如何解决Python Tika 错误:URLError: <urlopen error unknown url type: c>
我一直在使用很多 python tika 从一些 pdf 文件中提取文本。突然 Tika 不再使用以下代码和类似代码:
from tika import parser
document = parser.from_file("prova.pdf")['content']
或
from tika import parser
parser.from_file("C:/Users/Daniele/Desktop/progetto_tesi_magistrale/prova.pdf")['content']
每次我收到此错误时:
2021-02-23 10:57:36,244 [MainThread ] [INFO ] Retrieving C:\Program Files\tika-server-1.24.1.jar to C:\Users\Daniele\AppData\Local\Temp\tika-server.jar.
---------------------------------------------------------------------------
URLError Traceback (most recent call last)
~\anaconda3\lib\site-packages\tika\tika.py in getRemoteJar(urlOrPath,destPath)
797 try:
--> 798 urlretrieve(urlOrPath,destPath)
799 except IOError:
~\anaconda3\lib\urllib\request.py in urlretrieve(url,filename,reporthook,data)
246
--> 247 with contextlib.closing(urlopen(url,data)) as fp:
248 headers = fp.info()
~\anaconda3\lib\urllib\request.py in urlopen(url,data,timeout,cafile,capath,cadefault,context)
221 opener = _opener
--> 222 return opener.open(url,timeout)
223
~\anaconda3\lib\urllib\request.py in open(self,fullurl,timeout)
524 sys.audit('urllib.Request',req.full_url,req.data,req.headers,req.get_method())
--> 525 response = self._open(req,data)
526
~\anaconda3\lib\urllib\request.py in _open(self,req,data)
546
--> 547 return self._call_chain(self.handle_open,'unkNown',548 'unkNown_open',req)
~\anaconda3\lib\urllib\request.py in _call_chain(self,chain,kind,meth_name,*args)
501 func = getattr(handler,meth_name)
--> 502 result = func(*args)
503 if result is not None:
~\anaconda3\lib\urllib\request.py in unkNown_open(self,req)
1420 type = req.type
-> 1421 raise URLError('unkNown url type: %s' % type)
1422
URLError: <urlopen error unkNown url type: c>
During handling of the above exception,another exception occurred:
URLError Traceback (most recent call last)
<ipython-input-4-5aa5aa48deec> in <module>
1 from tika import parser
2
----> 3 document = parser.from_file("prova.pdf")['content']
4 #import tika
5 #from tika import parser
~\anaconda3\lib\site-packages\tika\parser.py in from_file(filename,serverEndpoint,service,xmlContent,headers,config_path,requestOptions)
38 '''
39 if not xmlContent:
---> 40 output = parse1(service,headers=headers,config_path=config_path,requestOptions=requestOptions)
41 else:
42 output = parse1(service,services={'Meta': '/Meta','text': '/tika','all': '/rMeta/xml'},~\anaconda3\lib\site-packages\tika\tika.py in parse1(option,urlOrPath,verbose,tikaServerJar,responseMimeType,services,rawResponse,requestOptions)
334 headers.update({'Accept': responseMimeType,'Content-disposition': make_content_disposition_header(path.encode('utf-8') if type(path) is unicode_string else path)})
335 with urlOrPath if _is_file_object(urlOrPath) else open(path,'rb') as f:
--> 336 status,response = callServer('put',f,337 headers,338 rawResponse=rawResponse,requestOptions=requestOptions)
~\anaconda3\lib\site-packages\tika\tika.py in callServer(verb,httpVerbs,classpath,requestOptions)
529 global TikaClientOnly
530 if not TikaClientOnly:
--> 531 serverEndpoint = checkTikaServer(scheme,serverHost,port,config_path)
532
533 serviceUrl = serverEndpoint + service
~\anaconda3\lib\site-packages\tika\tika.py in checkTikaServer(scheme,config_path)
590 if not alreadyRunning:
591 if not os.path.isfile(jarPath) and urlp.scheme != '':
--> 592 getRemoteJar(tikaServerJar,jarPath)
593
594 if not checkJarSig(tikaServerJar,jarPath):
~\anaconda3\lib\site-packages\tika\tika.py in getRemoteJar(urlOrPath,destPath)
806 if os.path.exists(destPath) and os.path.isfile(destPath):
807 os.remove(destPath)
--> 808 urlretrieve(urlOrPath,destPath)
809
810 return (destPath,'remote')
~\anaconda3\lib\urllib\request.py in urlretrieve(url,data)
245 url_type,path = _splittype(url)
246
--> 247 with contextlib.closing(urlopen(url,data)) as fp:
248 headers = fp.info()
249
~\anaconda3\lib\urllib\request.py in urlopen(url,context)
220 else:
221 opener = _opener
--> 222 return opener.open(url,timeout)
223
224 def install_opener(opener):
~\anaconda3\lib\urllib\request.py in open(self,timeout)
523
524 sys.audit('urllib.Request',data)
526
527 # post-process response
~\anaconda3\lib\urllib\request.py in _open(self,data)
545 return result
546
--> 547 return self._call_chain(self.handle_open,req)
549
~\anaconda3\lib\urllib\request.py in _call_chain(self,*args)
500 for handler in handlers:
501 func = getattr(handler,meth_name)
--> 502 result = func(*args)
503 if result is not None:
504 return result
~\anaconda3\lib\urllib\request.py in unkNown_open(self,req)
1419 def unkNown_open(self,req):
1420 type = req.type
-> 1421 raise URLError('unkNown url type: %s' % type)
1422
1423 def parse_keqv_list(l):
URLError: <urlopen error unkNown url type: c>
我试图卸载 tika python、tika 服务器、java、python ......基本上所有的东西。奇怪的是,我的第二台电脑突然出现了同样的问题。 有什么建议么 ?非常感谢。
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。