Ошибка при парсинге сайтов на pycharm
При попытке достать код сайта вылезает множество ошибок, но если поменять сайт то всё заработает, код ошибки ниже
Traceback (most recent call last):
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\urllib3\connectionpool.py", line 703, in urlopen
httplib_response = self._make_request(
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\urllib3\connectionpool.py", line 449, in _make_request
six.raise_from(e, None)
File "<string>", line 3, in raise_from
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\urllib3\connectionpool.py", line 444, in _make_request
httplib_response = conn.getresponse()
File "D:\Projects. Pycharm\Python\lib\http\client.py", line 1374, in getresponse
response.begin()
File "D:\Projects. Pycharm\Python\lib\http\client.py", line 318, in begin
version, status, reason = self._read_status()
File "D:\Projects. Pycharm\Python\lib\http\client.py", line 287, in _read_status
raise RemoteDisconnected("Remote end closed connection without"
http.client.RemoteDisconnected: Remote end closed connection without response
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\requests\adapters.py", line 489, in send
resp = conn.urlopen(
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\urllib3\connectionpool.py", line 787, in urlopen
retries = retries.increment(
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\urllib3\util\retry.py", line 550, in increment
raise six.reraise(type(error), error, _stacktrace)
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\urllib3\packages\six.py", line 769, in reraise
raise value.with_traceback(tb)
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\urllib3\connectionpool.py", line 703, in urlopen
httplib_response = self._make_request(
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\urllib3\connectionpool.py", line 449, in _make_request
six.raise_from(e, None)
File "<string>", line 3, in raise_from
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\urllib3\connectionpool.py", line 444, in _make_request
httplib_response = conn.getresponse()
File "D:\Projects. Pycharm\Python\lib\http\client.py", line 1374, in getresponse
response.begin()
File "D:\Projects. Pycharm\Python\lib\http\client.py", line 318, in begin
version, status, reason = self._read_status()
File "D:\Projects. Pycharm\Python\lib\http\client.py", line 287, in _read_status
raise RemoteDisconnected("Remote end closed connection without"
urllib3.exceptions.ProtocolError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\Костьян\Desktop\Projects\parsing\TEST PARSING.py", line 4, in <module>
url = requests.get(url)
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\requests\api.py", line 73, in get
return request("get", url, params=params, **kwargs)
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\requests\api.py", line 59, in request
return session.request(method=method, url=url, **kwargs)
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\requests\sessions.py", line 587, in request
resp = self.send(prep, **send_kwargs)
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\requests\sessions.py", line 701, in send
r = adapter.send(request, **kwargs)
File "C:\Users\Костьян\Desktop\Projects\venv\lib\site-packages\requests\adapters.py", line 547, in send
raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))
Ответы (1 шт):
Автор решения: ZxNuClear
→ Ссылка
Попробуй вот так
import requests
url = 'https://tursportopt.ru/category/rybolovnye-tovary-optom/'
headers = requests.utils.default_headers()
headers.update(
{
'User-Agent': 'My User Agent 1.0',
}
)
response = requests.get(url, headers=headers)
print(response.text)