Ниже приведена трассировка стека на конце терминала в Ubuntu. Даже моя анакинда тратит слишком много времени на открытие (около 20 минут).
Traceback (most recent call last):
File "/home/narendra/anaconda3/lib/python3.7/urllib/request.py", line 1317, in do_open
encode_chunked=req.has_header('Transfer-encoding'))
File "/home/narendra/anaconda3/lib/python3.7/http/client.py", line 1244, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/home/narendra/anaconda3/lib/python3.7/http/client.py", line 1290, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/home/narendra/anaconda3/lib/python3.7/http/client.py", line 1239, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/home/narendra/anaconda3/lib/python3.7/http/client.py", line 1026, in _send_output
self.send(msg)
File "/home/narendra/anaconda3/lib/python3.7/http/client.py", line 966, in send
self.connect()
File "/home/narendra/anaconda3/lib/python3.7/http/client.py", line 1406, in connect
super().connect()
File "/home/narendra/anaconda3/lib/python3.7/http/client.py", line 938, in connect
(self.host,self.port), self.timeout, self.source_address)
File "/home/narendra/anaconda3/lib/python3.7/socket.py", line 727, in create_connection
raise err
File "/home/narendra/anaconda3/lib/python3.7/socket.py", line 716, in create_connection
sock.connect(sa)
TimeoutError: [Errno 110] Connection timed out
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "TASK_1.py", line 23, in <module>
response = urllib.request.urlopen(line,context=gcontext)
File "/home/narendra/anaconda3/lib/python3.7/urllib/request.py", line 222, in urlopen
return opener.open(url, data, timeout)
File "/home/narendra/anaconda3/lib/python3.7/urllib/request.py", line 525, in open
response = self._open(req, data)
File "/home/narendra/anaconda3/lib/python3.7/urllib/request.py", line 543, in _open
'_open', req)
File "/home/narendra/anaconda3/lib/python3.7/urllib/request.py", line 503, in _call_chain
result = func(*args)
File "/home/narendra/anaconda3/lib/python3.7/urllib/request.py", line 1360, in https_open
context=self._context, check_hostname=self._check_hostname)
File "/home/narendra/anaconda3/lib/python3.7/urllib/request.py", line 1319, in do_open
raise URLError(err)
urllib.error.URLError: <urlopen error [Errno 110] Connection timed out>
ниже - мой код.
this Код извлекает данные Url в файл
, один за другим выбирает URL для url.txt
, затем извлекает все данные страницы из этого конкретного URL.
import urllib.request, urllib.error, urllib.parse
import io
import ssl
#localhost, 127.0.0.0/8, ::1, 10.0.0.0/8
# using readline() that reads file line by line.
file1 = open("url.txt", "r")
count = 0
gcontext = ssl.SSLContext()`
для i в диапазоне (18): количество + = 1
# Getting the next line from file
line = file1.readline()
# if line is empty
# end of file is reached
if not line:
break
response = urllib.request.urlopen(line,context=gcontext)
webContent = response.read()
with io.open("file_" + str(i) + ".txt", 'w', encoding='utf-8') as f:
f.write(webContent)
f.close()