I’m trying to retrieve audio files via URLs retrieved from conllu files. I receive the link, but when I want to download the file, I get the following error, while when I enter the link on the browser I manage to download the file, however I have more than 300 audio files to collect, I can’t collect them all manually. Can you help me ?
Here is my code:
import os
import re
import urllib.request
from conll3 import *
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
def extract_and_save_wav(file_path, output_directory):
"""
Extracts and saves WAV audio file from a data file.
Args:
file_path (str): Path of the data file.
output_directory (str): Output directory for the WAV audio file.
Return:
str or None: Path of the extracted and saved WAV audio file, or None if no audio file is found.
"""
for root, dirs, files in os.walk(directory_path):
for file in files:
if file.endswith(".conllu"):
file_path = os.path.join(root, file)
trees = conllFile2trees(file_path)
print(file_path)
for tree in trees:
tree_str = str(tree)
sound_url_match = re.search(r'# sound_url = (.+)', tree_str) # Recherche de l'URL du fichier audio
if sound_url_match:
sound_url = sound_url_match.group(1)
print(sound_url)
if sound_url.endswith('.wav'):
file_name = os.path.basename(file_path)
file_name_without_ext = os.path.splitext(file_name)[0]
output_file_name = f"{file_name_without_ext}.wav"
if output_directory is not None:
output_path = os.path.join(output_directory, output_file_name)
urllib.request.urlretrieve(sound_url, output_path) # Téléchargement et sauvegarde du fichier audio
return output_path
return None
directory_path = "../SUD_Naija-NSC-master/non_gold/"
output_wav = "../WAV/non_gold/"
extract_and_save_wav(directory_path, output_wav)
Here is the error message:
Reloaded modules: conll3
../SUD_Naija-NSC-master/non_gold/LAG_01_Hairdressing_M.conllu
Traceback (most recent call last):
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:1348 in do_open
h.request(req.get_method(), req.selector, req.data, headers,
File ~/miniconda3/envs/tal-ml/lib/python3.10/http/client.py:1283 in request
self._send_request(method, url, body, headers, encode_chunked)
File ~/miniconda3/envs/tal-ml/lib/python3.10/http/client.py:1329 in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File ~/miniconda3/envs/tal-ml/lib/python3.10/http/client.py:1278 in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File ~/miniconda3/envs/tal-ml/lib/python3.10/http/client.py:1038 in _send_output
self.send(msg)
File ~/miniconda3/envs/tal-ml/lib/python3.10/http/client.py:976 in send
self.connect()
File ~/miniconda3/envs/tal-ml/lib/python3.10/http/client.py:1455 in connect
self.sock = self._context.wrap_socket(self.sock,
File ~/miniconda3/envs/tal-ml/lib/python3.10/ssl.py:513 in wrap_socket
return self.sslsocket_class._create(
File ~/miniconda3/envs/tal-ml/lib/python3.10/ssl.py:1071 in _create
self.do_handshake()
File ~/miniconda3/envs/tal-ml/lib/python3.10/ssl.py:1342 in do_handshake
self._sslobj.do_handshake()
SSLError: [SSL: UNSAFE_LEGACY_RENEGOTIATION_DISABLED] unsafe legacy renegotiation disabled (_ssl.c:1007)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File ~/miniconda3/envs/tal-ml/lib/python3.10/site-packages/spyder_kernels/py3compat.py:356 in compat_exec
exec(code, globals, locals)
File ~/Desktop/Stage 2023-2024/Python/recuperation_audio.py:47
extract_and_save_wav(directory_path, output_wav)
File ~/Desktop/Stage 2023-2024/Python/recuperation_audio.py:39 in extract_and_save_wav
urllib.request.urlretrieve(sound_url, output_path) # Téléchargement et sauvegarde du fichier audio
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:241 in urlretrieve
with contextlib.closing(urlopen(url, data)) as fp:
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:216 in urlopen
return opener.open(url, data, timeout)
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:525 in open
response = meth(req, response)
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:634 in http_response
response = self.parent.error(
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:557 in error
result = self._call_chain(*args)
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:496 in _call_chain
result = func(*args)
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:749 in http_error_302
return self.parent.open(new, timeout=req.timeout)
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:519 in open
response = self._open(req, data)
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:536 in _open
result = self._call_chain(self.handle_open, protocol, protocol +
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:496 in _call_chain
result = func(*args)
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:1391 in https_open
return self.do_open(http.client.HTTPSConnection, req,
File ~/miniconda3/envs/tal-ml/lib/python3.10/urllib/request.py:1351 in do_open
raise URLError(err)
URLError: <urlopen error [SSL: UNSAFE_LEGACY_RENEGOTIATION_DISABLED] unsafe legacy renegotiation disabled (_ssl.c:1007)>
>Solution :
Here is an example how you can twak the https:// adapter to accept connections like these:
import ssl
import warnings
import requests
import requests.packages.urllib3.exceptions as urllib3_exceptions
warnings.simplefilter("ignore", urllib3_exceptions.InsecureRequestWarning)
class TLSAdapter(requests.adapters.HTTPAdapter):
def init_poolmanager(self, *args, **kwargs):
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.set_ciphers("DEFAULT@SECLEVEL=1")
ctx.options |= 0x4
kwargs["ssl_context"] = ctx
return super(TLSAdapter, self).init_poolmanager(*args, **kwargs)
url = "http://naijasyncor.huma-num.fr/carte/mp3/LAG_01_Hairdressing_M.wav"
with requests.session() as s:
s.mount("https://", TLSAdapter())
response = s.get(url)
with open("LAG_01_Hairdressing_M.wav", "wb") as f_out:
f_out.write(response.content)
This downloads LAG_01_Hairdressing_M.wav:
$ ls -alF *wav
-rw-r--r-- 1 root root 14044900 oct 30 22:17 LAG_01_Hairdressing_M.wav