Estou iniciando um projeto para fins de estudo. Gostaria de um script que precisaria consumir dados do site (Reclame Aqui) de empresas específicas. Tentei contatá-los para ver se poderiam fornecer uma API, mas não conseguiram. Tentei fazer scraping, mas mesmo tentando reduzir o número de chamadas, o resultado foi "muitas requisições". Alguém sabe como posso fazer isso? ------- edit ps: estou usando um notebook no anaconda Reclamações: "https://www.reclameaqui.com.br/empresa/santander/lista-reclamacoes/" Gostaria de pesquisar reclamações na lista de reclamações e salvá-las em um dataframe from selenium import webdriver from selenium.webdriver.chrome.service import Service from webdriver_manager.chrome import ChromeDriverManager from selenium.webdriver.common.by import By import pandas as pd import time # Iniciar navegador (visível) driver = webdriver.Chrome(service=Service(ChromeDriverManager().install())) # Acessar a página url = "https://www.reclameaqui.com.br/empresa/santander/lista-reclamacoes/" driver.get(url) time.sleep(10) # Espera o carregamento completo # Seleciona os cards de reclamações cards = driver.find_elements(By.CSS_SELECTOR, "div.rai-card") # Coletar as 5 primeiras reclamacoes = [] for card in cards[:5]: try: titulo = card.find_element(By.CSS_SELECTOR, "h4").text data = card.find_element(By.CSS_SELECTOR, "span.rai-card-subtitle").text resumo = card.find_element(By.CSS_SELECTOR, "p").text status = card.find_element(By.CSS_SELECTOR, "div.rai-status-label").text reclamacoes.append({ "Título": titulo, "Data": data, "Resumo": resumo, "Status": status }) except Exception as e: print("Erro ao extrair uma reclamação:", e) # Encerrar navegador driver.quit() # Salvar em CSV df = pd.DataFrame(reclamacoes) df.to_csv("reclamacoes_santander.csv", index=False, encoding="utf-8") print("✅ Arquivo CSV criado com sucesso: reclamacoes_santander.csv") in this part: Pegar os blocos cards = driver.find_elements(By.CSS_SELECTOR, "div.rai-card") # seletor genérico mais seguro ERRO: ConnectionRefusedError Traceback (most recent call last) ~\anaconda3\lib\site-packages\urllib3\connection.py in _new_conn(self) 168 try: --> 169 conn = connection.create_connection( 170 (self._dns_host, self.port), self.timeout, **extra_kw ~\anaconda3\lib\site-packages\urllib3\util\connection.py in create_connection(address, timeout, source_address, socket_options) 95 if err is not None: ---> 96 raise err 97 ~\anaconda3\lib\site-packages\urllib3\util\connection.py in create_connection(address, timeout, source_address, socket_options) 85 sock.bind(source_address) ---> 86 sock.connect(sa) 87 return sock ConnectionRefusedError: [WinError 10061] Nenhuma conexão pôde ser feita porque a máquina de destino as recusou ativamente During handling of the above exception, another exception occurred: NewConnectionError Traceback (most recent call last) ~\anaconda3\lib\site-packages\urllib3\connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw) 698 # Make the request on the httplib connection object. --> 699 httplib_response = self._make_request( 700 conn, ~\anaconda3\lib\site-packages\urllib3\connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw) 393 else: --> 394 conn.request(method, url, **httplib_request_kw) 395 ~\anaconda3\lib\site-packages\urllib3\connection.py in request(self, method, url, body, headers) 233 headers["User-Agent"] = _get_default_user_agent() --> 234 super(HTTPConnection, self).request(method, url, body=body, headers=headers) 235 ~\anaconda3\lib\http\client.py in request(self, method, url, body, headers, encode_chunked) 1254 """Send a complete request to the server.""" -> 1255 self._send_request(method, url, body, headers, encode_chunked) 1256 ~\anaconda3\lib\http\client.py in _send_request(self, method, url, body, headers, encode_chunked) 1300 body = _encode(body, 'body') -> 1301 self.endheaders(body, encode_chunked=encode_chunked) 1302 ~\anaconda3\lib\http\client.py in endheaders(self, message_body, encode_chunked) 1249 raise CannotSendHeader() -> 1250 self._send_output(message_body, encode_chunked=encode_chunked) 1251 ~\anaconda3\lib\http\client.py in _send_output(self, message_body, encode_chunked) 1009 del self._buffer[:] -> 1010 self.send(msg) 1011 ~\anaconda3\lib\http\client.py in send(self, data) 949 if self.auto_open: --> 950 self.connect() 951 else: ~\anaconda3\lib\site-packages\urllib3\connection.py in connect(self) 199 def connect(self): --> 