Skip to content
This repository was archived by the owner on Jul 17, 2025. It is now read-only.

Unable to download corpora other than English #11

@wangxuxuxuw

Description

@wangxuxuxuw

Downloading mtedx_el.tgz from https://www.openslr.org/resources/100/mtedx_el.tgz
Traceback (most recent call last):
File "/home/w30043779/miniconda3/lib/python3.10/urllib/request.py", line 1348, in do_open
h.request(req.get_method(), req.selector, req.data, headers,
File "/home/w30043779/miniconda3/lib/python3.10/http/client.py", line 1282, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/home/w30043779/miniconda3/lib/python3.10/http/client.py", line 1328, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/home/w30043779/miniconda3/lib/python3.10/http/client.py", line 1277, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/home/w30043779/miniconda3/lib/python3.10/http/client.py", line 1037, in _send_output
self.send(msg)
File "/home/w30043779/miniconda3/lib/python3.10/http/client.py", line 975, in send
self.connect()
File "/home/w30043779/miniconda3/lib/python3.10/http/client.py", line 1454, in connect
self.sock = self._context.wrap_socket(self.sock,
File "/home/w30043779/miniconda3/lib/python3.10/ssl.py", line 513, in wrap_socket
return self.sslsocket_class._create(
File "/home/w30043779/miniconda3/lib/python3.10/ssl.py", line 1071, in _create
self.do_handshake()
File "/home/w30043779/miniconda3/lib/python3.10/ssl.py", line 1342, in do_handshake
self._sslobj.do_handshake()
ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self signed certificate in certificate chain (_ssl.c:997)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/w30043779/code1/muavic-main/utils.py", line 62, in download_file
wget.download(url, out=str(download_path / filename), bar=custom_bar)
File "/home/w30043779/miniconda3/lib/python3.10/site-packages/wget.py", line 526, in download
(tmpfile, headers) = ulib.urlretrieve(binurl, tmpfile, callback)
File "/home/w30043779/miniconda3/lib/python3.10/urllib/request.py", line 241, in urlretrieve
with contextlib.closing(urlopen(url, data)) as fp:
File "/home/w30043779/miniconda3/lib/python3.10/urllib/request.py", line 216, in urlopen
return opener.open(url, data, timeout)
File "/home/w30043779/miniconda3/lib/python3.10/urllib/request.py", line 519, in open
response = self._open(req, data)
File "/home/w30043779/miniconda3/lib/python3.10/urllib/request.py", line 536, in _open
result = self._call_chain(self.handle_open, protocol, protocol +
File "/home/w30043779/miniconda3/lib/python3.10/urllib/request.py", line 496, in _call_chain
result = func(*args)
File "/home/w30043779/miniconda3/lib/python3.10/urllib/request.py", line 1391, in https_open
return self.do_open(http.client.HTTPSConnection, req,
File "/home/w30043779/miniconda3/lib/python3.10/urllib/request.py", line 1351, in do_open
raise URLError(err)
urllib.error.URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self signed certificate in certificate chain (_ssl.c:997)>

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/w30043779/code1/muavic-main/get_data.py", line 115, in
main(args)
File "/home/w30043779/code1/muavic-main/get_data.py", line 84, in main
prepare_mtedx(args)
File "/home/w30043779/code1/muavic-main/get_data.py", line 15, in prepare_mtedx
download_mtedx_data(args["mtedx"], args["src_lang"], args["src_lang"])
File "/home/w30043779/code1/muavic-main/mtedx_utils.py", line 27, in download_mtedx_data
download_extract_file_if_not(
File "/home/w30043779/code1/muavic-main/utils.py", line 89, in download_extract_file_if_not
download_file(url, download_path)
File "/home/w30043779/code1/muavic-main/utils.py", line 65, in download_file
raise HTTPError(e.url, e.code, message, e.hdrs, e.fp)
AttributeError: 'URLError' object has no attribute 'url'

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions