.6/urllib/request.py in open(self, fullurl, data, timeout)
531 meth = getattr(processor, meth_name)
--> 532 response = meth(req, response)
533
/usr/lib/python3.6/urllib/request.py in http_response(self, request, response)
641 response = self.parent.error(
--> 642 'http', request, response, code, msg, hdrs)
643
/usr/lib/python3.6/urllib/request.py in error(self, proto, *args)
569 args = (dict, 'default', 'http_error_default') + orig_args
--> 570 return self._call_chain(*args)
571
/usr/lib/python3.6/urllib/request.py in _call_chain(self, chain, kind, meth_name, *args)
503 func = getattr(handler, meth_name)
--> 504 result = func(*args)
505 if result is not None:
/usr/lib/python3.6/urllib/request.py in http_error_default(self, req, fp, code, msg, hdrs)
649 def http_error_default(self, req, fp, code, msg, hdrs):
--> 650 raise HTTPError(req.full_url, code, msg, hdrs, fp)
651
HTTPError: HTTP Error 504: Gateway Time-out
During handling of the above exception, another exception occurred:
HTTPError Traceback (most recent call last)
<ipython-input-5-f304ccbde1d0> in <module>()
13
14 # Read the ;PDF file
---> 15 parsed = parser.from_file('/content/gdrive/My Drive/Colab Notebooks/data/sample_pdf_for_excel.pdf')
16 # content = parsed["content"].strip()
17
/usr/local/lib/python3.6/dist-packages/tika/parser.py in from_file(filename, serverEndpoint, xmlContent, headers, config_path)
34 '''
35 if not xmlContent:
---> 36 jsonOutput = parse1('all', filename, serverEndpoint, headers=headers, config_path=config_path)
37 else:
38 jsonOutput = parse1('all', filename, serverEndpoint, services={'meta': '/meta', 'text': '/tika', 'all': '/rmeta/xml'},
/usr/local/lib/python3.6/dist-packages/tika/tika.py in parse1(option, urlOrPath, serverEndpoint, verbose, tikaServerJar, responseMimeType, services, rawResponse, headers, config_path)
326 if service == '/tika': responseMimeType = 'text/plain'
327 status, response = callServer('put', serverEndpoint, service, open(path, 'rb'),
--> 328 headers, verbose, tikaServerJar, config_path=config_path, rawResponse=rawResponse)
329
330 if file_type == 'remote': os.unlink(path)
/usr/local/lib/python3.6/dist-packages/tika/tika.py in callServer(verb, serverEndpoint, service, data, headers, verbose, tikaServerJar, httpVerbs, classpath, rawResponse, config_path)
520 global TikaClientOnly
521 if not TikaClientOnly:
--> 522 serverEndpoint = checkTikaServer(scheme, serverHost, port, tikaServerJar, classpath, config_path)
523
524 serviceUrl = serverEndpoint + service
/usr/local/lib/python3.6/dist-packages/tika/tika.py in checkTikaServer(scheme, serverHost, port, tikaServerJar, classpath, config_path)
569 if not alreadyRunning:
570 if not os.path.isfile(jarPath) and urlp.scheme != '':
--> 571 getRemoteJar(tikaServerJar, jarPath)
572
573 if not checkJarSig(tikaServerJar, jarPath):
/usr/local/lib/python3.6/dist-packages/tika/tika.py in getRemoteJar(urlOrPath, destPath)
724 if os.path.exists(destPath) and os.path.isfile(destPath):
725 os.remove(destPath)
--> 726 urlretrieve(urlOrPath, destPath)
727
728 return (destPath, 'remote')
/usr/lib/python3.6/urllib/request.py in urlretrieve(url, filename, reporthook, data)
246 url_type, path = splittype(url)
247
--> 248 with contextlib.closing(urlopen(url, data)) as fp:
249 headers = fp.info()
250
/usr/lib/python3.6/urllib/request.py in urlopen(url, data, timeout, cafile, capath, cadefault, context)
221 else:
222 opener = _opener
--> 223 return opener.open(url, data, timeout)
224
225 def install_opener(opener):
/usr/lib/python3.6/urllib/request.py in open(self, fullurl, data, timeout)
530 for processor in self.process_response.get(protocol, []):
531 meth = getattr(processor, meth_name)
--> 532 response = meth(req, response)
533
534 return response
/usr/lib/python3.6/urllib/request.py in http_response(self, request, response)
640 if not (200 <= code < 300):
641 response = self.parent.error(
--> 642 'http', request, response, code, msg, hdrs)
643
644 return response
/usr/lib/python3.6/urllib/request.py in error(self, proto, *args)
568 if http_err:
569 args = (dict, 'default', 'http_error_default') + orig_args
--> 570 return self._call_chain(*args)
571
572 # XXX probably also want an abstract factory that knows when it makes
/usr/lib/python3.6/urllib/request.py in _call_chain(self, chain, kind, meth_name, *args)
502 for handler in handlers:
503 func = getattr(handler, meth_name)
--> 504 result = func(*args)
505 if result is not None:
506 return result
/usr/lib/python3.6/urllib/request.py in http_error_default(self, req, fp, code, msg, hdrs)
648 class HTTPDefaultErrorHandler(BaseHandler):
649 def http_error_default(self, req, fp, code, msg, hdrs):
--> 650 raise HTTPError(req.full_url, code, msg, hdrs, fp)
651
652 class HTTPRedirectHandler(BaseHandler):
HTTPError: HTTP Error 504: Gateway Time-out
Java-версия
!java -version
openjdk version "11.0.3" 2019-04-16
OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu218.04.1)
OpenJDK 64-Bit Server VM (build 11.0.3+7-Ubuntu-1ubuntu218.04.1, mixed mode, sharing)
На другой машине, где я попробовал тот же код
> java -version
java version "1.8.0_172"
Java(TM) SE Runtime Environment (build 1.8.0_172-b11)
Java HotSpot(TM) Client VM (build 25.172-b11, mixed mode, sharing)
Когда я нажимаю ссылку Java (поиск Maven) http://search.maven.org/remotecontent?filepath=org/apache/tika/tika-server/1.19/tika-server-1.19.jar, это дает 504 Время ожидания шлюза
Пожалуйста, предложите.