200 conn = self._new_conn() 201 self._prepare_conn(conn) ~\anaconda3\lib\site-packages\urllib3\connection.py in _new_conn(self) 180 except SocketError as e: --> 181 raise NewConnectionError( 182 self, "Failed to establish a new connection: %s" % e NewConnectionError: <urllib3.connection.HTTPConnection object at 0x000001ECD88CFB50>: Failed to establish a new connection: [WinError 10061] Nenhuma conexão pôde ser feita porque a máquina de destino as recusou ativamente During handling of the above exception, another exception occurred: MaxRetryError Traceback (most recent call last) <ipython-input-15-9066030c2018> in <module> 1 # Pegar os blocos ----> 2 cards = driver.find_elements(By.CSS_SELECTOR, "div.rai-card") # seletor genérico mais seguro ~\anaconda3\lib\site-packages\selenium\webdriver\remote\webdriver.py in find_elements(self, by, value) 790 # Return empty list if driver returns null 791 # See https://github.com/SeleniumHQ/selenium/issues/4555 --> 792 return self.execute(Command.FIND_ELEMENTS, {"using": by, "value": value})["value"] or [] 793 794 @property ~\anaconda3\lib\site-packages\selenium\webdriver\remote\webdriver.py in execute(self, driver_command, params) 380 params["sessionId"] = self.session_id 381 --> 382 response = self.command_executor.execute(driver_command, params) 383 if response: 384 self.error_handler.check_response(response) ~\anaconda3\lib\site-packages\selenium\webdriver\remote\remote_connection.py in execute(self, command, params) 402 trimmed = self._trim_large_entries(params) 403 LOGGER.debug("%s %s %s", command_info[0], url, str(trimmed)) --> 404 return self._request(command_info[0], url, body=data) 405 406 def _request(self, method, url, body=None): ~\anaconda3\lib\site-packages\selenium\webdriver\remote\remote_connection.py in _request(self, method, url, body) 426 427 if self._client_config.keep_alive: --> 428 response = self._conn.request(method, url, body=body, headers=headers, timeout=self._client_config.timeout) 429 statuscode = response.status 430 else: ~\anaconda3\lib\site-packages\urllib3\request.py in request(self, method, url, fields, headers, **urlopen_kw) 76 ) 77 else: ---> 78 return self.request_encode_body( 79 method, url, fields=fields, headers=headers, **urlopen_kw 80 ) ~\anaconda3\lib\site-packages\urllib3\request.py in request_encode_body(self, method, url, fields, headers, encode_multipart, multipart_boundary, **urlopen_kw) 168 extra_kw.update(urlopen_kw) 169 --> 170 return self.urlopen(method, url, **extra_kw) ~\anaconda3\lib\site-packages\urllib3\poolmanager.py in urlopen(self, method, url, redirect, **kw) 373 response = conn.urlopen(method, url, **kw) 374 else: --> 375 response = conn.urlopen(method, u.request_uri, **kw) 376 377 redirect_location = redirect and response.get_redirect_location() ~\anaconda3\lib\site-packages\urllib3\connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw) 781 "Retrying (%r) after connection broken by '%r': %s", retries, err, url 782 ) --> 783 return self.urlopen( 784 method, 785 url, ~\anaconda3\lib\site-packages\urllib3\connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw) 781 "Retrying (%r) after connection broken by '%r': %s", retries, err, url 782 ) --> 783 return self.urlopen( 784 method, 785 url, ~\anaconda3\lib\site-packages\urllib3\connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw) 781 "Retrying (%r) after connection broken by '%r': %s", retries, err, url 782 ) --> 783 return self.urlopen( 784 method, 785 url, ~\anaconda3\lib\site-packages\urllib3\connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw) 753 e = ProtocolError("Connection aborted.", e) 754 --> 755 retries = retries.increment( 756 method, url, error=e, _pool=self, _stacktrace=sys.exc_info()[2] 757 ) ~\anaconda3\lib\site-packages\urllib3\util\retry.py in increment(self, method, url, response, error, _pool, _stacktrace) 572 573 if new_retry.is_exhausted(): --> 574 raise MaxRetryError(_pool, url, error or ResponseError(cause)) 575 576 log.debug("Incremented Retry for (url='%s'): %r", url, new_retry) MaxRetryError: HTTPConnectionPool(host='localhost', port=16453): Max retries exceeded with url: /session/c82213a39cb17d63a2f4a28a808732fb/elements (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x000001ECD88CFB50>: Failed to establish a new connection: [WinError 10061] Nenhuma conexão pôde ser feita porque a máquina de destino as recusou ativamente')) Continue reading...
